检索结果-内蒙古大学图书馆

Flexible Vertical Federated Learning With Heterogeneous Parties

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第12期35卷 17878-17892页

作者： Castiglia, Timothy Wang, Shiqiang Patterson, Stacy Ab Initio Software Lexington MA 02421 USA IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA Rensselaer Polytech Inst Dept Comp Sci Troy NY 12180 USA

We propose flexible vertical federated learning (Flex-VFL), a distributed machine algorithm that trains a smooth, nonconvex function in a distributed system with vertically partitioned data. We consider a system with several parties that wish to collaboratively learn a global function. Each party holds a local dataset;the datasets have different features but share the same sample ID space. The parties are heterogeneous in nature: the parties' operating speeds, local model architectures, and optimizers may be different from one another and, further, they may change over time. To train a global model in such a system, Flex-VFL utilizes a form of parallel block coordinate descent (P-BCD), where parties train a partition of the global model via stochastic coordinate descent. We provide theoretical convergence analysis for Flex-VFL and show that the convergence rate is constrained by the party speeds and local optimizer parameters. We apply this analysis and extend our algorithm to adapt party learning rates in response to changing speeds and local optimizer parameters. Finally, we compare the convergence time of Flex-VFL against synchronous and asynchronous VFL algorithms, as well as illustrate the effectiveness of our adaptive extension.

关键词： Algorithms computational and artificial intelligence convergence distributed algorithms federated learning machine learning mathematics neural networks nonconvex optimization stochastic gradient descent (SGD)

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Formulation to Compare 4-D Seismic and Reservoir Simulation Models

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2022年第5期52卷 3052-3065页

作者： Rollmann, Klaus Soriano-Vargas, Aurea Almeida, Forlan Davolio, Alessandra Schiozer, Denis Jose Rocha, Anderson Univ Estadual Campinas Inst Comp BR-13083872 Campinas SP Brazil

We propose a novel approach based on Deep Learning methods using a convolutional neural networks (CNNs) to compare observed four-dimensional (4-D) seismic data with reservoir simulation model results and select the simulation models with the best match. Our approach advantages are twofold: 1) it is not a pixel-based approach, as it learns spatial features through training examples and 2) it does not require the simulation model and 4-D seismic maps to be in the same domain, enabling a direct comparison of maps in the seismic domain with maps in the numerical simulation domain. Additionally, we present a new methodology to quantitatively assess the performance of each method relative to the expected results. For this purpose, we build an annotated dataset containing the maps that best match the 4-D seismic in different realistic scenarios while taking into account the specialists' knowledge. We apply our methodology to evaluate if a method is able to perform according to what specialists expect, considering the annotated data. We also propose an improvement to traditional methods using a statistical method to convert maps of different physical properties into a common property, which can be used as an alternative to avoid forward and/or inversion procedures commonly used to bring 4-D seismic and simulation data to the same domain. Finally, we present an extensive comparison, qualitative and quantitative, of our approaches with other methods in the literature, such as the traditional pixelwise strategy for maps in the same domain, and methods based on binarization of maps in different domains. The results show that our proposed methods are capable of more accurately identifying the best-matched models, according to the specialists' answers.

关键词： Data models Reservoirs Biological system modeling Uncertainty computational modeling Production Numerical models computational and artificial intelligence industry applications learning systems manufacturing industries multi-layer neural network neural networks petroleum industry semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Sparse Label Smoothing Regularization for Person Re-Identification

引用

IEEE ACCESS 2019年 7卷 27899-27910页

作者： Ainam, Jean-Paul Qin, Ke Liu, Guisong Luo, Guangchun Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Sichuan Peoples R China Adventist Cosendai Univ BP 04 Nanga Eboko Cameroon

Person re-identification (re-id) is a cross-camera retrieval task which establishes a correspondence between images of a person from multiple cameras. Deep learning methods have been successfully applied to this problem and have achieved impressive results. However, these methods require a large amount of labeled training data. Currently, the labeled datasets in person re-id are limited in their scale and manual acquisition of such large-scale datasets from surveillance cameras is a tedious and labor-intensive task. In this paper, we propose a framework that performs intelligent data augmentation and assigns the partial smoothing label to generated data. Our approachfirst exploits the clustering property of existing person re-id datasets to create groups of similar objects that model cross-view variations. Each group is then used to generate realistic images through adversarial training. Our aim is to emphasize the feature similarity between generated samples and the original samples. Finally, we assign a non-uniform label distribution to the generated samples and define a regularized loss function for training. The proposed approach tackles two problems 1) how to efficiently use the generated data and 2) how to address the over-smoothness problem found in current regularization methods. The extensive experiments on four large-scale datasets show that our regularization method significantly improves the re-id accuracy compared to existing methods.

关键词： computational and artificial intelligence artificial neural network feature extraction image retrieval

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence for sEMG-Based Muscular Movement Recognition for Hand Prosthesis

引用

IEEE ACCESS 2023年 11卷 38850-38863页

作者： Hye, Nafe Muhtasim Hany, Umma Chakravarty, Sumit Akter, Lutfa Ahmed, Imtiaz Ahsanullah Univ Sci & Technol Dept Elect & Elect Engn Dhaka 1208 Bangladesh Kennesaw State Univ Dept Elect & Comp Engn Marietta GA 30060 USA Bangladesh Univ Engn & Technol Dept Elect & Elect Engn Dhaka 1205 Bangladesh Howard Univ Dept Elect Engn & Comp Sci Washington DC 20059 USA

The muscular activities gathered by real-time myoelectric interfaces of surface electromyography (sEMG) can be used to develop myoelectric prosthetic hands for physically disabled people. However, the acquired myoelectric signals must be accurately classified in real time to properly control the operation of the external devices. In this study, we propose methods for detecting and classifying muscular activities using sEMG signals. These methods include outlier removal, data manipulation, data preprocessing, dimensionality reduction, and classification. We use the Ninapro database 1 (DB1) containing sEMG signals from 27 intact subjects while performing 53 hand movements repeatedly. We apply the Principle Component Analysis (PCA), Independent Component Analysis (ICA), and t-distributed Stochastic Neighbor Embedding (t-SNE) feature extraction methods for dimensionality reduction. Five machine learning (ML) algorithms and deep learning artificial neural networks (ANN) are applied for the classification of muscular movements. It is observed that for the recognition of 53 muscular movements of 27 subjects with preprocessed raw data, ANN obtains the highest accuracy of 93.92% for inter-subject and 97.73% for intra-subject movement recognition. Among the ML algorithms, K-Nearest Neighbors (KNN) performs the best with both t-SNE features and the preprocessed raw data in least computational time. With the preprocessed raw data, KNN obtains 93.174% and 97.458% for inter-subject and intra-subject movement classification, respectively while with the t-SNE features, KNN obtains 89.844% accuracy for inter-subject and 95.04% accuracy for intra-subject in reduced computational time.

关键词： Feature extraction Databases Electrodes Electromyography Real-time systems Prosthetic hand Gesture recognition computational and artificial intelligence biomedical signal processing

来源：评论

学校读者我要写书评

暂无评论

Data Fusion and IoT for Smart Ubiquitous Environments: A Survey

引用

IEEE ACCESS 2017年 5卷 9533-9554页

作者： Alam, Furqan Mehmood, Rashid Katib, Iyad Albogami, Nasser N. Albeshri, Aiiad King Abdulaziz Univ Fac Comp & Informat Technol Dept Comp Sci Jeddah 21589 Saudi Arabia King Abdulaziz Univ High Performance Comp Ctr Jeddah 21589 Saudi Arabia

The Internet of Things (IoT) is set to become one of the key technological developments of our times provided we are able to realize its full potential. The number of objects connected to IoT is expected to reach 50 billion by 2020 due to the massive influx of diverse objects emerging progressively. IoT, hence, is expected to be a major producer of big data. Sharing and collaboration of data and other resources would be the key for enabling sustainable ubiquitous environments, such as smart cities and societies. A timely fusion and analysis of big data, acquired from IoT and other sources, to enable highly efficient, reliable, and accurate decision making and management of ubiquitous environments would be a grand future challenge. computational intelligence would play a key role in this challenge. A number of surveys exist on data fusion. However, these are mainly focused on specific application areas or classifications. The aim of this paper is to review literature on data fusion for IoT with a particular focus on mathematical methods ( including probabilistic methods, artificial intelligence, and theory of belief) and specific IoT environments ( distributed, heterogeneous, nonlinear, and object tracking environments). The opportunities and challenges for each of the mathematical methods and environments are given. Future developments, including emerging areas that would intrinsically benefit from data fusion and IoT, autonomous vehicles, deep learning for data fusion, and smart cities, are discussed.

关键词： Internet of Things big data data fusion computational and artificial intelligence high performance computing smart cities smart societies ubiquitous environments

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Computing Beyond Search and Location-Based Services Introduction

引用

IEEE INTERNET COMPUTING 2012年第2期16卷 12-16页

作者： Mehra, Pankaj Whodini

The holy grail of search is intent; of browsing, scent; and of classification, meaning. Each of these pillar technologies of the information age therefore depends critically on extracting and mining human context. Context awareness is the discipline that brings together technologies for extracting data about the larger human context and reasoning with that data at scale. It seeks to make the benefits of contextualization as pervasive in our lives as technology itself.

关键词： computational and artificial intelligence Context Awareness Pervasive Computing Ubiquitous Computing Context Aware Services Information Retrieval Information Filtering Recommender Systems

来源：评论

学校读者我要写书评

暂无评论

Generating and Adapting to Diverse Ad Hoc Partners in Hanabi

引用

IEEE TRANSACTIONS ON GAMES 2023年第2期15卷 228-241页

作者： Canaan, Rodrigo Gao, Xianbo Togelius, Julian Nealen, Andy Menzel, Stefan Cal Poly State Univ San Luis Obispo CA 93407 USA NYU Tandon Sch Engn Brooklyn NY 11201 USA Univ Southern Calif Los Angeles CA 90007 USA Honda Res Inst Europe GmbH D-63073 Offenbach Germany

Hanabi is a cooperative game that brings the problem of modeling other players to the forefront. In this game, coordinated groups of players can leverage preestablished conventions to great effect. In this article, we focus on ad hoc settings with no previous coordination between partners. We introduce a "Bayesian Meta-Agent" that maintains a belief distribution over hypotheses of partner policies. The policies that serve as initial hypotheses are generated using MAP-Elites, to ensure behavioral diversity. We evaluate an "Adaptive" version of the agent, which selects a response policy based on the updated belief distribution and a "Generalist" version, which selects a response based on the uniform prior. In short episodes of ten games with a consistent partner, the "Adaptive" version outperforms the "Generalist" when the training and evaluation populations are the same. This presents a first step toward an agent that can model its partner and adapt within a time frame that is compatible with human interaction.

关键词： Learning (artificial intelligence) Naive Bayes methods computational and artificial intelligence Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Deep learning for procedural content generation

引用

NEURAL COMPUTING & APPLICATIONS 2021年第1期33卷 19-37页

作者： Liu, Jialin Snodgrass, Sam Khalifa, Ahmed Risi, Sebastian Yannakakis, Georgios N. Togelius, Julian Southern Univ Sci & Technol Dept Comp Sci & Engn Guangdong Prov Key Lab Brain Inspired Intelligent Shenzhen Peoples R China Modlai Copenhagen Denmark NYU New York NY 10003 USA IT Univ Copenhagen Copenhagen Denmark Univ Malta Inst Digital Games Msida Malta Tech Univ Crete Khania Greece

Procedural content generation in video games has a long history. Existing procedural content generation methods, such as search-based, solver-based, rule-based and grammar-based methods have been applied to various content types such as levels, maps, character models, and textures. A research field centered on content generation in games has existed for more than a decade. More recently, deep learning has powered a remarkable range of inventions in content production, which are applicable to games. While some cutting-edge deep learning methods are applied on their own, others are applied in combination with more traditional methods, or in an interactive setting. This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation.

关键词： Procedural content generation Game design Deep learning Machine learning computational and artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Exploring the Factors Influencing Big Data Technology Acceptance

引用

IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT 2023年第5期70卷 1738-1753页

作者： Rahman, Nayem Daim, Tugrul Basoglu, Nuri Portland State Univ Portland OR 97201 USA Izmir Inst Technol TR-35430 Izmir Turkey

Big Data has received great attention in academic literature and industry papers. Most of the experiments and studies focused on publishing results of big data technologies development, machine learning algorithms, and data analytics. To the best of our knowledge, there is not yet any comprehensive empirical study in the academic literature on big data technology acceptance. The statistical results of this model provide a compelling explanation of the relationships among the antecedent variables and the dependent variables. The analysis of the structural model reveals that the hypothesis tests are significant for 8 out of 12 path relationships.

关键词： Big Data Data models Tools Taxonomy Task analysis Companies Business artificial intelligence business business data processing computational and artificial intelligence data systems engineering management decision support systems decision making expert systems intelligent systems knowledge based systems management technology management

来源：评论

学校读者我要写书评

暂无评论

Robust Traffic Speed Inference With Ensemble Learning

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第10期23卷 17241-17257页

作者： Yang, Zhou Sun, Heli Huang, Jianbin He, Liang Jia, Xiaolin Zhao, Jizhong Qiao, Shaojie Xi An Jiao Tong Univ Dept Comp Sci & Technol Xian 710000 Peoples R China Xidian Univ Sch Comp Sci & Technol Xian 710000 Peoples R China Chengdu Univ Informat Technol Sch Cybersecur Chengdu 610225 Peoples R China

Traffic speed inference enables many applications that are essential for everyday life. Most traffic-prediction approaches assume that a constant number of sensors are deployed on the roads, whether they are either stationary loop detectors or vehicles equipped with Global Positioning System (GPS) tracking devices. The static nature of those fixtures limits their ability to adapt to scenarios that are more dynamic. Rather than relying on several fixed sensors to detect changes and infer traffic, we use crowdsourcing to judiciously select individuals and then make predictions. Our solution consists of three core components: dynamic seed selection, regional cluster building and ensemble traffic prediction. In the first phase, we employ Efficient Transition Probability (ETP) to evaluate candidate seed sets. Road clusters are then formed using hierarchical clustering that is tweaked by a dynamic programming technique. This method assesses the eccentricity of every cluster to bond every road within each cluster more closely. Subsequently, we develop an ensemble-learning strategy in conjunction with Lasso regression to forecast traffic. The strength of our ensemble approach is its ability to manage absent seeds, a condition that has never been investigated, to our knowledge. Substantial experimental evaluation indicates that our claim of dynamic updates is valid and effective. Our solution outperforms the state-of-the-art techniques by a wide margin, in terms of prediction accuracy.

关键词： Vehicle dynamics Roads Tensors Sensors Predictive models Soft sensors Global Positioning System Intelligent transportation systems smart transportation computational and artificial intelligence machine learning clustering algorithms prediction methods

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：