检索结果-内蒙古大学图书馆

multivariate Gaussian and Student-t process regression for multi-output prediction

NEURAL COMPUTING & APPLICATIONS 2020年第8期32卷 3005-3028页

作者： Chen, Zexun Wang, Bo Gorban, Alexander N. Univ Leicester Dept Math Leicester LE1 7RH Leics England Univ Exeter Coll Engn Math & Phys Sci Exeter EX4 4QF Devon England

Gaussian process model for vector-valued function has been shown to be useful for multi-output prediction. The existing method for this model is to reformulate the matrix-variate Gaussian distribution as a multivariate normal distribution. Although it is effective in many cases, reformulation is not always workable and is difficult to apply to other distributions because not all matrix-variate distributions can be transformed to respective multivariate distributions, such as the case for matrix-variate Student-t distribution. In this paper, we propose a unified framework which is used not only to introduce a novel multivariate Student-t process regression model (MV-TPR) for multi-output prediction, but also to reformulate the multivariate Gaussian process regression (MV-GPR) that overcomes some limitations of the existing methods. Both MV-GPR and MV-TPR have closed-form expressions for the marginal likelihoods and predictive distributions under this unified framework and thus can adopt the same optimization approaches as used in the conventional GPR. The usefulness of the proposed methods is illustrated through several simulated and real-data examples. In particular, we verify empirically that MV-TPR has superiority for the datasets considered, including air quality prediction and bike rent prediction. At last, the proposed methods are shown to produce profitable investment strategies in the stock markets.

关键词： multivariate Gaussian process multivariate Student-t process Gaussian process regression Student-t process regression multi-output prediction Stock investment strategy Industrial sector Time series prediction

来源：评论

学校读者我要写书评

暂无评论

Deep tree-ensembles for multi-output prediction

引用

PATTERN RECOGNITION 2022年 121卷

作者： Nakano, Felipe Kenji Pliakos, Konstantinos Vens, Celine Katholieke Univ Leuven Dept Publ Hlth & Primary Care Campus KULAKEtienne Sabbelaan 53 B-8500 Kortrijk Belgium Katholieke Univ Leuven Imec Res Grp Itec Etienne Sabbelaan 53 B-8500 Kortrijk Belgium

Recently, deep neural networks have expanded the state-of-art in various scientific fields and provided solutions to long standing problems across multiple application domains. Nevertheless, they also suf-fer from weaknesses since their optimal performance depends on massive amounts of training data and the tuning of an extended number of parameters. As a countermeasure, some deep-forest methods have been recently proposed, as efficient and low-scale solutions. Despite that, these approaches simply em-ploy label classification probabilities as induced features and primarily focus on traditional classification and regression tasks, leaving multi-output prediction under-explored. Moreover, recent work has demon-strated that tree-embeddings are highly representative, especially in structured output prediction. In this direction, we propose a novel deep tree-ensemble (DTE) model, where every layer enriches the origi-nal feature set with a representation learning component based on tree-embeddings. In this paper, we specifically focus on two structured output prediction tasks, namely multi-label classification and multi-target regression. We conducted experiments using multiple benchmark datasets and the obtained results confirm that our method provides superior results to state-of-the-art methods in both tasks. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： Ensemble learning Deep-forest multi-output prediction multi-target regression multi-label classification

来源：评论

学校读者我要写书评

暂无评论

Scalable multi-output label prediction: From classifier chains to classifier trellises

引用

PATTERN RECOGNITION 2015年第6期48卷 2096-2109页

作者： Read, Jesse Martino, Luca Olmos, Pablo M. Luengo, David Aalto Univ Dept Comp Sci Helsinki Finland Aalto Univ Helsinki Finland Univ Helsinki Dept Math & Stat Helsinki Finland Univ Carlos III Madrid Dept Signal Theory & Commun Madrid 28911 Spain Univ Politecn Madrid Dept Signal Theory & Commun Madrid 28031 Spain

multi-output inference tasks, such as multi-label classification, have become increasingly important in recent years. A popular method for multi-label classification is classifier chains, in which the predictions of individual classifiers are cascaded along a chain, thus taking into account inter-label dependencies and improving the overall performance. Several varieties of classifier chain methods have been introduced, and many of them perform very competitively across a wide range of benchmark datasets. However, scalability limitations become apparent on larger datasets when modelling a fully cascaded chain. In particular, the methods' strategies for discovering and modelling a good chain structure constitute a major computational bottleneck. In this paper, we present the classifier trellis (CT) method for scalable multi-label classification. We compare CT with several recently proposed classifier chain methods to show that it occupies an important niche: it is highly competitive on standard multi-label problems, yet it can also scale up to thousands or even tens of thousands of labels. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Classifier chains multi-label classification multi-output prediction Structured inference Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling of post-combustion carbon capture process based on multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder network

引用

APPLIED THERMAL ENGINEERING 2025年 258卷

作者： Zheng, Cheng Sha, Peng Mo, Zhengyang Tang, Zihan Wang, Meihong Wu, Xiao Southeast Univ Natl Engn Res Ctr Power Generat Control & Safety Sch Energy & Environm Nanjing 210096 Peoples R China Univ Sheffield Dept Chem & Biol Engn Sheffield S1 3JD England

Solvent-based post-combustion carbon capture (PCC) technology is a promising, near-term solution for decarbonizing power generation and industrial facilities. Model-based process simulation is crucial for the optimal design and operation of the PCC process. Recently, data-driven models have gained attention due to their adaptability, efficient computation and high accuracy. However, the nonlinearity, strong couplings and multitime scale features of the PCC process pose significant challenges for model identification. To this end, this paper proposes a multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder (MMoE-DAED) network for dynamic modeling of the PCC process under wide operating conditions. An encoder-decoder composed of long short-term memory (LSTM) network is employed to extract features from the time-dependent input data and learn the complex dynamic interactions caused by the inertial and delay properties of the process. Dual-stage attention mechanism is incorporated into the encoder and decoder respectively to select the most relevant input features and their correlations within the time series data. To enhance multioutput prediction accuracy, multi-gate mixture-of-experts (MMoE) framework that considers correlations of multitask learning is implemented. Simulation results using operating data from a PCC experimental setup indicate that the proposed modeling approach accurately predicts the steady-state values and dynamic trends of the CO2 capture rate and stripper bottom temperature over a wide operating range. The RMSE, MAPE and R2 indices for the CO2 capture rate are 2.1592, 0.0295, 0.9641, respectively, and for the stripper bottom temperature are 0.1491, 0.0003, 0.9833, respectively. Validations on a PCC simulator further verify the accuracy and efficiency of the MMoE-DAED model, which enables an 80.87% reduction in computation time compared to the simulator. This paper points to a new direction for the data-driven dyna

关键词： Post-combustion carbon capture Dynamic modeling multi-output prediction multi-gate mixture-of-experts Encoder-decoder Dual-stage attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A multi-output Long-term prediction Intervals Construction Method for Linz-Donawitz Gas Tanks 14

A Multi-output Long-term Prediction Intervals Construction M...

引用

14th Asian Control Conference (ASCC)

作者： Zhang, Chunling Wang, Jing Meng, Fanxing Mei, Yanping Wang, Ze Dalian Univ Technol Sch Elect & Automat City Inst Dalian Peoples R China Dalian Univ Technol Sch Control Sci & Engn Dalian Peoples R China

ISBN: (纸本)9798331540845;9789887581598

As one of the most crucial secondary energy resources in steel industry, Linz Donawitz converter gas (LDG) draws greatly attention for which the utilization has a close relationship with the energy saving for the enterprise. And accurate prediction for the gas tank levels can be deemed as scientific guidance for energy scheduling and optimization operations. Considering a LDG system of a steel plant in China, a granular computing-based multi-output long-term prediction intervals (PIs) method is proposed to estimate the future trend of gas tank levels. A hybrid collaborative fuzzy clustering model is constructed which utilizing horizontal and vertical structure for fully describes both the relationship between the tank and the related influence factors, and also the mutual impact of the multiple tank levels. Furthermore, by means of the longitudinal expansion on the clustering centers, the prediction horizon is extended from the pointwise mode to the interval values. Then after the optimization along with fuzzy inference and defuzzification, a multi-output long-term PIs construction on the LDG gas tank levels is finally addressed. The results of the experiments and on-site system application indicate the effectiveness and practicability of the proposed method.

关键词： Steel industry granular computing gas tank levels multi-output prediction real application

来源：评论

学校读者我要写书评

暂无评论

Drug-target interaction prediction with tree-ensemble learning and output space reconstruction

引用

BMC BIOINFORMATICS 2020年第1期21卷 1-11页

作者： Pliakos, Konstantinos Vens, Celine Katholieke Univ Leuven Fac Med Campus KULAK Kortrijk Belgium Katholieke Univ Leuven ITEC Imec Res Grp Kortrijk Belgium

Background: Computational prediction of drug-target interactions (DTI) is vital for drug discovery. The experimental identification of interactions between drugs and target proteins is very onerous. Modern technologies have mitigated the problem, leveraging the development of new drugs. However, drug development remains extremely expensive and time consuming. Therefore, in silico DTI predictions based on machine learning can alleviate the burdensome task of drug development. Many machine learning approaches have been proposed over the years for DTI prediction. Nevertheless, prediction accuracy and efficiency are persisting problems that still need to be tackled. Here, we propose a new learning method which addresses DTI prediction as a multi-output prediction task by learning ensembles of multi-output bi-clustering trees (eBICT) on reconstructed networks. In our setting, the nodes of a DTI network (drugs and proteins) are represented by features (background information). The interactions between the nodes of a DTI network are modeled as an interaction matrix and compose the output space in our problem. The proposed approach integrates background information from both drug and target protein spaces into the same global network framework. Results: We performed an empirical evaluation, comparing the proposed approach to state of the art DTI prediction methods and demonstrated the effectiveness of the proposed approach in different prediction settings. For evaluation purposes, we used several benchmark datasets that represent drug-protein networks. We show that output space reconstruction can boost the predictive performance of tree-ensemble learning methods, yielding more accurate DTI predictions. Conclusions: We proposed a new DTI prediction method where bi-clustering trees are built on reconstructed networks. Building tree-ensemble learning models with output space reconstruction leads to superior prediction results, while preserving the advantages of tree-ensembles,

关键词： Drug-target networks Network reconstruction Interaction prediction Tree-ensembles multi-output prediction

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning Approach for Predictive Maintenance in Investment Casting Process 20

Ensemble Learning Approach for Predictive Maintenance in Inv...

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Soni, Hima Sinha, Aparna Patel, Vibha Das, Debanjan Udutalapally, Venkanna Gujarat Technological University Dept. of Cse Gujarat India Iiit Naya Raipur Dept. of Ece Chhattisgarh India Vishwakarma Government Engineering College Dept. of It Gujarat India Iiit Naya Raipur Dept. of Cse Chhattisgarh India

ISBN: (纸本)9798350305593

Beyond the Automation Pyramid, industries are currently embracing intelligence. One of the challenges in Industry 4.0 is to conduct Predictive maintenance (PdM) for the Investment Casting Process, which is one of the oldest metal-forming industrial processes. According to the existing works, PdM is achieved by data-driven methods for scheduling just-in-time maintenance. However, traditional Machine Learning (ML) techniques can make good predictions to some extent but are not guaranteed to be accurate. This limitation served as the driving force behind the current research work, which examined ensemble technique-based algorithms and compared them with standalone ML algorithms for the investment casting dataset. The most effective technique is used to achieve an optimal outcome i.e. gradient Boosting, it predicted the possible proportion of alloys during fault occurrence with 83.63% accuracy and 5.505 Average MSE. As a result, industries can learn to identify multiple root causes of failure, such as possible environmental conditions or proportions of the Investment Casting Materials, and predicts the possibilities of defects such as Flash, Misrun, Ceramic Inclusion, Shrinkage, and Slag Inclusion to arise. It has been proved that the proposed approach can also prevent downtime and optimise the performance of just-in-time maintenance. © 2023 IEEE.

关键词： Asset management Ensemble learning Modern investment casting multi-output prediction PdM

来源：评论

学校读者我要写书评

暂无评论

Against the Flow of Time with multi-output Models

引用

MEASUREMENT SCIENCE REVIEW 2023年第4期23卷 175-183页

作者： Jakubik, Jozef Phuong, Mary Chvostekova, Martina Krakovska, Anna Slovak Acad Sci Inst Measurement Sci Dubravska Cesta 9 Bratislava Slovakia IST Austria Campus 1 Klosterneuburg Austria

Recent work has paid close attention to the first principle of Granger causality about the cause preceding the effect. In this context, the question may arise as to whether the detected direction of causality will also be reversed after the time reversal of unidirectionally coupled data. It has been shown recently that in the case of unidirectionally causally connected autoregressive (AR) processes X -> Y , after time-reversal of data, the detected causality often changes to Y -> X but mostly into bidirectional X <-> Y link. As we argue here, the answer is different when the data examined does not come from AR processes, but rather from linked deterministic systems. If the goal is the usual forward data analysis, cross-mapping causal methods correctly detect X -> Y , while tests based on Granger, which should not be used for deterministic time series, detect causal independence X (sic) Y . The results of the backward causal analysis depend on the predictability of the reversed data. Unlike AR processes, observables from deterministic dynamical systems, even complex nonlinear ones, are well predicted forwards while backward predictions can sometimes seem difficult (notably when the time reversal of a function leads to one-to-many relations). To address this problem, here we propose an approach based on models that provide multiple candidate predictions for the target, combined with a loss function that takes into account only the best candidate. The resulting good forward and backward predictability supports the view that with unidirectionally causally linked deterministic dynamical systems X -> Y can be expected to detect the same link both before and after time reversal.

关键词： Causality deterministic dynamical systems reversibility multi-output prediction

来源：评论

学校读者我要写书评

暂无评论

multi-output Monitoring of High-Speed Laser Welding State Based on Deep Learning

引用

SENSORS 2021年第5期21卷 1626页

作者： Xue, Boce Chang, Baohua Du, Dong Tsinghua Univ Dept Mech Engn Beijing 100084 Peoples R China Minist Educ Key Lab Adv Mat Proc Technol Beijing 100084 Peoples R China

In order to ensure the production quality of high-speed laser welding, it is necessary to simultaneously monitor multiple state properties. Monitoring methods combining vision sensing and deep learning models are popular but most models used can only make predictions on single welding state property. In this contribution, we propose a multi-output model based on a lightweight convolutional neural network (CNN) architecture and introduce the particle swarm optimization (PSO) technique to optimize the loss function of the model, to simultaneously monitor multiple state properties of high-speed laser welding of AISI 304 austenitic stainless steel. High-speed imaging is performed to capture images of the melt pool and the dataset is built. Test results of different models show that the proposed model can achieve monitoring of multiple welding state properties accurately and efficiently. In addition, we make an interpretation and discussion on the prediction of the model through a visualization method, which can help to deepen our understanding of the relationship between the melt pool appearance and welding state. The proposed method can not only be applied to the monitoring of high-speed laser welding but also has the potential to be used in other procedures of welding state monitoring.

关键词： laser welding monitoring deep learning multi-output prediction particle swarm optimization CNN visualization

来源：评论

学校读者我要写书评

暂无评论

Conformal multi-Target Hyperrectangles

引用

STATISTICAL ANALYSIS AND DATA MINING 2024年第5期17卷

作者： Sampson, Max Chan, Kung-Sik Univ Iowa Dept Stat & Actuarial Sci Iowa City IA 52242 USA

We propose conformal hyperrectangular prediction regions for multi-target regression. We propose split conformal prediction algorithms for both point and quantile regression to form hyperrectangular prediction regions, which allow for easy marginal interpretation and do not require covariance estimation. In practice, it is preferable that a prediction region is balanced, that is, having identical marginal prediction coverage, since prediction accuracy is generally equally important across components of the response vector. The proposed algorithms possess two desirable properties, namely, tight asymptotic overall nominal coverage as well as asymptotic balance, that is, identical asymptotic marginal coverage, under mild conditions. We then compare our methods to some existing methods on both simulated and real data sets. Our simulation results and real data analysis show that our methods outperform existing methods while achieving the desired nominal coverage and good balance between dimensions.

关键词： balance conformal prediction multi-output prediction multi-target regression uncertainty quantification

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：