检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年

作者： Ge, Zhiqiang Chen, Duxin Yu, Wenwu Southeast University School of Mathematics Nanjing210096 China

Recently, probabilistic latent variable models have played an important role in data analytics in various industrial application scenarios, such as process monitoring, fault diagnosis, and soft sensing. Inspired by the idea of lightweight deep learning, this paper proposes a new deep residual learning method for the probabilistic' partial least squares model. Firstly, layer-wise probabilistic modeling is carried out to extract supervised latent variables in different hidden layers of the deep model using a well-designed expectation-maximization algorithm for parameter optimization. Through this layer-wise residual learning process, more target-related latent variables can be extracted, which are supervised by the outputs of the predictive model. Next, an additional probabilistic model is constructed for information fusion and further extraction of supervised latent variables which are highly related to the modeling target. In fact, this step can be considered as an ensemble learning strategy, which has great potentials in decreasing modeling error and reducing prediction uncertainty. A soft-sensing strategy is then developed for online prediction of key variables. The performance is evaluated using two industrial examples. Compared to the shallow probabilistic model, the performance of the deep model has been improved by 10%-20%. © 2020 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Autonomous Exploration and Mapping Under Localization Uncertainty with expectation-maximization

Multi-Robot Autonomous Exploration and Mapping Under Localiz...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Huang, Yewei Lin, Xi Englot, Brendan Stevens Inst Technol Hoboken NJ 07030 USA

ISBN: (纸本)9798350384581;9798350384574

We propose an autonomous exploration algorithm designed for decentralized multi-robot teams, which takes into account map and localization uncertainties of range-sensing mobile robots. Virtual landmarks are used to quantify the combined impact of process noise and sensor noise on map uncertainty. Additionally, we employ an iterative expectation-maximization inspired algorithm to assess the potential outcomes of both a local robot's and its neighbors' next-step actions. To evaluate the effectiveness of our framework, we conduct a comparative analysis with state-of-the-art algorithms. The results of our experiments show the proposed algorithm's capacity to strike a balance between curbing map uncertainty and achieving efficient task allocation among robots.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

expectation maximization-based likelihood inference for flexible cure rate models with Weibull lifetimes

引用

STATISTICAL METHODS IN MEDICAL RESEARCH 2016年第4期25卷 1535-1563页

作者： Balakrishnan, Narayanaswamy Pal, Suvra McMaster Univ Dept Math & Stat Hamilton ON L8S 4K1 Canada King Abdulaziz Univ Dept Stat Jeddah Saudi Arabia

Recently, a flexible cure rate survival model has been developed by assuming the number of competing causes of the event of interest to follow the Conway-Maxwell-Poisson distribution. This model includes some of the well-known cure rate models discussed in the literature as special cases. Data obtained from cancer clinical trials are often right censored and expectation maximization algorithm can be used in this case to efficiently estimate the model parameters based on right censored data. In this paper, we consider the competing cause scenario and assuming the time-to-event to follow the Weibull distribution, we derive the necessary steps of the expectation maximization algorithm for estimating the parameters of different cure rate survival models. The standard errors of the maximum likelihood estimates are obtained by inverting the observed information matrix. The method of inference developed here is examined by means of an extensive Monte Carlo simulation study. Finally, we illustrate the proposed methodology with a real data on cancer recurrence.

关键词： cure rate models long-term survivor Conway-Maxwell-Poisson distribution maximum likelihood estimators expectation maximization algorithm profile likelihood lifetime data Weibull distribution asymptotic variances Akaike's information criterion Bayesian information criterion

来源：评论

学校读者我要写书评

暂无评论

Track Segment Association of Maneuvering Target based on expectation maximization 11

Track Segment Association of Maneuvering Target based on Exp...

引用

11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Sun, Jinping Wang, Naiyu Zhang, Zhiguo Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China

ISBN: (纸本)9781538676042

Because of the high maneuverability of targets, track breakages are common in the tracking process. With the purpose of stitching the track segments and achieving better tracking results, we adopt an algorithm to stitch the track segments based on expectation maximization (EM). The EM algorithm can be used to estimate and identify the maneuvering targets' state and angular velocities simultaneously. It consists of two steps. The expectation (E) step is implemented by an extended Kalman filter (EKF) and extended Rauch-Tung-Striebel smoother (ERTSS). The maximization (M) step is implemented by genetic algorithm, which can achieve the Maximum likelihood sequence estimation for unknown parameters. Experiments show that this algorithm can achieve better tracking results. Moreover, it also exhibits good capability when estimating the unknown parameter.

关键词： expectation maximization algorithm target tracking track segment association parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Direct Learning Coverage Control Based on expectation maximization in Wireless Sensor and Robot Network 1

Direct Learning Coverage Control Based on Expectation Maximi...

引用

1st Annual IEEE Conference on Control Technology and Applications

作者： Lin, Tsen-Chang Liu, Yen-Chen Natl Cheng Kung Univ Dept Mech Engn Tainan 70101 Taiwan

ISBN: (纸本)9781509021826

This paper proposes a direct learning controller for wireless sensor and robot network to coverage an environment by utilizing expectation maximization algorithm. In addition to sensors, including high-level and low-level sensors, mounted on mobile robots, low-level stationary sensors are considered to provide information for enhance the performance of coverage control. The main objective is to maximize the information quantity of high-level sensors from the sensing density generated by a group of low-level sensors. This direct method uses the parameter of basis function to design controller based on expectation maximization (EM) algorithm. Moreover, the proposed estimation and learning law are also used in indirect method for other coverage controller. Subsequently, this paper proposes a transformation method based on EM algorithm for coverage problem with complicated sensing function such as Gaussian function. Numerical examples are introduced to demonstrate the performance of the proposed direct coverage control in wireless sensor and robot network.

关键词： wireless sensor and robot network coverage control direct density estimation expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Bilinear Hybrid expectation maximization and expectation Propagation for Semi-Blind Channel Estimation 32

Bilinear Hybrid Expectation Maximization and Expectation Pro...

引用

32nd European Signal Processing Conference (EUSIPCO)

作者： Zhao, Zilu Slock, Dirk EURECOM Commun Syst Dept Biot France

ISBN: (纸本)9789464593617;9798331519773

This paper discusses channel estimation during uplink transmission in Cell-Free (CF) Massive MIMO (MaMIMO) systems. We model the problem as a semi-blind estimation problem with independent and identically distributed (i.i.d.) Gaussian input. Two hybrid expectation maximization (EM) and expectation Propagation (EP) algorithms are proposed to improve convergence behavior. The first algorithm, EM-EP, adopts a vector-level EP approach by treating the per-user channel coefficients and data sequence as EP variables. To make the algorithm tractable, we use the central limit theorem (CLT) to approximate the interference terms and employ EM to construct a majorizer function for the likelihood of the received data, leading to majorization minimization. To further enhance convergence behavior, we propose a matrix-level loop-free EM-EP algorithm. In this algorithm, we treat the channel coefficients and data sequences corresponding to users using the same pilot as EP variables. This method is an alternating minimization algorithm, ensuring convergence. Our simulations verify the effectiveness of the two proposed algorithms.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

From Biased Selective Labels to Pseudo-Labels: An expectation-maximization Framework for Learning from Biased Decisions 41

From Biased Selective Labels to Pseudo-Labels: An Expectatio...

引用

41st International Conference on Machine Learning (ICML)

作者： Chang, Trenton Wiens, Jenna Univ Michigan Div Comp Sci & Engn Ann Arbor MI 48109 USA

Selective labels occur when label observations are subject to a decision-making process;e.g., diagnoses that depend on the administration of laboratory tests. We study a clinically-inspired selective label problem called disparate censorship, where labeling biases vary across subgroups and unlabeled individuals are imputed as "negative" (i.e., no diagnostic test = no illness). Machine learning models naively trained on such labels could amplify labeling bias. Inspired by causal models of selective labels, we propose Disparate Censorship expectation-maximization (DCEM), an algorithm for learning in the presence of disparate censorship. We theoretically analyze how DCEM mitigates the effects of disparate censorship on model performance. We validate DCEM on synthetic data, showing that it improves bias mitigation (area between ROC curves) without sacrificing discriminative performance (AUC) compared to baselines. We achieve similar results in a sepsis classification task using clinical data.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Explicit Memory Learning with expectation maximization

Explicit Memory Learning with Expectation Maximization

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yin, Zhangyue Sun, Qiushi Guo, Qipeng Zeng, Zhiyuan Cheng, Qinyuan Qiu, Xipeng Huang, Xuanjing School of Computer Science Fudan University China The University of Hong Kong Hong Kong Shanghai AI Laboratory China

ISBN: (纸本)9798891761643

Large Language Models (LLMs) have revolutionized the landscape of natural language processing, demonstrating remarkable abilities across various complex tasks. However, their stateless nature limits the capability to retain information across interactions, hindering performance in scenarios requiring historical context recall. To mitigate this, current approaches primarily use explicit memory to allow LLMs to store useful information, which is accessible, readable, and interpretable. Nevertheless, explicit memory lacks the reliable learning mechanisms of implicit memory, which can be optimized end-to-end. To harness the benefits of both, we introduce EM2, a novel framework enhancing explicit memory updates via the expectation-maximization (EM) algorithm. EM2 treats memory as a latent variable, ensuring continual learning and improvement during updates. Experimental results on streaming inference tasks demonstrate that EM2 outperforms existing methods without memory or with static external memory. Our in-depth analysis highlights that EM2 significantly enhances performance across various backbones and memory strategies, providing a robust solution for advancing LLM memory management and enabling explicit memory to learn and improve similarly to implicit memory. © 2024 Association for Computational Linguistics.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

System Identification for Linear Dynamics with Bilinear Observation Models: An expectation-maximization Approach 63

System Identification for Linear Dynamics with Bilinear Obse...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Liu, Diyou Khosravi, Mohammad Delft University of Technology Delft Center for Systems and Control Delft Netherlands

ISBN: (纸本)9798350316339

In this paper, we study the system identification problem for linear time-invariant dynamics with bilinear observation models. Accordingly, we consider a suitable parametric description for the system model and formulate the identification problem as estimating the parameters characterizing the mathematical representation of the system through input-output measurement data. To this end, we employ a probabilistic framework aiming to obtain the maximum likelihood estimates of the parameters. Accordingly, we propose utilizing the expectation-maximization approach to improve the tractability of the identification procedure. Through the numerical experiments, we verify the efficacy of the proposed scheme and demonstrate its performance. © 2024 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuzzy expectation maximization Phoneme Prediction in Diffusion Model-based Dysarthria Voice Conversion

Fuzzy Expectation Maximization Phoneme Prediction in Diffusi...

引用

2024 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2024

作者： Lin, Guang-Tao Hsu, Wen-Shin Liu, Guan-Tsen Chen, Su-Juan Chung Shan Medical University Department of Medical Information Taichung Taiwan Chung Shan Medical University & Chung Shan Medical University Hospital Department of Medical Information & Informatics Office Technology Taichung Taiwan

ISBN: (纸本)9798350352788

In this paper proposed an effective fuzzy expectation-maximization phoneme prediction method in diffusion model-based dysarthria voice conversion (FEMPPDM-DVC) which is accessible to (i) training without parallel data (ii) converting a longer duration of the audio data (iii) preserves speaker identity. By integrating Fuzzy expectation-maximization (FEM) clustering and Diffusion model-based dysarthria voice conversion approach, the proposed method is able gradually generate normal utterances. Feature extraction is performed using Mel-frequency cepstral coefficients (MFCCs), a robust method in acoustic feature extraction in Text-to-Speech systems. Ensures the effectiveness and accuracy, through repeated parameter adjustment using the FEM clustering algorithm. The conversion network is a diffusion model-based structure, which can convert normal utterances to dysarthria utterances in the forward diffusion process. After forward diffusion process, the dysarthria utterance will go through a reverse diffusion process to convert dysarthria voice to normal utterance. Once converted, a GAN-based vocoder is applied to convert mel-frequency spectrogram to waveform. Objective evaluation is conducted on the Saarbrücken Voice Database (SVD) dataset show that FEMDDPM-DVC is able to improve the intelligibility and naturalness of dysarthria utterances in 15 kinds of dysarthria voice. The proposed method is compared with five other dysarthria voice conversion methods, show that the proposed method has the most performance among other method. © 2024 IEEE.

关键词： expectation maximization algorithm

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：