检索结果-内蒙古大学图书馆

Weighted Least-Squares PARSIM

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Jiabao Rojas, Cristian R. Hjalmarsson, Håkan Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden

Subspace identification methods (SIMs) have proven very powerful for estimating linear state-space models. To overcome the deficiencies of classical SIMs, a significant number of algorithms has appeared over the last two decades, where most of them involve a common intermediate step, that is to estimate the range space of the extended observability matrix. In this contribution, an optimized version of the parallel and parsimonious SIM (PARSIM), PARSIMopt, is proposed by using weighted least-squares. It not only inherits all the benefits of PARSIM but also attains the best linear unbiased estimator for the above intermediate step. Furthermore, inspired by SIMs based on the predictor form, consistent estimates of the optimal weighting matrix for weighted least-squares are derived. Essential similarities, differences and simulated comparisons of some key SIMs related to our method are also presented. Copyright © 2024, The Authors. All rights reserved.

关键词： State space methods

On generalization bounds for projective clustering 23

学校读者我要写书评

暂无评论

On generalization bounds for projective clustering

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Maria Sofia Bucarelli Matilde Fjeldsø Larsen Chris Schwiegelshohn Mads Bech Toftrup Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Italy Department of Computer Science Aarhus University Denmark

Given a set of points, clustering consists of finding a partition of a point set into k clusters such that the center to which a point is assigned is as close as possible. Most commonly, centers are points themselves, which leads to the famous k-median and k-means objectives. One may also choose centers to be j dimensional subspaces, which gives rise to subspace clustering. In this paper, we consider learning bounds for these problems. That is, given a set of n samples P drawn independently from some unknown, but fixed distribution Ɗ, how quickly does a solution computed on P converge to the optimal clustering of Ɗ? We give several near optimal results. In particular,1. For center-based objectives, we show a convergence rate of Õ(√k/n). This matches the known optimal bounds of [Fefferman, Mitter, and Narayanan, Journal of the Mathematical Society 2016] and [Bartlett, Linder, and Lugosi, IEEE Trans. Inf. Theory 1998] for k-means and extends it to other important objectives such as k-median.2. For subspace clustering with j -dimensional subspaces, we show a convergence rate of Õ(√kj2/n). These are the first provable bounds for most of these problems. For the specific case of projective clustering, which generalizes k-means, we show a convergence rate of Ω(√kj/n) is necessary, thereby proving that the bounds from [Fefferman, Mitter, and Narayanan, Journal of the Mathematical Society 2016] are essentially optimal.

关键词：

Coherence-based Input Design for Sparse System Identification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Parsa, Javad Rojas, Cristian R. Hjalmarsson, Håkan Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden

The maximum absolute correlation between regressors, which is called mutual coherence, plays an essential role in sparse estimation. A regressor matrix whose columns are highly correlated may result from optimal input design, since there is no constraint on the mutual coherence, so when this regressor is used to estimate sparse parameter vectors of a system, it may yield a large estimation error. This paper aims to tackle this issue for fixed denominator models, which include Laguerre, Kautz, and generalized orthonormal basis function expansion models, for example. The paper proposes an optimal input design method where the achieved Fisher information matrix is fitted to the desired Fisher matrix, together with a coordinate transformation designed to make the regressors in the transformed coordinates have low mutual coherence. The method can be used together with any sparse estimation method and in a numerical study we show its potential for alleviating the problem of model order selection when used in conjunction with, for example, classical methods such as AIC and BIC. © 2024, CC BY.

关键词： Fisher information matrix

An evaluation and query algorithm for the influence of spatial location based on RkNN

学校读者我要写书评

暂无评论

Frontiers of computer science 2021年第2期15卷 81-89页

作者： Jingke XU Yidan ZHAO Ge YU School of Computer Science and Engineering Northeastern UniversityShenyang110819China School of Information and Control Engineering Shenyang Jianzhu UniversityShenyang110168China Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang110168China

This paper is devoted to the investigation of the evaluation and query algorithm problem for the influence of spatial location based on RkNN(reverse k nearest neighbor).On the one hand,an object can make contribution to multiple ***,for the existing measures for evaluating the influence of spatial location,an object only makes contribution to one location,and its influence is usually measured by the number of spatial objects in the *** this case,a new measure for evaluating the influence of spatial location based on the RkNN is *** the weight of the contribution is determined by the distance between the object and the location,the influence weight definition is given,which meets the actual *** the other hand,a query algorithm for the influence of spatial location is introduced based on the proposed ***,an algorithm named INCH(INtersection’s Convex Hull)is applied to get candidate regions,where all objects are ***,kNN and Range-k are used to refine ***,according to the proposed measure,the weights of objects in RkNN results are computed,and the influence of the location is *** experimental results on the real data show that the optimized algorithms outperform the basic algorithm on *** addition,in order to provide the best customer service in the location problem and make the best use of all infrastructures,a location algorithm with the query is presented based on *** influence of each facility is calculated in the location program and the equilibrium coefficient is used to evaluate the reasonability of the location in the *** smaller the equilibrium coefficient is,the more reasonability the program *** actual application shows that the location based on influence makes the location algorithm more reasonable and available.

关键词： spatial data reverse k nearest neighbor influence of spatial location location algorithm

PSRMER: Proactive Services Recommendation Driven-by Multimodal Emotion Recognition

学校读者我要写书评

暂无评论

PSRMER: Proactive Services Recommendation Driven-by Multimod...

IEEE International Conference on Web Services (ICWS)

作者： Zhizhong Liu Guangyu Huang Dianhui Chu Yuhang Sun School of Computer and Control Engineering Yantai University Yantai China School of Computer Science and Technology Harbin Institute of Technology Weihai China

In the past three years, global COVID-19 pandemic not only impacted people’s physical health but also significantly affected their mental health, which resulting in rapid increase of psychological problems. Emotions are a common manifestation of psychological changes, and some services (such as music, video, or psychological counseling services) can help users to adjust their emotions in a timely manner, thus to avoid bringing extreme events (e.g., running away from home or committing suicide). Therefore, how to perceive users’ real-time emotions and then recommend the most appropriate services to users has become a challenge. To address this issue, this work proposes an approach for proactive services recommendation driven-by multimodal emotion recognition (named as PSRMER). Specifically, PSRMER first actively identifies a user’s emotion with a multimodal emotion recognition model based on BiGRU and Transformer; Then, considering the user’s emotion and preferences, PSRMER selects the optimal services based on an index-graph linking different emotions and various services; Finally, PSRMER proactively recommends the selected optimal service to the user. Extensive experiments have been conducted and the effectiveness of our proposed method have been proved. Moreover, the proposed method can also be used in smart education, smart transportation, smart elderly care and other modern industry fields.

关键词：

On Generalization Bounds for Projective Clustering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bucarelli, Maria Sofia Larsen, Matilde Fjeldsø Schwiegelshohn, Chris Toftrup, Mads Bech Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Italy Department of Computer Science Aarhus University Denmark

Given a set of points, clustering consists of finding a partition of a point set into k clusters such that the center to which a point is assigned is as close as possible. Most commonly, centers are points themselves, which leads to the famous k-median and k-means objectives. One may also choose centers to be j dimensional subspaces, which gives rise to subspace clustering. In this paper, we consider learning bounds for these problems. That is, given a set of n samples P drawn independently from some unknown, but fixed distribution D, how quickly does a solution computed on P converge to the optimal clustering of D? We give several near optimal results. In particular, 1. For center-based objectives, we show a convergence rate of Õ (√k/n ) . This matches the known optimal bounds of [Fefferman, Mitter, and Narayanan, Journal of the Mathematical Society 2016] and [Bartlett, Linder, and Lugosi, IEEE Trans. Inf. Theory 1998] for k-means and extends it to other important objectives such as k-median. 2. For subspace clustering with j-dimensional subspaces, we show a convergence rate of Õ (√kj2/n ) . These are the first provable bounds for most of these problems. For the specific case of projective clustering, which generalizes k-means, we show a convergence rate of Ω (√kj/n ) is necessary, thereby proving that the bounds from [Fefferman, Mitter, and Narayanan, Journal of the Mathematical Society 2016] are essentially optimal. © 2023, CC BY.

关键词： K-means clustering

Progress of Brain Network Studies on Anesthesia and Consciousness: Framework and Clinical Applications

学校读者我要写书评

暂无评论

engineering 2023年第1期20卷 77-95页

作者： Jun Liu Kangli Dong Yi Sun Ioannis Kakkos Fan Huang Guozheng Wang Peng Qi Xing Chen Delin Zhang Anastasios Bezerianos Yu Sun Key Laboratory for Biomedical Engineering of Ministry of Education of China Zhejiang UniversityHangzhou 310007China Department of Neurology Sir Run Run Shaw HospitalSchool of MedicineZhejiang UniversityHangzhou 310020China School of Electrical and Computer Engineering National Technical University of AthensAthens 15780Greece Department of Control Science and Engineering College of Electronics and Information EngineeringTongji UniversityShanghai 200092China Department of Anesthesiology The First Affiliated HospitalSchool of MedicineZhejiang UniversityHangzhou 310003China The N1 Institute for Health Center for Life SciencesNational University of SingaporeSingapore 117456Singapore

Although the relationship between anesthesia and consciousness has been investigated for decades, our understanding of the underlying neural mechanisms of anesthesia and consciousness remains rudimentary, which limits the development of systems for anesthesia monitoring and consciousness evaluation. Moreover, the current practices for anesthesia monitoring are mainly based on methods that do not provide adequate information and may present obstacles to the precise application of anesthesia. Most recently, there has been a growing trend to utilize brain network analysis to reveal the mechanisms of anesthesia, with the aim of providing novel insights to promote practical application. This review summarizes recent research on brain network studies of anesthesia, and compares the underlying neural mechanisms of consciousness and anesthesia along with the neural signs and measures of the distinct aspects of neural activity. Using the theory of cortical fragmentation as a starting point, we introduce important methods and research involving connectivity and network analysis. We demonstrate that whole-brain multimodal network data can provide important supplementary clinical information. More importantly, this review posits that brain network methods, if simplified, will likely play an important role in improving the current clinical anesthesia monitoring systems.

关键词： Anesthesia Brain network Connectivity Graph theoretical analysis Clinical monitoring system

On final opinions of the Friedkin-Johnsen model over random graphs with partially stubborn community

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Lingfei Xing, Yu Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology with Digital Futures Stockholm Sweden

This paper studies the formation of final opinions for the Friedkin-Johnsen (FJ) model with a community of partially stubborn agents. The underlying network of the FJ model is symmetric and generated from a random graph model, in which each link is added independently from a Bernoulli distribution. It is shown that the final opinions of the FJ model will concentrate around those of an FJ model over the expected graph as the network size grows, on the condition that the stubborn agents are well connected to other agents. Probability bounds are proposed for the distance between these two final opinion vectors, respectively for the cases where there exist non-stubborn agents or not. Numerical experiments are provided to illustrate the theoretical findings. The simulation shows that, in presence of non-stubborn agents, the link probability between the stubborn and the non-stubborn communities affect the distance between the two final opinion vectors significantly. Additionally, if all agents are stubborn, the opinion distance decreases with the agent stubbornness. Copyright © 2024, The Authors. All rights reserved.

关键词：

Embedded Multi-Port Converters for Synthesis and Enhancement of Hybrid-Clamped Multilevel Converters

学校读者我要写书评

暂无评论

Embedded Multi-Port Converters for Synthesis and Enhancement...

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Yuzhuo Li Pasan Gunawardena Hao Tian Yunwei Li Department of Electrical and Computer Engineering University of Alberta Edmonton Canada School of Control Science and Engineering Shandong University Jinan China

Leveraging a number of inner capacitors/inductors, hybrid-clamped multilevel converters (MLCs) normally face great challenges among good performance (proper charge/discharge of these devices), high efficiency (maintaining low losses) and high power density (compact profile). On the other hand, these multiple-device energy-processing requirements have been addressed well in some promising multi-port converters (MPCs), and, therefore, inspire us to implement well-developed compact MPCs to facilitate the voltage/current level generation process in hybrid-clamped MLCs. Though recently, some researchers started to integrate active cells into hybrid-clamped MLCs and improve capacitor voltage control and generate extra output levels, the systematic synthesis method is still unclear and rarely discussed in the literature. To address this gap, we propose a systematic synthesis method for those hybrid clamped MLCs that can benefit from embedding well-developed MPCs. The approach can be applied for both voltage-source and current-source hybrid-clamped MLCs, covering emerging MLCs. In particular, we also derived and verified a new mixed hybrid MLC family through an emerging current-fed dual-input isolated multi-port converter. This topology features both current-source and voltage-source benefits and is ideal for future renewable generation integration.

关键词：