检索结果-内蒙古大学图书馆

International Workshop on Acoustic Signal Enhancement (IWAENC)

作者： Yoshiaki Sumura Diego Di Carlo Aditya Arie Nugraha Yoshiaki Bando Kazuyoshi Yoshii Graduate School of Informatics Kyoto University Kyoto Japan Center for Advanced Intelligence Project (AIP) RIKEN Tokyo Japan National Institute for Advanced Industrial Science and Technology (AIST) Tokyo Japan Graduate School of Engineering Kyoto University Kyoto Japan

ISBN: (数字)9798350361858

ISBN: (纸本)9798350361865

This paper describes a statistically principled method that simultaneously localizes and separates multiple sound sources using multiple calibrated microphone arrays distributed in a room. Given the extensive research on direction of arrival (DOA) estimation with a single microphone array, for 3D source localization, one may attempt triangulation based on DOAs separately and egocentrically estimated by multiple arrays. However, in multiple sources scenarios, this cascading approach faces both the inter-array DOA association problem and the error accumulation problem. To solve these problems, we propose a spatially regularized extension of a versatile blind source separation method called multichannel nonnegative matrix factorization (MNMF). Our method treats multiple microphone arrays as a single big array and puts priors on the frequency-wise spatial covariance matrices (SCMs) of each source. These priors are defined using the source DOA computed from the 3D positions of the source and arrays. The power spectral densities (PSDs), SCMs, and positions of multiple sources are jointly estimated under the unified maximum-a-posteriori (MAP) principle. We show the effectiveness of the joint statistical estimation for real data recorded by four five-channel microphone arrays of Microsoft Azure Kinect.

关键词： Location awareness Maximum likelihood estimation Direction-of-arrival estimation Three-dimensional displays Sensitivity Probabilistic logic Microphone arrays State-space methods Arrays Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Parallel LSTM Enhanced Forecasting System for Dependable and Secure Household Energy Consumption 23

Parallel LSTM Enhanced Forecasting System for Dependable and...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Yan, Ke Yang, Fan Zhou, Xiaokang Liang, Wei College of Design and Engineering National University of Singapore Singapore Singapore College of Information Engineering China Jiliang University Hangzhou China Shiga University Faculty of Data Science Hikone Japan Riken Center for Advanced Intelligence Project Tokyo Japan School of Frontier Crossover Studies Hunan University of Technology and Business Changsha China

ISBN: (纸本)9781665494571

A dependable and secure energy consumption forecasting system is proposed with parallel long short term memory neural networks and singular spectrum analysis (SSA). The input data is a time series dataset collected by an energy loading sensor installed for a particular household. The energy consumption patterns of in total five households in the UK were investigated. The SSA is employed for feature extraction by decomposing the original time series data into a series of constitutive sub-signals. A Parallel LSTM (PLSTM) learning model is then conducted to predict the energy consumption patterns for each SSA sub-signal. The decomposition and signal merging processes enhance the resilience for sensor faulty and errors, i.e., improve the security and dependability levels. Experiment results demonstrate that the proposed hybrid model significantly improves the prediction precision compared with benchmark models. The pressure of power load and maintenance cost of the grid can be drastically reduced. In addition, the training time of our proposed model is much faster than the benchmark model. The shortening of model training time can greatly advance the research on household power consumption. © 2021 IEEE.

关键词： Training Energy consumption Time series analysis Predictive models Data models Reliability Forecasting

来源：评论

学校读者我要写书评

暂无评论

Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty

arXiv

引用

arXiv 2023年

作者： Inatsu, Yu Takeno, Shion Hanada, Hiroyuki Iwata, Kazuki Takeuchi, Ichiro Department of Computer Science Nagoya Institute of Technology Japan RIKEN Center for Advanced Intelligence Project Japan Department of Mechanical Systems Engineering Nagoya University Japan

In this study, we propose a novel multi-objective Bayesian optimization (MOBO) method to efficiently identify the Pareto front (PF) defined by risk measures for black-box functions under the presence of input uncertainty (IU). Existing BO methods for Pareto optimization in the presence of IU are risk-specific or without theoretical guarantees, whereas our proposed method addresses general risk measures and has theoretical guarantees. The basic idea of the proposed method is to assume a Gaussian process (GP) model for the black-box function and to construct high-probability bounding boxes for the risk measures using the GP model. Furthermore, in order to reduce the uncertainty of non-dominated bounding boxes, we propose a method of selecting the next evaluation point using a maximin distance defined by the maximum value of a quasi distance based on bounding boxes. As theoretical analysis, we prove that the algorithm can return an arbitrary-accurate solution in a finite number of iterations with high probability, for various risk measures such as Bayes risk, worst-case risk, and value-at-risk. We also give a theoretical analysis that takes into account approximation errors because there exist non-negligible approximation errors (e.g., finite approximation of PFs and sampling-based approximation of bounding boxes) in practice. We confirm that the proposed method outperforms compared with existing methods not only in the setting with IU but also in the setting of ordinary MOBO through numerical experiments. Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

A DRL-Framework for Full-Duplex WPCN Enabled Mobile Edge Computing

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Bao, Senlei Zhang, Shubin Chi, Kaikai Yu, Keping Mumtaz, Shahid Zhejiang University of Technology School of Computer Science and Technology China Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan RIKEN Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Silesian University of Technology Department of Applied Informatics Poland Nottingham Trent University Department of Engineering United Kingdom

As the Internet of Things (IoT) continues to expand in both daily life and industrial production, the data generated by IoT devices is increasing rapidly. To address the challenges of limited battery life and computational capacity in these devices, two promising solutions have emerged: wireless power transfer (WPT) and mobile edge computing (MEC). By receiving radio frequency (RF) energy from a hybrid access point (HAP), wireless devices (WDs) can either offload data to the HAP or process it locally. In this paper, we explore the full-duplex WPT-MEC scenario and maximize the sum computation rate (SCR) by optimizing the offloading decision and resource allocation of WDs in different access modes and energy harvest models. This problem is formulated as a mixed-integer nonlinear programming (MINLP) problem. To address this, we decompose the problem into two sub-problems: one focuses on optimizing offloading decisions, and the other focuses on energy power and bandwidth allocation under given the offloading decisions. We propose a deep reinforcement learning approach based on policy gradients to make offloading decisions, and we design an optimization algorithm for efficient bandwidth and energy resource allocation. Simulation results show that our proposed algorithm achieves approximately 96% of the maximum possible computation rate while maintaining low computational complexity © 1967-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On `p-hyperparameter Learning via Bilevel Nonsmooth Optimization

引用

Journal of Machine Learning Research 2021年 22卷 1-47页

作者： Okuno, Takayuki Takeda, Akiko Kawana, Akihiro Watanabe, Motokazu Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Graduate School of Information Science and Technology The University of Tokyo Tokyo113-8656 Japan Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Department of Industrial Engineering and Economics Tokyo Institute of Technology Tokyo152-8550 Japan Department of Mathematical Informatics The University of Tokyo Tokyo113-8656 Japan

We propose a bilevel optimization strategy for selecting the best hyperparameter value for the nonsmooth `p regularizer with 0 p-regularized problem as the lower-level problem. Despite the recent popularity of nonconvex `p-regularizer and the usefulness of bilevel optimization for selecting hyperparameters, algorithms for such bilevel problems have not been studied because of the difficulty of `p-regularizer. Our contribution is the proposal of the first algorithm equipped with a theoretical guarantee for finding the best hyperparameter of `p-regularized supervised learning problems. Specifically, we propose a smoothing-type algorithm for the above mentioned bilevel optimization problems and provide a theoretical convergence guarantee for the algorithm. Indeed, since optimality conditions are not known for such bilevel optimization problems so far, new necessary optimality conditions, which are called the SB-KKT conditions, are derived and it is shown that a sequence generated by the proposed algorithm actually accumulates at a point satisfying the SB-KKT conditions under some mild assumptions. The proposed algorithm is simple and scalable as our numerical comparison to Bayesian optimization and grid search indicates. ©2021 Takayuki Okuno, Akiko Takeda, Akihiro Kawana, and Motokazu Watanabe.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of Dust Monitoring System for Photovoltaic Power Generation 23

The Design and Implementation of Dust Monitoring System for ...

引用

作者： Chen, Yuliang Ma, Jiali Ma, Yanhong Zhang, Yingli Zhou, Xiaokang Zhou, Rui School of Information Science and Engineering Lanzhou University Lanzhou China State Grid Gansu Electric Power Company Lanzhou China Shiga University Faculty of Data Science Hikone Japan Riken Center for Advanced Intelligence Project Tokyo Japan

ISBN: (纸本)9781665494571

In recent years, photovoltaic power generation, as one of the most important modes of clean energy generation, has gradually become the focus of China's energy development efforts. The Jiuquan area in Gansu, with good solar radiation conditions, high light intensity and high solar power generation potential, is an ideal area for building solar photovoltaic power generation farms. However, as the photovoltaic panels(PV panels) are exposed to the outdoors for a long time, the surface of the panels tend to accumulate a layer of dust, which makes it difficult for the sunlight to shine directly on the power generation area, seriously reducing the actual power generation efficiency of the panels, and at the same time, the 'heat island effect' caused by the dust may lead to damage of the panels. In this paper, a PV dust monitoring system is designed to solve the problem of low efficiency of PV power generation system caused by dust. The first part introduces the background, purpose and significance of the research, introduces the current status of domestic and international research, and states the main research work of this topic;the second part introduces the basic theory of PV power generation system and the effect of dust on PV power generation system;the third part introduces the design scheme of the system from the perspective of hardware and software;the fourth part introduces the specific implementation scheme of the system. This paper provides a solution to monitor the dust accumulation on the surface of PV panels, and provides support for the prediction of power generation and the recommendation of the cleaning cycle of PV panels. © 2021 IEEE.

关键词： Photovoltaic systems Smart cities Buildings Software Hardware Cleaning Thermal pollution

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Time Series Data Forecasting Using Machine Learning Based on Improved Grey Model 23

A Comparative Study of Time Series Data Forecasting Using Ma...

引用

作者： Li, Yan Zhang, Jiaming Ma, Yanhong Li, Xiaomin Liu, Ziang Zhou, Xiaokang Zhou, Rui School of Information Science and Engineering Lanzhou University Lanzhou China State Grid Gansu Electric Power Company Lanzhou China Shiga University Faculty of Data Science Hikone Japan Riken Center for Advanced Intelligence Project Tokyo Japan

ISBN: (纸本)9781665494571

This paper proposes a time-series data prediction hybrid model suitable for groundwater level to further study its impact on new energy power generation through the close relationship between groundwater level and climate. The model is based on the improved grey model (IGM) and combined with other models such as backpropagation neural network (BP) and general vector machine (GVM), which are used to predict time series data. Based on the time series data of groundwater level, the prediction ability of IGM BP, IGM RBF, IGM support vector machine, and IGM-GVM hybrid model is studied, which proved the feasibility of the model. The statistical parameter values finally conclude that the IGM-GVM model outperforms other selected models in the dataset utilized in the paper. In addition, the mixed model has a better effect on the dataset than the corresponding single model. © 2021 IEEE.

关键词： Support vector machines Temperature distribution Smart cities Time series analysis Machine learning Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "A facile and scalable strategy for constructing Janus cotton fabric with persistent antibacterial activity" [Int. J. Biol. Macromol. 236 (2023) 123946] (International Journal of Biological Macromolecules (2023) 236, (S0141813023008401), (10.1016/***.2023.123946))

引用

International Journal of Biological Macromolecules 2025年 307卷 142036页

作者： Li, Yong Wang, Pei Chen, Maoshuang Chen, Jinlin Huang, Wenjia Xiang, Shuangfei Zhao, Shujun Fu, Feiya Liu, Xiangdong School of Materials Science and Engineering and Institute of Smart Fiber Materials Zhejiang Sci-Tech University Hangzhou310018 China Project Promotion Department Zhejiang Provincial Innovation Center of Advanced Textile Technology Shaoxing China

The authors regret that there were errors in in Fig. 6e and Fig. 9a of the printed version of the above article. The correct and final version follows. The authors would like to clarify that there are no changes to the main text, and these corrections do not affect the overall conclusions of the article. Corrigendum Fig. 6e: The corrected figure is shown as below.[Figure presented] Corrigendum Fig. 9a: The corrected figure is shown as below.[Figure presented] The authors would like to apologise for any inconvenience caused. © 2025 Elsevier B.V.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Monitoring System for New Energy Data Call Based on Blockchain 23

Design and Implementation of Monitoring System for New Energ...

引用

作者： Liu, Ziang Huang, Yuanyuan Zhou, Qiang Zhang, Yingli Zhou, Xiaokang Zhou, Rui School of Information Science and Engineering Lanzhou University Lanzhou China State Grid Gansu Electric Power Research Institute Lanzhou China Shiga University Faculty of Data Science Hikone Japan Riken Center for Advanced Intelligence Project Tokyo Japan

ISBN: (纸本)9781665494571

With the energy revolution starting the third transformation to new energy, new energy has become essential for human energy. In order to better organize and utilize new energy, more and more research is committed to predicting the power generation capacity of new energy through the power generation data collected by intelligent systems to make better use of new energy. However, with the increase of new energy digital platforms and supporting infrastructure improvement, the distribution and management of relevant data also begin to face significant challenges. New energy data faces a substantial potential threat in distributing and using data to various digital platforms. Based on this, this paper designs and implements a new energy data call monitoring system based on blockchain to ensure the security of new energy data by tracking data operation information. © 2021 IEEE.

关键词： Smart cities Consensus algorithm Machine learning Blockchains Safety Recording Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

TENSOR STAR TENSOR DECOMPOSITION AND ITS APPLICATIONS TO HIGHER-ORDER COMPRESSION AND COMPLETION

arXiv

引用

arXiv 2024年

作者： Zhou, Wuyang Zheng, Yu-Bang Zhao, Qibin Mandic, Danilo Department of Electrical and Electronic Engineering Imperial College London United Kingdom School of Information Science and Technology Southwest Jiaotong University China Tensor Learning Team RIKEN Center for Advanced Intelligence Project Japan

A novel tensor decomposition framework, termed Tensor Star (TS) decomposition, is proposed which represents a new type of tensor network decomposition based on tensor contractions. This is achieved by connecting the core tensors in a ring shape, whereby the core tensors act as skip connections between the factor tensors and allow for direct correlation characterisation between any two arbitrary dimensions. Uniquely, this makes it possible to decompose an order-N tensor into N order-3 factor tensors {Gk}Nk=1 and N order-4 core tensors {Ck}Nk=1, which are arranged in a star shape. Unlike the class of Tensor Train (TT) decompositions, these factor tensors are not directly connected to one another. The so obtained core tensors also enable consecutive factor tensors to have different latent ranks. In this way, the TS decomposition alleviates the "curse of dimensionality" and controls the "curse of ranks", exhibiting a storage complexity which scales linearly with the number of dimensions and as the fourth power of the ranks. Copyright © 2024, The Authors. All rights reserved.

关键词： Stars

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：