检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shi, Runwu Yen, Benjamin Nakadai, Kazuhiro Dept. of Systems & Control Engineering Tokyo Institute of Technology Tokyo Japan

ISBN: (纸本)9798350368741

This paper aims to achieve single-channel target speech extraction (TSE) in enclosures by solely utilizing distance information. This is the first work that utilizes only distance cues without using speaker physiological information for single-channel TSE. Inspired by recent single-channel Distance-based separation and extraction methods, we introduce a novel model that efficiently fuses distance information with time-frequency (TF) bins for TSE. Experimental results in both single-room and multi-room scenarios demonstrate the feasibility and effectiveness of our approach. This method can also be employed to estimate the distances of different speakers in mixed speech. Online demos are available at https://***/distance-demo-page/. © 2025 IEEE.

关键词： distance based sound separation single-channel Target speech extraction

来源：评论

学校读者我要写书评

暂无评论

Closed-Loop System Identification of an Unstable Nonlinear System Using Koopman Operator 4

Closed-Loop System Identification of an Unstable Nonlinear S...

引用

4th International Symposium on Instrumentation, control, Artificial Intelligence, and Robotics, ICA-SYMP 2025

作者： Maneeloke, Benjaset Boonto, Sudchai Sanposh, Peerayot Tipsuwan, Yodyium Chinthaned, Natthawut Tanaprasitpattana, Warit Kasetsart University Dept. of Electrical Engineering Bangkok Thailand King Mongkut's University of Technology Thonburi Dept. of Control Systems and Instrumentation Engineering Bangkok Thailand Kasetsart University Dept. of Computer Engineering Bangkok Thailand

ISBN: (纸本)9798331505400

This paper presents a novel methodology for closed-loop system identification of unstable nonlinear systems using the Koopman operator with Extended Dynamic Mode Decomposition with control (EDMDc). The study highlights the critical role of selecting appropriate observable functions to develop accurate and efficient Koopman models. We demonstrate that the resulting Koopman models exhibit excellent fitting and validation properties and retain the stabilizability of the original nonlinear systems. These models are verified through time and frequency responses under closed-loop control using a Linear Quadratic Regulator (LQR), confirming their effectiveness. Future work will extend this framework to more complex systems and incorporate machine learning techniques to refine the selection of observable functions. This approach aims further to enhance the adaptability and robustness of Koopman-based control strategies. © 2025 IEEE.

关键词： Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Drive Stabilization of Multi-Degree-of-Freedom Maglev Planar Motor Based on Closed Loop System Identification

Drive Stabilization of Multi-Degree-of-Freedom Maglev Planar...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Nakata, Keigo Ohnishi, Wataru Koseki, Takafumi Nakamura, Yuichiro Takahashi, Kenji Sekiguchi, Hiroyuki The University of Tokyo Dept. of Electrical Engineering and Information systems Tokyo Japan Advanced Technology R&D Center Mitsubishi Electric Corporation Hyogo Japan

ISBN: (纸本)9798331533892

Magnetic levitation planar motor can move at high speed and with high accuracy, and prevent vibration and noise because of no friction. This technology leads to the application of a transport system that requires high-speed and high-precision movement. However, the design of appropriate control algorithms is essential to achieve stability and high-speed, high-precision control of the maglev planar motor. In this research, we stabilized a maglev planar motor on the basis of system identification. Initially, we designed a whole control system for the movement of the maglev planar motor. Furthermore, we conducted system identification and verified that the maglev planar motor works with the designed control system and evaluated its motion performance. Through experiments, it was confirmed that accurate motion control was possible. This research is expected to be a basis for improving control performance soon. © 2025 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Distance Based Single-Channel Target Speech Extraction

Distance Based Single-Channel Target Speech Extraction

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Runwu Shi Benjamin Yen Kazuhiro Nakadai Dept. of Systems & Control Engineering Tokyo Institute of Technology Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Time-frequency analysis Fuses Buildings Signal processing Physiology Acoustics Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Ion Mobility in Helmholtz Layer Enabling Ultrathick Electrodes

引用

ACS Nano 2025年第18期19卷 17917-17928页

作者： Wang, Yuanzhen Aubermann, Florian Spatz, Joachim P. Max Planck Institute for Medical Research@Bildungscampus Heilbronn Dept. of Cellular Biophysics HeilbronnD-74076 Germany Institute for Molecular Systems Engineering and Advanced Materials Heidelberg University HeidelbergD-69120 Germany Max Planck School Matter to Life@Bildungscampus Heilbronn HeilbronnD-74076 Germany

A previously unknown mechanism for enhancing the diffusivity of lithium ions in liquid electrolytes is reported by immersing a charged copper surface in an electrolyte, which forms a laterally ultramobile Helmholtz layer at the copper-electrolyte interface. A microfluidic chip in combination with Raman spectroscopy and molecular ab initio dynamic simulations allowed for a quantitative study and mechanistic description of the diffusion enhancement. The synthesis of an ultrafine copper fiber fleece with a large copper surface area enables the fabrication of a 3-dimensional graphite/copper fleece composite electrode. Such electrodes demonstrate enhanced ion diffusivity and electrical conductivity compared to traditional electrodes without copper fleece but with copper foil. This electrode design allows electrochemically functional ultrathick anodes of up to 1.2 mm thickness and 32 mAh/cm2 areal capacity in half-cell format. The fleece electrodes use half the amount of copper compared to conventional foil-based electrodes and therefore provide significantly higher volumetric and gravimetric energy densities. © 2025 The Authors. Published by American Chemical Society.

关键词： Coated wire electrodes

来源：评论

学校读者我要写书评

暂无评论

SB-AGT: A stochastic beam search-enhanced attention-based Gumbel tree framework for drug-drug interaction extraction from biomedical literature

引用

Computers in Biology and Medicine 2025年 189卷 110011-110011页

作者： Saad, Eman Kishk, Sherif Ali-Eldin, Amr Saleh, Ahmed I. Communication and Information Technology Center Mansoura University Egypt Electronics and Communication Engineering Dept. Mansoura University Egypt Computer Engineering & Control Systems Dept. Mansoura University Egypt

Drug-Drug Interactions (DDI) and Chemical-Protein Interactions (CPI) detection are crucial for patient safety, as unidentified interactions may lead to severe Adverse Drug Reactions (ADRs). While extensive DDI and CPI information exists within biomedical literature, manual extraction by experts proves time-intensive and resource-demanding. This study presents SB-AGT: Stochastic Beam Search-enhanced Attention-based Gumbel Tree an innovative approach to automated DDI and CPI extraction through an attention-based architecture incorporating a modified Gumbel-Tree method with stochastic beam search optimization. SB-AGT leverages multi-head attention mechanisms and enhanced latent tree structures to effectively capture complex syntactic features and drug relationship patterns. Also, the methodology includes comprehensive preprocessing protocols and addresses dataset imbalance through hybrid sampling techniques. Experimental validation on the DDIExtraction 2013 and CHEMPROT datasets demonstrates the model's effectiveness, achieving precision, surpassing traditional approaches and showing competitive performance compared to contemporary pre-trained models. Through parametric analysis, we establish optimal beam search configurations that maximize the model's extraction accuracy. © 2025 Elsevier Ltd

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Proposal for a Job Management Tool for Deep Learning in a Mixed Environment of Heterogeneous GPUs

Proposal for a Job Management Tool for Deep Learning in a Mi...

引用

Consumer Technology (ICCT-Pacific), International Conference on

作者： Nobuyuki Ishii Aoi Kondo Hiroaki Koga Dept. Control and Information Systems Engineering National Institute of Technology Kurume College Fukuoka Japan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

In recent years, the use of GPUs for computation has become commonplace in deep learning. It is not uncommon for deep learning labs to procure GPU servers for computation without standardising specifications such as GPU architecture and VRAM capacity, resulting in a heterogeneous GPU server environment. Container technology is also widely used as a method of isolating software execution environments. Among them, Docker is the de facto standard for container platforms. In this paper, we have developed a management system that can allocate deep learning training jobs to GPU servers (workers) using container technology to absorb differences in execution environments in heterogeneous GPU server environments. In experiments, we confirmed that the proposed system can estimate the completion time of training for each worker and can detect Out-Of-Memory (OOM) of GPUs in advance. We were able to confirm in advance the “inference time” and the “possibility of OOM”, which are difficult to predict when performing deep learning. We have succeeded in obtaining the “predicted value of learning time” and “possibility of OOM” that engineers need to know in advance, and have shown that the proposed system is effective in deep learning tests.

关键词： Deep learning Training Graphics processing units Containers Software Servers Resource management Proposals Standards Testing

来源：评论

学校读者我要写书评

暂无评论

Verification of the Effect of Label Modification on Neural Network Learning

Verification of the Effect of Label Modification on Neural N...

引用

Consumer Technology (ICCT-Pacific), International Conference on

作者： Tsubasa Oka Hiroaki Koga Dept. Control and Information Systems Engineering National Institute of Technology Kurume College Fukuoka Japan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

This study focuses on the problem of subjective labeling that arises in the application of machine learning with neural networks to the medical field. The first problem is that of subjectivity, which arises because the labeling of medical data relies on expert knowledge and the process can be subjective. The second problem is the reduced information content of labels caused by discrete and quantitative labeling. If the intermediate values between the discrete values also have evaluative meaning, the detailed information is lost due to the discrete numerical labeling. We focus on such instability in labels and propose an approach to label modification using values inferred during neural network training. Specifically, we consider labels that are discrete, quantitative numbers as continuous numbers, compare the inferred value with the label value at each step in the learning phase, and compare the label value with the inferred value at each step in the learning phase. The update method is to give the label a sign-responsive variation. The goal is to modify each label using the value inferred by the inference made during learning in this way. As an experiment, we conducted an experiment on label modification under pseudo-conditions to verify its effectiveness. The results showed that when the amount of label modification was controlled by a constant, the generalization performance and the nature of label modification differed depending on the constant. In particular, generalization performance was improved when the constant of the label modification amount was determined so that the label value was separated from the inferred value at each step.

关键词： Training Neural networks Machine learning Labeling

来源：评论

学校读者我要写书评

暂无评论

Multi-Point Positional Insertion Tuning for Small Object Detection

Multi-Point Positional Insertion Tuning for Small Object Det...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kanoko Goto Takumi Karasawa Takumi Hirose Rei Kawakami Nakamasa Inoue Dept. of Computer Science Institute of Science Tokyo Tokyo Japan Dept. of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object detection models has emerged as a promising approach. However, finetuning large models is computationally and memory expensive. To address this issue, this paper introduces multi-point positional insertion (MPI) tuning, a parameter-efficient finetuning (PEFT) method for small object detection. Specifically, MPI incorporates multiple positional embeddings into a frozen pretrained model, enabling the efficient detection of small objects by providing precise positional information to latent features. Through experiments, we demonstrated the effectiveness of the proposed method on the SODA-D dataset. MPI performed comparably to conventional PEFT methods, including CoOp and VPT, while significantly reducing the number of parameters that need to be tuned.

关键词： Computational modeling Object detection Signal processing Feature extraction Encoding Acoustics Speech processing Tuning

来源：评论

学校读者我要写书评

暂无评论

Comparison of Track Management Strategies in Automotive Track-to-Track Fusion Algorithms

Comparison of Track Management Strategies in Automotive Trac...

引用

International Symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： László Lindenmaier Szilárd Aradi Tamás Bécsi Balázs Fekete Dept. of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Budapest Hungary Dept. of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350379365

ISBN: (纸本)9798350379372

advanced driver assistance and automated driving systems rely on an enhanced perception, which requires a reliable fusion of heterogeneous data from multiple sensors. Track-to-track fusion is a commonly used architecture in automotive perception systems. However, track management is still under-discussed among other modules of track-to-track fusion, i.e., association and state fusion, despite its significant impact on the fidelity of the fused data. Track management is responsible for maintaining the fused track list by handling appearing and disappearing objects and, more importantly, determining if a sensor track was generated by a real target or false detections. In this paper, we compare different track management strategies using simulated and real data from a radar-camera sensor cluster, analyzing their false alarm filtering effectiveness.

关键词： Target tracking Sensor fusion Radar tracking Sensor systems Reliability Informatics Machine intelligence Intelligent sensors Automotive engineering Vehicles

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：