检索结果-内蒙古大学图书馆

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

作者： Hao Ma Zhiyuan Peng Xu Li Yukai Li Mingjie Shao Qiuqiang Kong Ju Liu School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University North Carolina USA ARC Lab Tencent PCG Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability.

关键词： Training Large language models Training data Signal processing Information leakage Acoustics Data models Data mining Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

A multiple criteria analysis approach for assessing regional and territorial progress toward achieving the Sustainable Development Goals in Italy

引用

Decision Analytics Journal 2025年 15卷

作者： Gastaldi, Massimo Uricchio, Antonio Felice Department of Computer Control and Management Engineering Sapienza University of Rome Rome 00185 Italy Department of Industrial and Information Engineering and Economics University of L'Aquila L'Aquila 67100 Italy President of the Governmental Agency for the Evaluation of Universities and Research System (ANVUR) Rome 00153 Italy University of Bari Aldo Moro Bari 70121 Italy

Sustainability is a pressing global challenge demanding an integrated approach balancing economic, environmental, and social perspectives. Numerous indicators have been proposed in the literature to assess progress toward the Sustainable Development Goals (SDGs), including equitable and sustainable well-being (BES). To effectively manage and monitor these indicators, robust analytical models are essential. The present study proposed an integrated analytical framework combining the 0–1 (min–max) method and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The analysis examined 61 indicators from the 2024 Equitable and Sustainable Well-being of the Territories, a dataset developed by the Italian National Institute of Statistics (ISTAT) to assess regional social, economic, and environmental sustainability across Italy. The results confirmed a persistent north–south divide, with average scores of 3.9 in the north and 1.4 in the south on a 1–5 scale, and central Italy demonstrating an intermediate performance of 3.1. At the regional level, Trentino-Alto Adige, Lombardia, and Valle d'Aosta emerged as top performers, while at the territorial level, Milano, Bologna, and Trieste stood out. These insights highlight the need for stronger synergies between territories to enhance competitiveness and elevate “Made in Italy” on the global stage. Effective regional collaboration may optimize resource allocation, harmonize territorial disparities, and accelerate progress toward the SDGs by leveraging local strengths and fostering sustainable development. © 2025 The Author(s)

关键词： Min-Max method Multiple criteria decision analysis Performance indicators Regional and territorial analysis Sustainable Development Goals TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Dynamic event-triggered mechanism-based design of H_∞ reliable state estimator for discrete-time neural networks

引用

International Journal of systems Science 2025年

作者： Guo, Siyu Luo, Yuqiang Zhu, Kaiqun Lin, Hong Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai China Informatization Office University of Shanghai for Science and Technology Shanghai China Shanghai Key Lab of Modern Optical System Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai China State Key Laboratory of Internet of Things for Smart City University of Macau Macao Institute of Intelligence Science and Engineering Shenzhen Polytechnic University Shenzhen China

In this paper, we investigate the reliable (Formula presented.) state estimation problem for discrete-time neural networks, where the activation function is assumed to satisfy a prescribed nonlinearity condition. To alleviate communication burden and save transmission energy, a dynamic event-triggered mechanism (DETM) is employed in the communication procedure. Considering the possible failures experienced by the data receiving register in engineering practice, a failure matrix is introduced to characterise the real received measurements. Initially, based on the obtained measurements, we design a full-order state estimator for the target neural networks. Through introducing new vectors of error and augmentation, the state estimation error dynamics is established. Then, by applying Lyapunov stability theory, matrix theory, nonlinearity analysis, and the relevant lemmas, both the asymptotical stability and the (Formula presented.) performance of the augmented error dynamics are thoroughly analysed, and the corresponding criteria are derived. Next, the target estimator parameter is determined based on the analysis of stability and disturbance attenuation. The effectiveness of the proposed estimation approach is demonstrated through a numerical example. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： DETM failure matrix H∞ performance measurement failures Neural network nonlinearity function reliable estimation stability analysis state estimation

来源：评论

学校读者我要写书评

暂无评论

A NEW TABULAR FORM FOR DETERMINING ROOT DISTRIBUTION OF A COMPLEX POLYNOMIAL WITH RESPECT TO THE IMAGINARY AXIS

引用

IEEE TRANSACTIONS ON AUTOMATIC control 1993年第10期38卷 1536-1541页

作者： CHEN, SS TSAI, JSH Control System Laboratory Department of Electrical Engineering National Cheng-Kung University

The original Routh table dealing with real polynomials is further investigated for complex polynomials. A new tabular form for determining root distribution of a complex polynomial with respect to the imaginary axis is developed, and modified procedures for directly treating singularities in the array are proposed. Also, new procedures are developed for determining the respective orders of simple and/or repeated roots lying on the imaginary axis. As a result, the situation of conditional stability or instability can be distinguished by the criteria developed in this note.

关键词： Polynomials Parameter estimation control systems Stability criteria Linear regression Heuristic algorithms Signal processing algorithms Recursive estimation Yield estimation Linear systems

来源：评论

学校读者我要写书评

暂无评论

PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport

arXiv

引用

arXiv 2025年

作者： Guo, Tian Yuan, Hui Liu, Qi Su, Honglei Hamzaoui, Raouf Kwong, Sam School of Control Science and Engineering Shandong University Jinan250061 China Key Laboratory of Machine Intelligence and System Control Ministry of Education Ji’nan250061 China School of Electronic Information Qingdao University Qingdao266071 China School of Engineering and Sustainable Development De Montfort University LeicesterLE1 9BH United Kingdom Department of Computing and Decision Science Lingnan University Hong Kong

Point cloud compression significantly reduces data volume but sacrifices reconstruction quality, highlighting the need for advanced quality enhancement techniques. Most existing approaches focus primarily on point-to-point fidelity, often neglecting the importance of perceptual quality as interpreted by the human visual system. To address this issue, we propose a generative adversarial network for point cloud quality enhancement (PCE-GAN), grounded in optimal transport theory, with the goal of simultaneously optimizing both data fidelity and perceptual quality. The generator consists of a local feature extraction (LFE) unit, a global spatial correlation (GSC) unit and a feature squeeze unit. The LFE unit uses dynamic graph construction and a graph attention mechanism to efficiently extract local features, placing greater emphasis on points with severe distortion. The GSC unit uses the geometry information of neighboring patches to construct an extended local neighborhood and introduces a transformer-style structure to capture long-range global correlations. The discriminator computes the deviation between the probability distributions of the enhanced point cloud and the original point cloud, guiding the generator to achieve high quality reconstruction. Experimental results show that the proposed method achieves state-of-the-art performance. Specifically, when applying PCE-GAN to the latest geometry-based point cloud compression (G-PCC) test model, it achieves an average BD-rate of -19.2% compared with the PredLift coding configuration and -18.3% compared with the RAHT coding configuration. Subjective comparisons show a significant improvement in texture clarity and color transitions, revealing finer details and more natural color gradients. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High Speed Autofocusing system for Micro system Applications

引用

Journal of Electronic Science and Technology 2016年第1期14卷 73-79页

作者： Phuchong Sripolsaen Pradit Mittrapiyanuruk Pakorn Keawtrakulpong the Deptartment of Control System and Instrumentation Engineering Faculty of EngineeringKing Mongkut’s University of Technology Thonburi (KMUTT) the Department of Mathematics Faculty of ScienceSrinakharinwirot University the Department of Control System and Instrumentation Engineering Faculty of EngineeringKMUTT

In this paper,we present a high speed autofocus system for micro system applications and design a look-up-table based autofocusing algorithm for applications when a target object is always visible,e.g.,manufacturing parts with alignment *** perform an evaluation of 24 focus measures to verify that which focus measure is the best for the look-up-table based *** the evaluation,we find that the Chebyshev moments-based focus measure（CHEB） is the most ***,we also develop a look-up-table based autofocus system that uses CHEB as the focus *** training phase,we offline construct a table from training images of an object that are captured at several lens *** entry of table consists of focus measure computed from image and lens *** working phase,given an input image,the algorithm first computes the focus measure and then finds the best match focus measure from the table and looks up the corresponding lens position for moving it into the in-focus *** algorithm can perform autofocusing within only 2 steps of lens *** experiment shows that the system can perform high speed autofocusing of micro objects.

关键词： High speed autofocusing look-up table micro system

来源：评论

学校读者我要写书评

暂无评论

APPLICATIONS OF THE FUZZY-LOGIC IN AUTOMATED ROBOTIC DEBURRING

引用

FUZZY SETS AND systemS 1994年第3期63卷 293-305页

作者： LIU, MH WIENAND, S Department of Control Engineering Control System Theory & Robotics Group Technical University of Darmstadt Darmstadt Germany

Some applications of the fuzzy logic in the automated robotic deburring are described. Main motivations for these applications are (1) the unpredictability of positional inaccuracies and variations of buff sizes, which are difficult to measure;and (2) the nonlinear and complex behaviour of the deburring process. For a passive deburring strategy the fuzzy logic is used to supervise positional inaccuracies, to directly process disturbed force/torque measurements to avoid time delays, and to adjust controller parameters according to working conditions. For an active deburring strategy a fuzzy man-machine interface is built to take the advantage of utilizing operator's knowledges about buff characteristics, and a fuzzy modeling algorithm is developed to get the input-output relationship of, and to extract qualitative understanding about the deburring process. Some experimental results are presented.

关键词： DEBURRING FORCE control FUZZY LOGIC LINGUISTIC MODELING MAN-MACHINE INTERFACE ROBOTS

来源：评论

学校读者我要写书评

暂无评论

Self-Tuning Clamping Force control with Optimal Trajectory Tracking for Autonomous Pipe Inspection Robots

SSRN

引用

SSRN 2025年

作者： Sun, Guoxin Xia, Longfei Du, Xinpeng Yu, Qihui Zhang, Jianlong Qin, Ripeng School of Mechanical Engineering Inner Mongolia University of Science and Technology Inner Mongolia Autonomous Region Baotou014010 China Inner Mongolia Engineering Technology Research Center of Mechatronics System Intelligent Diagnosis & Control Engineering 014010 China Inner Mongolia Ming yang North Smart Energy Research and Development Center Co LTD China Department of Mechanical Engineering Denmark Inner Mongolia University of Science and Technology China

In response to the limitations of existing external pipe-crawling robots, which are unable to automatically adjust clamping force during operation, a novel external pipe-crawling robot has been designed. To enable adaptive clamping based on varying pipeline conditions, an adaptive clamping force control method based on optimal speed curve tracking is proposed. First, the target clamping force is calculated according to pipeline conditions, and it is then converted into a target speed signal through optimal speed curve planning. Subsequently, the motor precisely tracks the speed signal to achieve accurate clamping force control. Experimental results from the robot prototype demonstrate that the proposed algorithm maintains a clamping force control error rate of less than 8.0% under pipelines with different diameters, inclination angles, and surface roughness, ensuring stable operation across various pipeline conditions. © 2025, The Authors. All rights reserved.

关键词： Clamping devices

来源：评论

学校读者我要写书评

暂无评论

FURTHER RESEARCH OF A NEW KIND OF SERIES REPAIRABLE system

引用

Journal of systems Science & Complexity 2012年第4期25卷 744-758页

作者： Lina GUO Houbao XU Chao GAO Guangtian ZHU Department of Mathematics Taiyuan University of Technology Department of Mathematics Beijing Institute of Technology Department of System Engineering Beijing Institute of Information and Control Academy of Mathematics and System Sciences Chinese Academy of Sciences

This paper is devoted to studying the uniqueness and existence of the system dynamic solution by using C0-semigroup theory and discussing its exponential stability by analyzing the spectrul distribution of system operator and its quasi-compactness. Some primary reliability indices are discussed with the eigenfunction of system operator and the optimal vacation time to get the maximum system profit is analyzed at the end of paper.

关键词： Co-semigroup theory dynamic solution exponential stability profit analysis reliability indices steady-state solution.

来源：评论

学校读者我要写书评

暂无评论

A Full-Lifecycle Calibration Method for Camera and LiDAR in Autonomous Driving

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wei, Ming Lu, Jun-Guo Ye, Nan Zhu, Zhen Zhang, Qinghao Wang, Yafei Shanghai Jiao Tong University Ministry of Education of China Department of Automation and the Key Laboratory of System Control and Information Processing Shanghai200240 China Nanjing University of Aeronautics and Astronautics College of Mechanical and Electrical Engineering Nanjing210016 China Shanghai Jiao Tong University School of Mechanical Engineering Shanghai200240 China

In recent years, advancements in light laser detection and ranging (LiDAR) and camera technologies have brought increasing attention to autonomous driving. Sensor fusion provides complementary information that overcomes the limitations of individual sensors and improves the safety of autonomous vehicles. The key to achieving this fusion lies in sensor calibration. This article presents a full-lifecycle calibration method that integrates offline and online processes to achieve high-precision and efficient calibration for camera-LiDAR systems in autonomous driving. The proposed approach unifies the calibration stages, addressing both the initial factory calibration and the dynamic adjustments required during vehicle operation. Offline calibration is performed using specialized calibration boards and standardized workflows to establish accurate initial parameters, ensuring a robust foundation for subsequent operations. Online calibration leverages a learning-based, end-to-end deep declarative network to dynamically adjust calibration parameters in real time, compensating for sensor displacement caused by vibration, loosening, or collisions. Extensive experiments are conducted to validate the proposed method. The accuracy and robustness of the offline calibration are validated through quantitative and qualitative results in simulated and real-world tests. Competitive precision in online calibration is demonstrated on public datasets, with average translation errors of 0.667 and 1.937 cm, and average rotation errors of 0.149° and 0.138° achieved on the KITTI and NuScenes datasets, respectively. Additionally, the online calibration method’s real-time capability is confirmed in practical experiments, with a frame rate of approximately 11 frames/s. This full-lifecycle calibration method significantly improves the accuracy, reliability, and long-term stability of autonomous driving systems, addressing critical challenges in sensor calibration across diverse environments. © 1

关键词： Autonomous 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：