检索结果-内蒙古大学图书馆

SLAM-based Joint Calibration of Multiple Asynchronous Microphone Arrays and Sound Source Localization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Jiang He, Yuanzheng Su, Daobilige Itoyama, Katsutoshi Nakadai, Kazuhiro Wu, Junfeng Huang, Shoudong Li, Youfu Kong, He The Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology No. 1088 Xueyuan Avenue Shenzhen China The College of Engineering China Agricultural University Beijing China The Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan The School of Data Science The Chinese University of Hong Kong Shenzhen China The Robotics Institute University of Technology Sydney Sydney Australia The Department of Mechanical Engineering City University of Hong Kong Hong Kong

Robot audition systems with multiple microphone arrays have many applications in practice. However, accurate calibration of multiple microphone arrays remains challenging because there are many unknown parameters to be identified, including the relative transforms (i.e., orientation, translation) and asynchronous factors (i.e., initial time offset and sampling clock difference) between microphone arrays. To tackle these challenges, in this paper, we adopt batch simultaneous localization and mapping (SLAM) for joint calibration of multiple asynchronous microphone arrays and sound source localization. Using the Fisher information matrix (FIM) approach, we first conduct the observability analysis (i.e., parameter identifiability) of the above-mentioned calibration problem and establish necessary/sufficient conditions under which the FIM and the Jacobian matrix have full column rank, which implies the identifiability of the unknown parameters. We also discover several scenarios where the unknown parameters are not uniquely identifiable. Subsequently, we propose an effective framework to initialize the unknown parameters, which is used as the initial guess in batch SLAM for multiple microphone arrays calibration, aiming to further enhance optimization accuracy and convergence. Extensive numerical simulations and real experiments have been conducted to verify the performance of the proposed method. The experiment results show that the proposed pipeline achieves higher accuracy with fast convergence in comparison to methods that use the noise-corrupted ground truth of the unknown parameters as the initial guess in the optimization and other existing frameworks. © 2024, CC BY.

关键词： Mapping

A Generic Load Flow Solution for Droop-Controlled AC Microgrids Considering Electric Vehicle Loads

学校读者我要写书评

暂无评论

A Generic Load Flow Solution for Droop-Controlled AC Microgr...

International Conference on Power Electronic Drives

作者： Ghanshyam Meena Akhilesh Mathur V. P. Singh Krishna Murari Sukumar Kamalasadan Department of Electrical Engineering Malaviya National Institute of Technology Jaipur Rajasthan India Electrical Engineering and Computer Science Department The University of Toledo Toledo Ohio USA Department of Electrical Engineering Power Energy and Intelligent Systems Laboratory EPIC University of North Carolina at Charlotte Charlotte NC USA

ISBN: (数字)9798350372472

ISBN: (纸本)9798350372489

Microgrids (MGs) have become more unpredictable due to integration of renewable generation sources. Several methods are used to solve load flow problems in MGs. Load flow analysis is a complex problem for islanded MGs due to the absence of slack bus and dependency of active power generation of droop-controlled DGs on frequency. In this paper, a Modified Newton Raphson (MNR) approach is used to perform load flow analysis of isolated MGs considering various types of electric vehicle (EV) loads. The presented method has been validated on 6-bus and 38-bus test systems of the islanded microgrid to give an accurate and simple approach for computing the load flow solutions.

关键词： Renewable energy sources Microgrids Drives Electric vehicles Software Power electronics Distributed power generation Planning MATLAB Load flow analysis

Model-agnostic Body Part Relevance Assessment for Pedestrian Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Günder, Maurice Banerjee, Sneha Sifa, Rafet Bauckhage, Christian Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Schloss Birlinghoven Sankt Augustin53757 Germany University of Bonn Institute for Computer Science III Friedrich-Hirzebruch-Allee 5 Bonn53115 Germany RWTH Aachen University Department of Computer Science Ahornstraße 55 Aachen52074 Germany

Model-agnostic explanation methods for deep learning models are flexible regarding usability and availability. However, due to the fact that they can only manipulate input to see changes in output, they suffer from weak performance when used with complex model architectures. For models with large inputs as, for instance, in object detection, sampling-based methods like KernelSHAP are inefficient due to many computation-heavy forward passes through the model. In this work, we present a framework for using sampling-based explanation models in a computer vision context by body part relevance assessment for pedestrian detection. Furthermore, we introduce a novel sampling-based method similar to KernelSHAP that shows more robustness for lower sampling sizes and, thus, is more efficient for explainability analyses on large-scale datasets. © 2023, CC BY-NC-ND.

关键词： Object detection

Ensemble Kalman Inversion for Image Guided Guide Wire Navigation in Vascular systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hanu, Matei Hesser, Jürgen Kanschat, Guido Moviglia, Javier Schillings, Claudia Stallkamp, Jan FU Berlin Department of Mathematics and Computer Science Berlin14195 Germany Mannheim Institute for Intelligent Systems in Medicine Heidelberg University Mannheim Germany Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany

This paper addresses the challenging task of guide wire navigation in cardiovascular interventions, focusing on the parameter estimation of a guide wire system using Ensemble Kalman Inversion (EKI) with a subsampling technique. The EKI uses an ensemble of particles to estimate the unknown quantities. However since the data misfit has to be computed for each particle in each iteration, the EKI may become computationally infeasible in the case of high-dimensional data, e.g. high-resolution images. This issue can been addressed by randomised algorithms that utilize only a random subset of the data in each iteration. We introduce and analyse a subsampling technique for the EKI, which is based on a continuous-time representation of stochastic gradient methods and apply it to on the parameter estimation of our guide wire system. Numerical experiments with real data from a simplified test setting demonstrate the potential of the *** Codes 65N21, 90C56, 68W20, 60J25 Copyright © 2023, The Authors. All rights reserved.

关键词： Parameter estimation

OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiang, Qiuchi Cheng, Jintao Luo, Jiehao Wu, Jin Fan, Rui Chen, Xieyuanli Tang, Xiaoyu School of Data Science and Engineering Xingzhi College South China Normal University Shanwei516600 China School of Electronic and Information Engineering South China Normal University Guangdong Foshan528225 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong College of Intelligence Science and Technology National University of Defense Technology Changsha China College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods utilize mundane point cloud representations as input and deep learning-based LiDAR-based Place Recognition (LPR) approaches employing different point cloud image inputs with convolutional neural networks (CNNs) or transformer architectures. However, the recently proposed Mamba deep learning model, combined with state space models (SSMs), holds great potential for long sequence modeling. Therefore, we developed OverlapMamba, a novel network for place recognition, which represents input range views (RVs) as sequences. In a novel way, we employ a stochastic reconstruction approach to build shift state space models, compressing the visual representation. Evaluated on three different public datasets, our method effectively detects loop closures, showing robustness even when traversing previously visited locations from different directions. Relying on raw range view inputs, it outperforms typical LiDAR and multi-view combination methods in time complexity and speed, indicating strong place recognition capabilities and realtime efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

Fairer Machine Learning Through the Hybrid of Multi-objective Evolutionary Learning and Adversarial Learning

学校读者我要写书评

暂无评论

Fairer Machine Learning Through the Hybrid of Multi-objectiv...

International Joint Conference on Neural Networks (IJCNN)

作者： Shenhao Gui Qingquan Zhang Changwu Huang Bo Yuan Research Institute of Trustworthy Autonomous Systems (RITAS) Southern University of Science and Technology (SUSTech) Shenzhen China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology (SUSTech) Shenzhen China

With growing concerns about the unwanted bias or discrimination in machine learning, a number of fairness-aware machine learning algorithms have been developed to mitigate bias in the prediction. Because the objectives of accuracy and fairness are antagonistic, it is hard to balance the trade-off between them. Recently, Multi-objective Evolutionary Learning (MOEL) framework has been proposed to train a set of Pareto models with the consideration of accuracy and fairness simultaneously. However, this framework prefers to train more accurate models rather than fairer models due to the lack of gradient in terms of fairness. In this paper, MOEL is enhanced through introducing Adversarial Learning (AL). The MOEL-AL framework aims to maximize a set of predictors' ability to predict true labels and minimize the ability of an adversarial network to predict the sensitive attributes from the predictors' output. Specifically, the adversarial network can be regarded as a proxy of the undifferentiable fairness metrics, so it is possible to propagate gradients in terms of both accuracy and fairness for the predictors during the back-propagation process. Besides, the adversarial strength for different predictors is adjusted dynamically according to their fairness metric. Compared with the state-of-the-art methods, experimental studies on seven well-known datasets show that our method can provide a set of fairer Pareto models with little drop on accuracy.

关键词：

Taming Cluster Synchronization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tomaselli, Cinzia Gambuzza, Lucia Valentina Sun, Gui-Quan Boccaletti, Stefano Frasca, Mattia Department of Electrical Electronics and Computer Science Engineering University of Catania Italy Sino-Europe Complex Science Center North University of China Taiyuan Shanxi030051 China Complex Systems Research Center Shanxi University Taiyuan Shanxi030006 China Institute of Interdisciplinary Intelligent Science Ningbo Univ. of Technology Ningbo China CNR - Institute of Complex Systems Sesto FiorentinoI-50019 Italy

Synchronization is a widespread phenomenon observed across natural and artificial networked systems. It often manifests itself by clusters of units exhibiting coincident dynamics. These clusters are a direct consequence of the organization of the Laplacian matrix eigenvalues into spectral localized blocks. We show how the concept of spectral blocks can be leveraged to design straightforward yet powerful controllers able to fully manipulate cluster synchronization of a generic network, thus shaping at will its parallel functioning. Specifically, we demonstrate how to induce the formation of spectral blocks in networks where such structures would not exist, and how to achieve precise mastering over the synchronizability of individual clusters by dictating the sequence in which each of them enters or exits the synchronization stability region as the coupling strength varies. Our results underscore the pivotal role of cluster synchronization control in shaping the parallel operation of networked systems, thereby enhancing their efficiency and adaptability across diverse applications. © 2024, CC BY.

关键词： Synchronization

Ensemble of CNN classifiers using Choquet Fuzzy Integral Technique for PCB Defect Classification

学校读者我要写书评

暂无评论

Ensemble of CNN classifiers using Choquet Fuzzy Integral Tec...

IEEE International Conference on computer Communication and the Internet (ICCCI)

作者： Boonchana Purahong Woranidtha Krungseanmuang Kasi Tenghongsakul Tuanjai Archevapanich Parkpoom Khunthawiwone Nitjaree Satayarak Attasit Lasakul Department of Computer Engineering School of Engineering King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Department of Robotics and Computational Intelligent Systems School of Engineering King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Department of Electrical Engineering School of Engineering King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Department of Electronics and Communication Engineering Faculty of Engineering and Architecture Rajamagala University of Technology Suvarnabhumi Nonthaburi Thailand

ISBN: (数字)9798350351767

ISBN: (纸本)9798350351774

This paper presents a novel method for detecting defects in printed circuit boards (PCBs) using an ensemble of classifiers based on the Choquet fuzzy integral. Our approach employs convolutional neural network (CNN) models, specifically ResNet152, VGG19, and InceptionV3 as base classifiers to identify six types of PCB defects: spurs, mouse bites, short circuits, open circuits, spurious copper, and pinholes. Given the critical role of PCBs in ensuring electronic equipment reliability, effective defect detection methods like ours are essential. We employ pre-trained CNN models for feature extraction and classification of PCB defects. Following this, we combine the prediction scores using the Choquet fuzzy integral to derive more accurate final labels, exceeding the accuracy of standalone models. Our approach is tested on PCB images obtained from public repositories, captured using a linear scan CCD. The evaluation results demonstrate average precision, recall, F-score, and accuracy of 93.0%, 95.2%, 95.1%, and 95.1%, respectively.

关键词： Measurement Accuracy Electronic equipment Printed circuits Predictive models Feature extraction Internet

A Feed-forward Switched Adaptive Filtering configuration for Underwater Acoustic Signal Denoising Technique with low-complexity

学校读者我要写书评

暂无评论

A Feed-forward Switched Adaptive Filtering configuration for...

OCEANS

作者： Deekshitha Adusumalli Swapnil Maiti S. Hannah Pauline Gerard Dooly Samiappan Dhanalakshmi Department of Electronics and Communication Engg. College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Tech. SRM Nagar Kattankulathur Kanchipuram Chennai India Center for Robotics and Intelligent Systems (CRIS) University of Limerick Limerick Ireland

The Underwater acoustic communication is difficult by virtue of the noise that exists undersea. This can be caused by both natural phenomena, like waves and currents, as well as artificial sources such as ships and boats. In order to reduce or eliminate this interference, it is necessary to process the signal before further processing. One way of doing this is through denoising. However, because noise constantly fluctuates in intensity, predicting its future behavior becomes almost impossible. To address this problem, we propose a new method for filtering underwater communications using an superlative feedfoward switched adaptive filter model using Signed Error variant of Least Mean Square (SELMS) and Signed Data variant of Least Mean Square (SDLMS) algorithm that takes into account signed form LMS values. The effectiveness of the filter is tested using a clean fish sound that has been tainted by noises from underwater vessels from the ShipsEar database.

关键词：