检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Mingfei Shlizerman, Eli Department of Electrical & Computer Engineering University of Washington Seattle United States Department of Applied Mathematics University of Washington Seattle United States

We propose a novel approach for rendering high-quality spatial audio for 3D scenes that is in synchrony with the visual stream but does not rely or explicitly conditioned on the visual rendering. We demonstrate that such an approach enables the experience of immersive virtual tourism - performing a real-time dynamic navigation within the scene, experiencing both audio and visual content. Current audio-visual rendering approaches typically rely on visual cues, such as images, and thus visual artifacts could cause inconsistency in the audio quality. Furthermore, when such approaches are incorporated with visual rendering, audio generation at each viewpoint occurs after the rendering of the image of the viewpoint and thus could lead to audio lag that affects the integration of audio and visual streams. Our proposed approach, AV-Cloud, overcomes these challenges by learning the representation of the audio-visual scene based on a set of sparse AV anchor points, that constitute the Audio-Visual Cloud, and are derived from the camera calibration. The Audio-Visual Cloud serves as an audio-visual representation from which the generation of spatial audio for arbitrary listener location can be generated. In particular, we propose a novel module Audio-Visual Cloud Splatting which decodes AV anchor points into a spatial audio transfer function for the arbitrary viewpoint of the target listener. This function, applied through the Spatial Audio Render Head module, transforms monaural input into viewpoint-specific spatial audio. As a result, AV-Cloud efficiently renders the spatial audio aligned with any visual viewpoint and eliminates the need for pre-rendered images. We show that AV-Cloud surpasses current state-of-the-art accuracy on audio reconstruction, perceptive quality, and acoustic effects on two real-world datasets. AV-Cloud also outperforms previous methods when tested on scenes "in the wild". © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tell What You Hear From What You See - Video to Audio Generation Through Text 38

Tell What You Hear From What You See - Video to Audio Genera...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Xiulong Su, Kun Shlizerman, Eli Department of Electrical & Computer Engineering University of Washington Seattle United States Department of Applied Mathematics University of Washington Seattle United States

The content of visual and audio scenes is multi-faceted such that a video stream can be paired with various audio streams and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description (caption) of the audio. Such a framework has two unique advantages: i) Video-to-Audio generation process can be refined and controlled via text which complements the context of the visual information, and ii) The model can suggest what audio to generate for the video by generating audio captions. VATT consists of two key modules: VATT Converter, which is an LLM that has been fine-tuned for instructions and includes a projection layer that maps video features to the LLM vector space, and VATT Audio, a bi-directional transformer that generates audio tokens from visual frames and from optional text prompt using iterative parallel decoding. The audio tokens and the text prompt are used by a pretrained neural codec to convert them into a waveform. Our experiments show that when VATT is compared to existing video-to-audio generation methods in objective metrics, such as VGGSound audiovisual dataset, it achieves competitive performance when the audio caption is not provided. When the audio caption is provided as a prompt, VATT achieves even more refined performance (with lowest KLD score of 1.41). Furthermore, subjective studies asking participants to choose the most compatible generated audio for a given silent video, show that VATT Audio has been chosen on average as a preferred generated audio than the audio generated by existing methods. VATT enables controllable video-to-audio generation through text as well as suggest

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physics-Constrained Adversarial Training for Neural Networks in Stochastic Power Grids

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1121-1131页

作者： Li, Wenting Deka, Deepjyoti Wang, Ren Paternina, Mario R. Arrieta LANL Applied Mathematics and Plasmas Physics Division Los AlamosNM87544 United States Illinois Institute of Technology Department of Electrical and Computer Engineering ChicagoIL60616 United States National Autonomous University of Mexico Department of Electrical Engineering Mexico City04510 Mexico

The growth in distributed energy resources (DERs) is an important step toward solving the global climate crisis. However, many DERs, such as wind and solar power, are random and intermittent, causing the data in power grids to be perturbed with high uncertainty. Such perturbations degrade the performance of data-driven algorithms introduced in power grids for sensing and control. Existing approaches can strengthen machine learning models against well-designed malicious attacks. However, such physics-agnostic efforts fail to ensure the robustness of natural perturbations in power grids, that occur due to varying loads and changes in control inputs. This article proposes a novel physics-constrained adversarial training method for robustifying neural networks for the crucial problem of locating edge-faults in power grids. Our approach relies on first deriving analytical physical laws that are satisfied by state perturbations in realistic grids and then using the descriptive sets during adversarial training. Compared to state-of-the-art methods, our perturbation-robust neural networks have higher robust accuracy as well as training efficiency. Also, we demonstrate that the proposed approach achieves a tighter upper bound of robust risks than traditional efforts. The numerical experimental results in the IEEE 68-bus benchmark system validate our adversarial training in two scenarios when loads and control inputs vary randomly. The proposed method shows superior performance in accuracy and efficiency for different perturbed datasets. In addition, we testify the influence of different inputs on the robustness. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Strategic Renewable Energy Resource Selection Using a Fuzzy Decision-Making Method

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2117-2134页

作者： Anas Quteishat M.A.A.Younis Electrical Engineering Department Faculty of Engineering TechnologyAl-Balqa Applied UniversityAl-SaltJordan Department of Electrical and Computer Engineering Sohar UniversitySultanate of Oman

Renewable energy is created by renewable natural resources such as geothermal heat,sunlight,tides,rain,and *** resources are vital for all countries in terms of their economies and *** a result,selecting the optimal option for any country is critical in terms of energy *** country is nowadays planning to increase the share of renewable energy in their universal energy sources as a result of global *** the present work,the authors suggest fuzzy multi-characteristic decision-making approaches for renew-able energy source selection,and fuzzy set theory is a valuable methodology for dealing with uncertainty in the presence of incomplete or ambiguous *** study employed a hybrid method for order of preference by resemblance to an ideal solution based on fuzzy analytical network process-technique,which agrees with professional assessment scores to be linguistic phrases,fuzzy numbers,or crisp *** hybrid methodology is based on fuzzy set ideologies,which calculate alternatives in accordance with professional functional requirements using objective or subjective *** best-suited renewable energy alternative is discovered using the approach presented.

关键词： Multi characteristic decision making framework fuzzy sets fuzzy theory renewable energy energy resource selection

来源：评论

学校读者我要写书评

暂无评论

Modelling and simulation of energy management of power-split hybrid electric vehicles using the discrete EVent system specification

引用

International Journal of Vehicle Systems Modelling and Testing 2024年第1期18卷 33-61页

作者： Maatoug, Abdelfettah Kharoubi, Sahraoui Maaskri, Moustafa Belalem, Ghalem Mahmoudi, Said Faculty of Applied Sciences Science and Technology Department University of Tiaret Tiaret14000 Algeria Faculty of Mathematics and Computer Science Computer Science Department University of Tiaret Tiaret14000 Algeria Faculty of Applied Sciences Electrical Engineering Department University of Tiaret Tiaret14000 Algeria Faculty of Exact and Applied Sciences Computer Science Department University of Oran 1 Ahmed Ben Bella Oran31000 Algeria Faculty of Engineering Computer Science Department University of Mons Mons7000 Belgium

This work provides a basis for studying energy management optimisation in power-split hybrid electric vehicles (PSHEVs) to reduce fuel consumption and increase powertrain efficiency by enforcing a strategy related to battery level and vehicle speed. Three modes were used to operate the vehicle to meet different situations related to available energy and desired speed. These are particularly abundance mode, ascetic mode and optimal mode. For this, a system was designed based on several sub-models written in the discrete EVent system (DEVS) specification. The vehicle's power train and control strategy models were created in the DEVSimPy environment, and a joint simulation was carried out from the composite sub models until the overall model is reached. Simulation results under several driving cycles showed that the proposed system improves the energy consumption of the vehicle in different operating modes of the engines and gives more opportunities to adopt electric motors in vehicle transmission. © 2024 Inderscience Enterprises Ltd.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

Relation Between electrical Grid Congestion and Bus Characteristics

Relation Between Electrical Grid Congestion and Bus Characte...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Verdaasdonk, Flin Vlasiou, Maria Hoogsteen, Gerwin Hurink, Johann University of Twente Department of Electrical Engineering Mathematics Computer Science Netherlands

ISBN: (纸本)9789531842976

electrical grids are increasingly congested, which causes stability and safety risks. To get more insights in how congestion can be managed, this paper analyses whether bus characteristics exist that have a consistent influence on grid loading. To study this, a metric for quantifying bus influence on grid loading is introduced and applied in two case studies. The first case study investigates if there are characteristics that correlate with congestion consistently, regardless of grid topology. The results from this case study suggest that none of the evaluated characteristics consistently correlate with grid loading. These results imply that topology should be explicitly considered in congestion management. The second case study investigates the variance in the correlation between bus characteristics and influence, within a single topology, over a variety of conditions. The results of the second case study suggest that this correlation is robust to reasonable changes in bus loads. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Degree-Based Entropy Descriptors of Graphenylene Using Topological Indices

引用

computer Modeling in engineering & Sciences 2023年第10期137卷 939-964页

作者： M.C.Shanmukha Sokjoon Lee A.Usha K.C.Shilpa Muhammad Azeem Department of Mathematics Bapuji Institute of Engineering&TechnologyDavanagere577004India Department of Computer Engineering(Smart Security) Gachon UniversitySeongnam13120South Korea Department of Mathematics Alliance School of Applied MathematicsAlliance UniversityBangalore562106India Department of Computer Science and Engineering Bapuji Institute of Engineering&TechnologyDavanagere577004India Department of Mathematics Riphah Institute of Computing and Applied SciencesRiphah International UniversityLahore54660Pakistan

Graph theory plays a significant role in the applications of chemistry,pharmacy,communication,maps,and aeronautical *** molecules of chemical compounds are modelled as a graph to study the properties of the *** geometric structure of the compound relates to a few physical properties such as boiling point,enthalpy,π-electron energy,andmolecular *** article aims to determine the practical application of graph theory by solving one of the interdisciplinary problems describing the structures of benzenoid hydrocarbons and *** topological index is an invariant of a molecular graph associated with the chemical structure,which shows the correlation of chemical structures using many physical,chemical properties and biological *** study aims to introduce some novel degree-based entropy descriptors such as ENTSO,ENTGH,ENTHG,ENTSS,ENTNSO,ENTNReZ1,ENTNReZ2 and ENTNSS using the respective topological ***,the above-mentioned entropy measures and physico-chemical properties of benzenoid hydrocarbons are fitted using linear regression models and calculated for graphenylene structure.

关键词： Topological descriptors weighted entropy graphenylene

来源：评论

学校读者我要写书评

暂无评论

Arbitrary style transfer system with split-and-transform scheme

引用

Multimedia Tools and Applications 2024年第23期83卷 62497-62517页

作者： Tu, Ching-Ting Lin, Hwei Jen Tsai, Yihjia Lin, Zi-Jun Department of Applied Mathematics National Chung Hsing University Taichung Taiwan Department of Computer Science and Information Engineering Tamkang University New Taipei Taiwan

For the subject of arbitrary image style transfer, there have been some proposed architectures that directly compute the transformation matrix of the whitening and coloring transformation (WCT) to obtain more satisfactory transformation results. However, calculating the transformation matrix of WCT is time-consuming. Li et al. trained a linear transformation module to generate a WCT transformation matrix for any pair of images, i.e., content image and style image, to avoid complex calculations and improves time efficiency. In this work, we introduce a flexible arbitrary image style transfer framework based on the LST, which uses deep neural networks to train a linear transformation matrix as the standard matrix for WCT. For the first part, inverse relationship between the Whitening matrix and the Coloring matrix w.r.t. the same image is enforced during the training of the linear transformation matrix, so that the resulting matrix will be more accurate and closer to the standard matrix of WCT. For the second part, a split-and-transform scheme is proposed. Unlike LST, which transforms the block of feature maps as a whole, the split-and-transform scheme divides the feature block into several smaller blocks and transforms them individually, so that the transformation is more localized, and the more the number of divided blocks, the more localized. In addition, the proposed split-and-transform scheme allows users to determine the number of divided blocks to flexibly control the locality of the transformations. Experimental results demonstrate the effectiveness and flexibility of the proposed framework by the high-quality stylized images and adjustable balance between globality and locality of transformations. The use of the split-and-transform scheme can reduce the computational time while preserving or even improving the stylization results. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Nonlinearity in Large-Cycle Cellular Automata

引用

Complex Systems 2025年第1期34卷 129-160页

作者： Mukherjee, Sukanya Adak, Sumit Department of Computer Science and Engineering Institute of Engineering and Management Kolkata University of Engineering and Management West Bengal Kolkata700091 India Department of Applied Mathematics and Computer Science DTU Compute Technical University of Denmark Kgs. Lyngby2800 Denmark

The class of maximal-length cellular automata (CAs) has gained significant attention over the last few years due to the fact that it can generate cycles with the longest possible lengths. For every l of the form l = 2n-1 where n ∈ , a cycle of length l can be generated by a cellular automaton (CA) of size ⌊log2 l⌋ + 1;this maximal-length CA is in fact the optimal (minimum-sized) CA to generate a cycle of length l. However, maximal-length CAs are, in general, linear and have some drawbacks. Moreover, it is nontrivial to address this problem for any l ∈ , that is, removing the constraint that l is of the form 2n-1. In this paper we therefore employ nonlinearity in the rules and aim to generate the near-optimal CA for any given cycle length l, meaning that the generated CAs will be of size n = (⌊log2 l⌋ + 1) + d, where the displacement d is as small as possible. We use a generic operator to concatenate a collection of component CAs of sizes n1, n2, …, nk by employing an evolutionary strategy. Here, n = n1 + n2 + ⋯ + nk and l ≥ lcm(1, 2, …, k ), where i (1 ≤ i ≤ k) is the maximum cycle length of a CA of size ni . An influencing factor in the design of component CAs is to achieve the near-optimal CA for a given cycle length. Here we consider nonlinear reversible large-cycle CAs as component CAs. We also measure the effectiveness of nonlinearity in large-cycle generation. © 2025, Complex Systems Publications, Inc. All rights reserved.

关键词： CAs cellular automata evolution large-cycle CA neighborhood dependent nonlinearity reversible CAs

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Power of Sparse Neural Networks for Feature Selection 27

Unveiling the Power of Sparse Neural Networks for Feature Se...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Atashgahi, Zahra Liu, Tennison Pechenizkiy, Mykola Veldhuis, Raymond Mocanu, Decebal Constantin van der Schaar, Mihaela Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Netherlands Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Department of Computer Science University of Luxembourg Luxembourg

ISBN: (纸本)9781643685489

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared to dense networks. This paper addresses these gaps by presenting a comprehensive systematic analysis of feature selection with sparse neural networks. Moreover, we introduce a novel metric considering sparse neural network characteristics, which is designed to quantify feature importance within the context of SNNs. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than 50% memory and 55% FLOPs reduction compared to the dense networks, while outperforming them in terms of the quality of the selected features. © 2024 The Authors.

关键词：

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：