检索结果-南通市图书馆

Audio Mixing Inversion via Embodied Self-supervised Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine intelligence Research 2024年第1期21卷 55-62页

作者： Haotian Zhou Feng Yu Xihong Wu Department of AI Music and Music Information Technology Central Conservatory of MusicBeijing 100031China lab.ratory of Music artificial intelligence Laboratory of Philosophy and Social SciencesMinistry of EducationBeijing 100031China School of intelligence Science and Technology Peking UniversityBeijing 100871China

Audio mixing is a crucial part of music *** analyzing or recreating audio mixing,it is of great importance to conduct research on estimating mixing parameters used to create mixdowns from music recordings,i.e.,audio mixing ***,approaches of audio mixing inversion are rarely explored.A method of estimating mixing parameters from raw tracks and a stereo mixdown via embodied self-supervised learning is *** this work,several commonly used audio effects including gain,pan,equalization,reverb,and compression,are taken into *** method is able to learn an inference neural network that takes a stereo mixdown and the raw audio sources as input and estimate mixing parameters used to create the mixdown by iteratively sampling and *** the sampling step,the inference network predicts a set of mixing parameters,which is sampled and fed to an audio-processing framework to generate audio data for the training *** the training step,the same network used in the sampling step is optimized with the sampled data generated from the sampling *** method is able to explicitly model the mixing process in an interpretable way instead of using a black-box neural network model.A set of objective measures are used for *** experimental results show that this method has better performance than current state-of-the-art methods.

关键词： Audio mixing inversion intelligent audio mixing self-supervised learning audio signal processing deep learning

Spatially selective p-type doping for constructing lateral WS2 p-n homojunction via low-energy nitrogen ion implantation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2024年第6期13卷 1159-1169页

作者： Yufan Kang Yongfeng Pei Dong He Hang Xu Mingjun Ma Jialu Yan Changzhong Jiang Wenqing Li Xiangheng Xiao School of Physics and Technology Key Lab of Artificial Micro-and Nano-Structures of Ministry of EducationWuhan UniversityWuhanChina

The construction of lateral p-n junctions is very important and challenging in two-dimensional(2D)semiconductor manufacturing *** researches have demonstrated that vertical p-n junction can be prepared simply by vertical stacking of 2D ***,interface pollution and large area scalab.lity are challenges that are difficult to overcome with vertical stacking *** 2D lateral p-n homojunction is an effective strategy to address these *** selective p-type doping of 2D semiconductors is expected to construct lateral p-n *** this work,we have developed a low-energy ion implantation system that reduces the implanted energy to 300 ***-energy implantation can form a shallow implantation depth,which is more suitable for modulating the electrical and optical properties of 2D ***,we utilize low-energy ion implantation to directly dope nitrogen ions into few-layer WS_(2) and successfully realize a precise regulation for WS_(2) with its conductivity type transforming from n-type to bipolar or even p-type ***,the universality of this method is demonstrated by extending it to other 2D semiconductors,including WSe_(2),SnS_(2) and MoS_(2).Based on this method,a lateral WS_(2) p-n homojunction is fabricated,which exhibits significant rectification characteristics.A photodetector based on p-n junction with photovoltaic effect is also prepared,and the open circuit voltage can reach to 0.39 *** work provides an effective way for controllab.e doping of 2D semiconductors.

关键词： implantation doping Spatial

TEAM:Transformer Encoder Attention Module for Video Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2024年第2期48卷 451-477页

作者： Hae Sung Park Yong Suk Choi Department of artificial intelligence Hanyang UniversitySeoulKorea Department of Computer Science Hanyang UniversitySeoulKorea

Much like humans focus solely on object movement to understand actions,directing a deep learning model’s attention to the core contexts within videos is crucial for improving video *** the recent study,Video Masked Auto-Encoder(VideoMAE)employs a pre-training approach with a high ratio of tube masking and reconstruction,effectively mitigating spatial bias due to temporal redundancy in full video *** steers the model’s focus toward detailed temporal ***,as the VideoMAE still relies on full video frames during the action recognition stage,it may exhibit a progressive shift in attention towards spatial contexts,deteriorating its ability to capture the main spatio-temporal *** address this issue,we propose an attention-directing module named Transformer Encoder Attention Module(TEAM).This proposed module effectively directs the model’s attention to the core characteristics within each video,inherently mitigating spatial *** TEAM first figures out the core features among the overall extracted features from each *** that,it discerns the specific parts of the video where those features are located,encouraging the model to focus more on these informative ***,during the action recognition stage,the proposed TEAM effectively shifts the VideoMAE’s attention from spatial contexts towards the core spatio-temporal *** attention-shift manner alleviates the spatial bias in the model and simultaneously enhances its ability to capture precise video *** conduct extensive experiments to explore the optimal configuration that enables the TEAM to fulfill its intended design purpose and facilitates its seamless integration with the VideoMAE *** integrated model,i.e.,VideoMAE+TEAM,outperforms the existing VideoMAE by a significant margin on Something-Something-V2(71.3%vs.70.3%).Moreover,the qualitative comparisons demonstrate that the TEAM encourages the model to disregard insignificant featur

关键词： Video classification action recognition vision transformer masked auto-encoder

Unsupervised multi-modal image translation based on the squeeze-and-excitation mechanism and feature attention module

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2024年第1期30卷 23-30页

作者：胡振涛 HU Chonghao YANG Haoran SHUAI Weiwei School of artificial intelligence Henan UniversityZhengzhou 450046P.R.China 95795 Troops of the PLA Guilin 541003P.R.China

The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target ***,the multi-generator mechanism is employed among the advanced approaches availab.e to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image *** address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image ***,firstly,the domain code is introduced in this paper to explicitly control the different generation ***,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)***,the model integrates multiple optimization objectives to ensure efficient multi-modal *** paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing ***,experimental results have shown that the proposed method is versatile and scalab.e.

关键词： multi-modal image translation generative adversarial network(GAN) squeezeand-excitation(SE)mechanism feature attention(FA)module

维普期刊数据库

Intelligent 3D garment system of the human body based on deep spiking neural network

在线全文

学校读者我要写书评

暂无评论

虚拟现实与智能硬件（中英文） 2024年第1期6卷 43-55页

作者： Minghua JIANG Zhangyuan TIAN Chenyu YU Yankang SHI Li LIU Tao PENG Xinrong HU Feng YU School of Computer and artificial intelligence Wuhan Textile UniversityWuhan 430200China Engineering Research Center of Hubei Province for Clothing Information Wuhan 430200China

Background Intelligent garments,a burgeoning class of wearable devices,have extensive applications in domains such as sports training and medical ***,existing research in the smart wearables domain predominantly emphasizes sensor functionality and quantity,often skipping crucial aspects related to user experience and *** To address this gap,this study introduces a novel real-time 3D interactive system based on intelligent *** system utilizes lightweight sensor modules to collect human motion data and introduces a dual-stream fusion network based on pulsed neural units to classify and recognize human movements,thereby achieving real-time interaction between users and ***,the system incorporates 3D human visualization functionality,which visualizes sensor data and recognizes human actions as 3D models in real time,providing accurate and comprehensive visual feedback to help users better understand and analyze the details and features of human *** system has significant potential for applications in motion detection,medical monitoring,virtual reality,and other *** accurate classification of human actions contributes to the development of personalized training plans and injury prevention *** This study has substantial implications in the domains of intelligent garments,human motion monitoring,and digital twin *** advancement of this system is expected to propel the progress of wearable technology and foster a deeper comprehension of human motion.

关键词： Intelligent garment system Internet of things Human action recognition Deep learning 3D visualization

维普期刊数据库

A novel graph oversampling framework for node classification in class-imbalanced graphs

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第6期67卷 214-229页

作者： Riting XIA Chunxu ZHANG Yan ZHANG Xueyan LIU Bo YANG Key lab.ratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University College of artificial intelligence Jilin University College of Computer Science and Technology Jilin University College of Communication Engineering Jilin University

Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关键词： graph neural network class-imbalanced graphs sum-product network oversampling node classification

同方期刊数据库

Orbital angular momentum-mediated machine learning for high-accuracy mode-feature encoding

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2024年第3期13卷 466-477页

作者： Xinyuan Fang Xiaonan Hu Baoli Li Hang Su Ke Cheng Haitao Luan Min Gu Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for artificial-intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China

Machine learning with optical neural networks has featured unique advantages of the information processing including high speed,ultrawide bandwidths and low energy consumption because the optical dimensions(time,space,wavelength,and polarization)could be utilized to increase the degree of ***,due to the lack of the capability to extract the information features in the orbital angular momentum(OAM)domain,the theoretically unlimited OAM states have never been exploited to represent the signal of the input/output nodes in the neural network ***,we demonstrate OAM-mediated machine learning with an all-optical convolutional neural network(CNN)based on Laguerre-Gaussian(LG)beam modes with diverse diffraction *** proposed CNN architecture is composed of a trainable OAM mode-dispersion impulse as a convolutional kernel for feature extraction,and deep-learning diffractive layers as a *** resultant OAM mode-dispersion selectivity can be applied in information mode-feature encoding,leading to an accuracy as high as 97.2%for MNIST database through detecting the energy weighting coefficients of the encoded OAM modes,as well as a resistance to eavesdropping in point-to-point free-space ***,through extending the target encoded modes into multiplexed OAM states,we realize all-optical dimension reduction for anomaly detection with an accuracy of 85%.Our work provides a deep insight to the mechanism of machine learning with spatial modes basis,which can be further utilized to improve the performances of various machine-vision tasks by constructing the unsupervised learning-based auto-encoder.

关键词： polarization mode momentum

A PI+R Control Scheme Based on Multi-Agent Systems for Economic Dispatch in Isolated BESSs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第10期11卷 2154-2165页

作者： Yalin Zhang Zhongxin Liu Zengqiang Chen the College of artificial intelligence Nankai University the Tianjin Key lab.ratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University IEEE

Battery energy storage systems (BESSs) are widely used in smart ***,power consumed by inner impedance and the capacity degradation of each battery unit become particularly severe,which has resulted in an increase in operating *** general economic dispatch (ED) algorithm based on marginal cost (MC) consensus is usually a proportional(P) controller,which encounters the defects of slow convergence speed and low control *** order to solve the distributed ED problem of the isolated BESS network with excellent dynamic and steady-state performance,we attempt to design a proportional integral (PI) controller with a reset mechanism (PI+R) to asymptotically promote MC consensus and total power mismatch towards 0 in this *** be frank,the integral term in the PI controller is reset to 0 at an appropriate time when the proportional term undergoes a zero crossing,which accelerates convergence,improves control accuracy,and avoids *** eigenvalues of the system under a PI+R controller is well analyzed,ensuring the regularity of the system and enabling the reset *** ensure supply and demand balance within the isolated BESSs,a centralized reset mechanism is introduced,so that the controller is distributed in a flow set and centralized in a jump *** cope with Zeno behavior and input delay,a dwell time that the system resides in a flow set is *** on this,the system with input delays can be reduced to a time-delay free *** the capacity limitation of the battery,a modified MC scheme with PI+R controller is *** correctness of the designed scheme is verified through relevant simulations.

关键词： Battery energy storage system (BESS) distributed control economic dispatch multi-agent system reset control

Ultrahigh performance passive radiative cooling by hybrid polar dielectric metasurface thermal emitters

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Opto-Electronic Advances 2024年第4期7卷 17-25页

作者： Yinan Zhang Yinggang Chen Tong Wang Qian Zhu Min Gu Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for artificial-intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China

Real-world passive radiative cooling requires highly emissive,selective,and omnidirectional thermal emitters to maintain the radiative cooler at a certain temperature below the ambient temperature while maximizing the net cooling *** various selective thermal emitters have been demonstrated,it is still challenging to achieve these conditions sim-ultaneously because of the extreme difficulty in controlling thermal emission of photonic structures in *** we demonstrated hybrid polar dielectric metasurface thermal emitters with machine learning inverse design,en-abling a high emissivity of~0.92 within the atmospheric transparency window 8-13μm,a large spectral selectivity of~1.8 and a wide emission angle up to 80 degrees,*** selective and omnidirectional thermal emitter has led to a new record of temperature reduction as large as~15.4°C under strong solar irradiation of~800 W/m2,signific-antly surpassing the state-of-the-art *** designed structures also show great potential in tackling the urban heat island effect,with modelling results suggesting a large energy saving and deployment area *** research will make significant impact on passive radiative cooling,thermal energy photonics and tackling global climate change.

关键词： radiative cooling dielectric metasurfaces machine learning thermal emitters

维普期刊数据库