检索结果-内蒙古大学图书馆

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

作者： Shuai Huang Yongxiong Wang Huan Luo Shuwen Jia Han Chen Chendong Qin Zhongcai He Rui Luo School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China Institute of Foreign Languages University of Shanghai for Science and Technology Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Auditory attention detection (AAD) from electroencephalography (EEG) signals has garnered significant interest for its potential in brain-computer interfaces and hearing aids. Nevertheless, accurate decoding remains challenging due to the high-dimensional, non-stationary, and inherently noisy characteristics of EEG signals. We introduce SSAAD, a novel self-supervised approach for binary AAD with three key innovations: (1) A multi-scale temporal-frequency graph convolutional network (MST-GCN) is developed to effectively capture both spatial and temporal EEG dynamics; (2) A hierarchical self-supervised contrastive learning method is designed to cultivate robust EEG representations without extensive labeled data; (3) A bespoke triple-stage mixup data augmentation strategy is proposed to enhance model generalization. Additionally, MST-GCN initialization is achieved via EEG autoencoder pre-training, facilitating superior feature extraction. The method's effectiveness is evaluated on the KUL and DTU datasets, demonstrating state-of-the-art performance with accuracy improvements of 1.4% and 1.7% for 0.1-second windows, respectively.

关键词： Technological innovation Accuracy Graph convolutional networks Contrastive learning Hearing aids Data augmentation Brain modeling Electroencephalography Brain-computer interfaces Speech processing

来源：评论

学校读者我要写书评

暂无评论

Stabilization of Uncertain Parabolic PDE Systems Under Weighted Try-Once-Discard Protocol With Actuator Failures

引用

IEEE Transactions on Industrial Informatics 2025年

作者： Liu, Jinliang Zha, Lijuan Jiang, Wen Tian, Engang Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Nanjing Forestry University School of Science Nanjing210037 China Nanjing University of Finance and Economics College of Information Engineering Nanjing210023 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China

This article investigates the output feedback stabilization problem for a parabolic partial differential equation (PDE) system with uncertain parameters, which is subject to limited communication resources. First, to alleviate the burden of channel communication and avert data collision, the multichannel measurement outputs are scheduled by the weighted try-once-discard protocol. Moreover, to bridge the gap between theory and reality, the Markov process is utilized to depict the occurrence of various actuator faults in a stochastic manner. An impulsive closed-loop model is established in light of the network-induced delay and various stochastically occurring actuator faults. Following the model, sufficient criteria for guaranteeing the input-to-state stability of the PDE system are put forward by constructing a new Lyapunov functional. Then, one can deduce the determination of the controller gains and weighted matrices by employing the technique of linearizing the matrix inequalities. Finally, simulation results unequivocally demonstrate the effectiveness of the proposed method. © 2005-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

JPEG Reversible Data Hiding via Block Sorting Optimization and Dynamic Iterative Histogram Modification

引用

IEEE Transactions on Multimedia 2025年

作者： Li, Fengyong Wang, Qiankuan Cheng, Hang Zhang, Xinpeng Qin, Chuan Shanghai University of Electric Power College of Computer Science and Technology Shanghai201306 China Fuzhou University School of Mathematics and Statistics Fuzhou Fujian350108 China Fudan University School of Computer Science Shanghai200433 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China

JPEG reversible data hiding (RDH) refers to covert communication technology to accurately extract secret data while also perfectly recovering the original JPEG image. With the development of cloud services, a large number of private JPEG images can be efficiently managed in cloud platforms by embedding user ID or authentication labels. Nevertheless, data embedding operations may inadvertently disrupt the encoding sequence of the original JPEG image, resulting in severe distortion of the host image when it is re-compressed to JPEG format. To address this problem, this paper proposes a new JPEG RDH scheme based on block sorting optimization and dynamic iterative histogram modification. We firstly design a block ordering optimization strategy by combining the number of zero coefficients and the quantization table values of non-zero coefficients in a DCT block. Subsequently, a dynamic iterative histogram modification scheme is proposed by considering the local features and embedding capability of histograms generated from different texture images. According to the given payloads, we introduce different parameters to control the iterations of two-dimensional histogram and then adaptively generate the optimal histogram modification mapping, which can realize low JPEG file size increments by guaranteeing most of the AC coefficients unchanged as much as possible. Numerous experiments have shown that our scheme can achieve an effective balance among embedding capacity, visual quality, file size increment, computational complexity, and outperforms the state-of-the-arts in terms of the above metrics. © 1999-2012 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Multi-Fault Diagnosis, Quantitative Analysis and Warning Strategy for Lithium-ion Battery System: When LSTM Meets the Fuzzy Logic Theory

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Chen, Hui Tian, Engang Wang, Licheng Zheng, Yuejiu University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Shanghai University of Electric Power College of Automation Engineering Shanghai200090 China University of Shanghai for Science and Technology College of Mechanical Engineering Shanghai200093 China

This paper is concerned with the multi-level secure warning problem for lithium-ion battery systems subject to multi-fault scenarios. First, the long short-term memory (LSTM) network is employed to design a series of cell voltage estimators. In comparison with the estimation of the cell voltage and its measurement, the estimation residual is constructed in terms of the Euclidean distance, which plays an essential index for the multi-fault detection issue. Furthermore, in combination of the voltage envelope relationship, a specific type of the faults is subsequently identified. Then, for the subsequent fault warning purpose, a novel fault quantitative analysis method is proposed to further determine not only the fault amplitude but also its duration. In addition, on the basis of specific characteristics of the fault such as the type, count, duration and the amplitude, a fuzzy-logic-based multi-level secure warning strategy is put forward. Finally, the effectiveness of the developed multi-level fault warning approach is substantiated through a comprehensive experimental validation. © 2015 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning for Enhanced Detection in Oral Cancer Screening

Multimodal Learning for Enhanced Detection in Oral Cancer Sc...

引用

IEEE International Symposium on Biomedical Imaging

作者： Jiayi Zhang Yuchen Tian Bofan Song Eung-Joo Lee School of Arts and Sciences Tufts University Boston USA College of Optical Science University of Arizona Tucson USA Department of Electrical and Computer Engineering University of Arizona Tucson USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multimodal deep learning integrates diverse data types to enhance model performance by capturing complex interactions between different modalities. Traditional models Fare limited to single data types, whereas multimodal approaches use fusion strategies-early, late, and hybrid-to combine information from different sources effectively. In this study, we introduce a multimodal learning framework for oral cancer detection. This framework integrates images from various imaging systems, specifically white light, and fluoroscopy, along with a tabular dataset containing patient information. Leveraging the CLIP model and deep neural network classification models, such as EfficientNet, DenseNet, and ResNet, we conducted a comprehensive analysis and comparison using various performance metrics. Our approach demonstrates the potential for improved diagnostic accuracy through enhanced feature extraction from multimodal sources.

关键词： Deep learning Analytical models Accuracy Biological system modeling Artificial neural networks Feature extraction Cancer detection Data models Cancer Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving Image Inpainting Using Markov Random Field Modeling

引用

IEEE Transactions on Multimedia 2025年

作者： Kong, Ping Li, An Guo, Daidou Zhou, Liang Qin, Chuan Zhang, Xinpeng Jiading District Central Hospital Affiliated Shanghai University of Medicine and Health Sciences Shanghai201800 China University of Shanghai for Science and Technology School of Health Science and Engineering Shanghai200093 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Fudan University School of Computer Science Shanghai200433 China

Cloud services have attracted extensive attention due to low cost, agility and mobility. However, when processing data on cloud servers, users may worry about semi-honest third parties stealing private information from them, hence, data encryption is applied for privacy protection. Inpainting is a technique that reconstructs certain undesirable regions in an image through an imperceptible manner, which can be accomplished by searching for well-matching candidate patches and copying them to to-be-inpainted locations. However, when the image is encrypted, the matched candidate patch searching is a challenging dilemma. Therefore, tackling these data-privacy issues for image inpainting over a cloud infrastructure, we propose an image inpainting scheme using Markov random field (MRF) modeling in encrypted domain. In this scheme, the sender encrypts the to-be-inapinted image by using a homomorphic cryptosystem that supports homomorphic ciphertext comparison. Then, the cloud realizes the MRF-based inpainting for encrypted images through some specific homomorphic operations. In addition, secure context descriptors are utilized to improve the inpainting of textures and structures. Finally, the receiver obtains the inpainted result through image decryption. The proposed scheme is proved to be secure through various cryptographic attacks. Qualitative and quantitative results demonstrate our scheme achieves better inpainted results in structure compared with state-of-the-art schemes in encrypted domain. © 1999-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Quasiphase transition of a single-file water chain influenced by atomic charges in a water model using orientational-biased replica exchange Monte Carlo simulations

引用

Physical Review E 2025年第1期111卷 015419-015419页

作者： Liang Zhao Junqing Ni Zhi Zhu Yusong Tu Chunlei Wang College of Physical Science and Technology and Microelectronics Industry Research Institute Yangzhou University Jiangsu 225009 China School of Optical-Electrical Computer Engineering University of Shanghai for Science and Technology Shanghai 200093 China College of Sciences Shanghai University Shanghai 200444 China

The recently observed temperature-dependent quasiphase transition of the single-file water chain confined within a carbon nanotube in experiments has been validated by the simple lattice theory and molecular dynamics simulations. It has been pointed out that the atomic charges in water models are important, yet how the values will affect the structural details and thermodynamic properties of the quasiphase transition has not been fully revealed. In this work we perform orientational-biased replica exchange Monte Carlo simulations in the canonical ensemble to explore the effect of atomic charges in the SPC/E water model on the quasiphase transition of a single-file water chain. Based on the atomic charge values reported in literature, three distinct quasiphases are reproduced, comprising a fully hydrogen-bonded water chain at lower temperatures, a more ordered dipolar orientation along the tube axis at intermediate temperatures, and a completely disordered structure at higher temperatures. Then by increasing the atomic charge values, we find that the fragmentation of the entire water chain into shorter water segments, the orientational ordering of water dipoles along the tube axis, and the transition towards complete disorder are all inhibited. Consequently, the transition temperatures between three quasiphases have been shifted to higher temperatures. The thermodynamic analysis demonstrates that the increased atomic charge values enhance the hydrogen bonding between neighboring water molecules and also the electrostatic attraction within the water chain, leading to a longer water dipole correlation length even at higher temperatures. These findings highlight the vital role of atomic charges in water models and also the electrostatic interaction in regulating the orientational ordering of water molecules under nanoconfinement.

关键词： Hydrogen bonds

来源：评论

学校读者我要写书评

暂无评论

Industrial Metaverse: Enabling Technologies, Open Problems, and Future Trends

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Zhang, Shiying Li, Jun Shi, Long Ding, Ming Nguyen, Dinh C. Chen, Wen Han, Zhu Nanjing University of Science and Technology School of Electronic and Optical Engineering Nanjing210094 China Southeast University School of Information Science and Engineering Nanjing210096 China CSIRO Data61 EveleighNSW Australia University of Alabama Department of Electrical and Computer Engineering Huntsville United States Shanghai Jiao Tong University Department of Electronic Engineering Shanghai200240 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

As an emerging technology that enables seamless integration between the physical and virtual worlds, the Metaverse has great potential to be deployed in the industrial production field with the development of extended reality (XR) and next-generation communication networks. The Industrial Metaverse is used for product design, production operations, quality inspection, and testing. However, there is limited understanding of the enabling technologies associated with it, including the specific industrial scenarios targeted by each technology and the potential migration of technologies from other domains to the industrial sector. This paper provides a comprehensive survey of the latest literature on the Industrial Metaverse. We first analyze its advantages for industrial production, then review key enabling technologies such as blockchain (BC), privacy-preserving computing (PPC), digital twin (DT), fifth/sixth generation mobile communication technology (5G/6G), XR, and artificial intelligence (AI), and explore how these technologies support different aspects of industrial production. We also present major challenges in the Industrial Metaverse, including privacy and security concerns, resource limitations, and interoperability constraints, along with existing solutions. Finally, we outline several open issues and future research directions. © 1998-2012 IEEE.

关键词： artificial intelligence blockchain digital twin extended reality fifth/sixth generation mobile communication technology industrial Metaverse privacy-preserving computing

来源：评论

学校读者我要写书评

暂无评论

In-situ dynamic spatial reconfiguration of nanoplasmonics using photothermal-shock tweezers

arXiv

引用

arXiv 2025年

作者： Zhu, Runlin Gu, Zhaoqi Shen, Tianci Liu, Yifei Shi, Zhangxing Linghu, Shuangyi Gu, Fuxing Laboratory of Integrated Opto-Mechanics and Electronics School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Physics Guizhou University Guiyang550025 China

Dynamic reconfiguration is crucial for nanoplasmonic structures to achieve diversified functions and optimize performances;however, the dynamic reconfiguration of spatial arrangements remains a formidable technological challenge. Here, we showcase in-situ dynamic spatial reconfiguration of plasmonic nanowire devices and circuits on dry solid substrates, by harnessing a photothermal-shock tweezers platform. Owing to its versatility, nanoscale precision, real-time operation, and large external output force, the multimodal platform enables dexterous fine-tuning of positions, overlap lengths, and coupling distances and orientations of discrete components in situ. Spatial position-dependent optical properties that have not been reported before or are challenging to achieve through traditional micro/nanomanipulation are easily tuned and observed, such as the intensity evolution of axial photon-plasmon coupling from near field to far field, and the resonant mode evolution of photonic cavity-plasmonic cavity coupling from weak to strong. We also employ the nanorobotic probe-based operation mode to optimize the side-mode suppression ratios of single-mode lasers and the intensity splitting ratios of 3-dB couplers. Our results are general and applicable to materials of almost any size, structure, and material type, as well as other narrow or curved micro/nano-waveguide surfaces, which opens new avenues for reconfigurable nanoplasmonic structures with dynamically tunable spatial features. Copyright © 2025, The Authors. All rights reserved.

关键词： Nanowires

来源：评论

学校读者我要写书评

暂无评论

Shaping terahertz harmonic frequency combs with frequency-dependent external reflectors

引用

Physical Review A 2025年第4期111卷 043522-043522页

作者： Carlo Silvestri Xiaoqiong Qi Thomas Taimre Aleksandar D. Rakić Institute of Photonics and Optical Science (IPOS) School of Physics University of Sydney Sydney New South Wales 2006 Australia School of Electrical Engineering and Computer Science The University of Queensland Brisbane QLD 4072 Australia School of Mathematics and Physics The University of Queensland Brisbane QLD 4072 Australia

We present a method for engineering harmonic frequency combs (HFCs) in the terahertz spectral region. This approach involves interfacing a quantum cascade laser (QCL) with an external reflector featuring frequency-dependent reflectivity. A notable advantage of this method over existing ones is its dual functionality in shaping HFCs, allowing for control over both the frequency offset and comb spacing based on the external reflectivity profile. Moreover, the resulting HFCs manifest as sequences of short pulses in the time domain. Consequently, our method enables the generation of ultrashort picosecond pulses passively, providing a distinct alternative to conventional pulse generation systems reliant on active bias current modulation, which struggle with modulation frequencies significantly higher than the first beat note. This offers intriguing prospects for utilizing HFCs in pump and probe spectroscopy, a field already recognized in the literature as one of the most compelling applications of these states. Furthermore, we demonstrate that these HFCs can be triggered from an initial condition of free-running unlocked dynamics, eliminating the need for assuming free-running comb emission. Thus, the utilization of an external, frequency-dependent reflector is capable of enhancing the coherence of the QCL emission.

关键词： Quantum cascade lasers

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：