检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Technologies, ICIT 2023

作者： Kyaw, Nwe Ni Mitra, Pabitra Sinha, G.R. Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal721302 India Indian Knowledge System Lab International Institute of Information Technology Bangalore Karnataka Bengaluru560100 India

ISBN: (纸本)9789819738588

The proposed system for recognizing Myanmar sign language between individuals who are deaf. The aim of this study is to develop deep learning models for the purpose of accurately identifying dynamic hand gesture images depicting 14 classes of Myanmar words and numbers. The present system utilizes a new dataset comprising 7834 images for 14 classes obtained through Webcam. The objective of this study is to enhance the robustness of the new model. Next, we proceed to evaluate the proposed model by comparing them to those of existing convolutional neural network models. These models are generally recognized as effective deep-learning approaches for recognition tasks. The proposed model exhibits a performance level of 96% for both validation and testing accuracies. Furthermore, the experimental finding demonstrates that the model, convolutional layers, achieved an accuracy of 100% in recognizing Myanmar Sign Language (MSL). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Swarm-Based Dynamic Coverage of Multi-ASV systems in the Presence of Measurement Noises

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 7237-7250页

作者： Liu, Lu Jiao, Shijian Han, Bing Li, Tieshan Peng, Zhouhua Dalian Maritime University School of Marine Electrical Engineering Dalian116026 China Dalian Key Laboratory of Swarm Control and Electrical Technology for Intelligent Ships Dalian116026 China State Key Laboratory of Maritime Technology and Safety Dalian116026 China Shanghai Ship and Shipping Research Institute National Engineering Research Center of Ship & Shipping Control System Shanghai200135 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China

This paper is concerned with the dynamic coverage of multiple autonomous surface vehicles (ASVs) in the presence of static and dynamic obstacles, limited communication distance, and measurement noises. A modular control method including planning, guidance, and control is proposed. At the planning level, a swarm-based dynamic coverage strategy is developed to achieve the coverage of a given domain. Both the collision avoidance and connectivity preservation issues are solved by using artificial potential fields. At the kinematic level, novel adaptive line-of-sight guidance laws are presented based on cascade extended state observers (CESOs), such that accurate guidance signals are given by compensating for time-varying sideslip angle and suppressing measurement noises. At the kinetic level, two CESOs are developed to estimate the internal model uncertainties and external environmental disturbance, and antidisturbance kinetic control laws are designed subsequently. The proposed CESOs overcome the noises sensitivity problem of classical observers, and thus facilitate the practical implementation under measurement noises. The input-to-state stability of the closed-loop system is confirmed by the Lyapunov theory and cascade stability theory. Simulation and hardware-in-the-loop experiment results are provided to demonstrate the effectiveness of the proposed swarm-based dynamic coverage method. © 1967-2012 IEEE.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation for Variable-SNR Signal Modulation Recognition 16

Unsupervised Domain Adaptation for Variable-SNR Signal Modul...

引用

16th International Conference on Signal Processing systems, ICSPS 2024

作者： Bai, Zixi Wang, Qing Yang, Kai Liang, Kun School of Electronic Information and Communications Huazhong University of Science and Technology China National Key Laboratory of Electromagnetic Energy Naval University of Engineering China

ISBN: (纸本)9781510689251

When the source domain and target domain differ in Signal-to-Noise Ratio (SNR), models trained on source data tend to perform poorly on target data. Given a labeled source dataset, unsupervised domain adaptation (UDA) aims to predict the labels of the target domain dataset by aligning the features of the source and target domains. Motivated by UDA, we propose a method that aligns the feature representations of the source and target domains to enable modulation classification under variable SNRs. Our experiments demonstrate that this approach results in a performance improvement of 3.9% to 15.39% compared to a model trained only on the source domain. © 2025 SPIE.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

Eco-friendly small molecule with polyhydroxyl ketone as buried interface chelator for enhanced carrier dynamics toward high-performance perovskite solar cells

引用

science China Materials 2025年第4期68卷 1249-1258页

作者： Rui Wu Bingxin Ding Shuping Xiao Wuchen Xiang Yiheng Gao Bobo Yuan Zhongli Qin Xiangbai Chen Pingli Qin Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of TechnologyWuhan 430205China School of Electronics and Information Engineering Hubei University of Science and TechnologyXianning 437100China School of Optoelectronic Information and Energy Engineering Wuhan Institute of TechnologyWuhan 430205China

Buried interface defects pose a significant challenge to achieving high efficiency and stability of n-i-p perovskite solar cells(PSCs).A multifunctional material is essential for passivating interface defects,suppressing non-radiative recombination,and facilitating rapid carrier transfer at these ***,a new multifunctional eco-friendly small molecule,D-fructose,was introduced into the interface as a modification layer,playing a significant role in passivating defects not only among SnO_(2) quantum dots(QDs),but also between perovskite and SnO_(2) *** coordination bonds of the C=O group with Pb^(2+)and Sn^(4+)/Sn^(2+),along with the hydrogen bonds of the-OH group with I^(-)in perovskite,contribute to this passivation ***,this multifunctional collaboration at the buried interface not only triggers uniform heterogeneous nucleation across the perovskite precursor film,leading to high-quality perovskite,but also effectively eliminates residual PbI2 at grain boundaries to suppress perovskite *** a more suitable energy level alignment between perovskite and SnO_(2) QDs can smooth the interface barrier,thereby facilitating the formation of an electron bridge for rapid electron extraction and ***,the D-fructose based PSC has achieved a champion efficiency of 24.91%with negligible J-V hysteresis,along with excellent stability.

关键词： D-fructose defect passivation buried interface device stability perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

Janus MXene film with gradient structure for highly efficient terahertz and infrared electromagnetic absorption

引用

Nano Research 2025年第1期18卷 434-442页

作者： Shaodian Yang Weiqiang Huang Zhiqiang Lin Zibo Chen Rongliang Yang Yi Jia Xuebin Liu Rui Wang Zhiping Zeng Yougen Hu Huanjun Chen Xuchun Gui11 State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information TechnologySun Yat-sen UniversityGuangzhou 510275China National Key Laboratory of Materials for Integrated Circuits Shenzhen Institute of Advanced Electronic MaterialsShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China China Academy of Aerospace Science and Innovation Beijing 100176China Guangdong Province Key Laboratory of Display Material and Technology Guangzhou 510275China School of Materials Science and Engineering Sun Yat-sen UniversityGuangzhou 510275China

Electromagnetic interference (EMI) shielding inhigh-frequency range, especially the rapidly growing terahertz(THz) frequency range, attracts increasing attention due tothe potential application of terahertz in 6G wirelesscommunication, and security inspection. However, traditionalconductive EMI films typically achieve high shieldingeffectiveness through strong reflection, which may causesecondary pollution to other devices. Here, a gradientstructure strategy was proposed to constructTi_(3)C_(2)Tx/hydroxypropyl methyl cellulose (HPMC) film, in whichthe content of Ti_(3)C_(2)Tx gradually increases along the thicknessdirection, resulting in different conductivity of the two surfaces(surface-M and surface-H) for the film. The obtained gradientfilmexhibits an EMI shielding efficiency of over 48.5 dB in theTHz range (0.2-1.6 THz) at a thickness of 40 μm. Especially,as the THz waves incident from the surface-H to the film, the absorption effectiveness reaches 48.2 dB (average absorbedpower loss up to 91.4%), and the reflection effectiveness is only 0.3 dB. In additions, the gradient-film also demonstrates ahigh absorption rate of 95.5% in the infrared band (2.5-16.7 μm). Moreover, the gradient-film exhibits an excellent tensilestress and Young’s modulus value of 173.1 MPa and 2.8 GPa, respectively. Therefore, the gradient-film proposed in thiswork, with excellent electromagnetic absorption in both THz and infrared band, provides a promising candidate for the nextgenerationEMI shielding applications.

关键词： electromagnetic interference shielding Janus film terahertz MXene

来源：评论

学校读者我要写书评

暂无评论

Higher-order topology in twisted multilayer systems:A review

引用

Chinese Physics B 2025年第3期34卷 2-10页

作者： Chunbo Hua Dong-Hui Xu Key Laboratory of Artificial Micro-and Nanostructures of Ministry of Education and School of Physics and Technology Wuhan UniversityWuhan 430072China School of Electronic and Information Engineering Hubei University of Science and TechnologyXianning 437100China Department of Physics and Chongqing Key Laboratory for Strongly Coupled Physics Chongqing UniversityChongqing 400044China Center of Quantum Materials and Devices Chongqing UniversityChongqing 400044China

In recent years,there has been a surge of interest in higher-order topological phases(HOTPs)across various disciplines within the field of *** unique phases are characterized by their ability to harbor topological protected boundary states at lower-dimensional boundaries,a distinguishing feature that sets them apart from conventional topological phases and is attributed to the higher-order bulk-boundary ***-dimensional(2D)twisted systems offer an optimal platform for investigating HOTPs,owing to their strong controllability and experimental ***,we provide a comprehensive overview of the latest research advancements on HOTPs in 2D twisted multilayer *** will mainly review the HOTPs in electronic,magnonic,acoustic,photonic and mechanical twisted systems,and finally provide a perspective of this topic.

关键词： higher-order topology twisted multilayer systems van der Waals materials corner states

来源：评论

学校读者我要写书评

暂无评论

Fast resistivity imaging of transient electromagnetic using an extreme learning machine

引用

Soft Computing 2025年第2期29卷 1121-1131页

作者： Li, Ruiyou Zhang, Yong Li, Guang Li, Ruiheng Hu, Jia Li, Min School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics NanChang330013 China School of Geophysics and Measurement Control Technology East China University of Technology NanChang330013 China School of Information Engineering Hubei University of Economics Wuhan430205 China The State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing University Chongqing400044 China

The transient electromagnetic method (TEM) is widely used in geophysical exploration. In TEM data interpretation, nonlinear inversion plays an important role. However, traditional TEM nonlinear inversion adopts the OCCAM imaging method, which merely presents the approximate shape of the stratum model, with poor inversion accuracy and much iteration time. To solve the above problems, a novel nonlinear inversion approach based on extreme learning machine (ELM) is proposed in this paper. The ELM is required to establish the input–output mapping relationship of the inversion network only once through the analytical method, which is different from the traditional neural network method that demands iterative gradient learning and is prone to fall into the local optimum. Moreover, the ELM inversion network by randomly assigning the hidden layer parameters is capable of mapping the observed TEM data and quickly producing resistivity images, which avoids time-consuming iteration and inversion calculations. The presented approach is applied to both synthetic and field examples. The results show that compared with the traditional nonlinear inversion algorithms (BP and OCCAM), the proposed method achieves better inversion accuracy and significantly reduces the calculation time, which verifies the effectiveness of the ELM algorithm for TEM data interpretation. Additionally, the research provides a new method and technology for TEM data inversion. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

UAV-Mounted Intelligent Reflecting Surface in Maritime Wireless Powered Communication Network

引用

China Communications 2025年第3期22卷 254-269页

作者： Liu Yuan Han Fengxia Zhao Shengjie School of Information Science and Electrical Engineering Shandong Jiaotong UniversityJinan 250357China College of Electronic and Information Engineering Tongji UniversityShanghai 201804China School of Software Engineering Tongji UniversityShanghai 201804China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of EducationShanghai 200003China Key Laboratory of Embedded System and Service Computing Tongji University Shanghai 201804China

Intelligent reflecting surface(IRS)assisted with the wireless powered communication network(WPCN)can enhance the desired signal energy and carry out the power-sustaining problem in ocean monitoring *** this paper,we investigate a reliable communication structure where multiple buoys transmit data to a base station(BS)with the help of the unmanned aerial vehicle(UAV)-mounted IRS and harvest energy from the base station *** organically combine WPCN with maritime data collection scenario,a scheduling protocol that employs the time division multiple access(TDMA)is proposed to serve multiple buoys for uplink data ***,we compare the full-duplex(FD)and half-duplex(HD)mechanisms in the maritime data collection system to illustrate different performances under these two *** maximize the fair energy efficiency under the energy harvesting constraints,a joint optimization problem on user association,BS transmit power,UAV’s trajectory and IRS’s phase shift is *** solve the non-convex problem,the original problem is decoupled into several subproblems,and successive convex optimization and block coordinate descent(BCD)methods are employed obtain the near-optimal solutions *** results demonstrate that the UAV-mounted IRS can significantly improve energy efficiency in our considered system.

关键词： full-duplex IRS joint optimization TDMA UAV WPCN

来源：评论

学校读者我要写书评

暂无评论

On-chip deep residual photonic neural networks using optical-electrical shortcut connections

引用

Optics Letters 2025年第3期50卷 860-863页

作者： Wang, Kaiyuan Tang, Zihao Li, Yunlong Wu, Yantao Zheng, Shuang Zhang, Minming School of Optical and Electronic Information Huazhong University of Science and Technology Hubei Wuhan430074 China National Engineering Research Center for Next Generation Internet Access System Hubei Wuhan430074 China Optics Valley Laboratory Hubei Wuhan430074 China Hubei Optical Fundamental Research Center Hubei Wuhan430074 China

On-chip photonic neural networks (PNNs) have recently emerged as an attractive hardware accelerator for deep learning applications. However, deep PNNs with higher inference complexity are harder to train due to gradient vanishing and exploding problems. In this work, we propose an on-chip deep residual photonic neural network architecture (Res-PNN), which enables the training of deeper PNNs by using optical-electrical shortcut connections. The opticalelectrical shortcut connection is designed using a power splitter, a wavelength demultiplexer, and photodetectors to directly connect the input and the output across optical weight layers. This optical-electrical shortcut connection alleviates the gradient vanishing and exploding problems by providing a direct path for gradient backpropagation, ensuring stable training of deeper PNNs. The proposed Res-PNN achieves classification accuracies of 88.4% on the CIFAR-10 dataset and 80.3% on the CIFAR-100 dataset. Compared to fully connected PNNs, Res-PNN improves classification accuracy by 3.2% on the CIFAR-10 dataset and 11.3% on the CIFAR-100 dataset. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

DialectMoE: An End-to-End Multi-dialect Speech Recognition Model with Mixture-of-Experts 23rd

DialectMoE: An End-to-End Multi-dialect Speech Recognition M...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhou, Jie Gao, Shengxiang Yu, Zhengtao Dong, Ling Wang, Wenjun Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Yunnan Kunming650500 China

ISBN: (纸本)9789819783663

Dialect speech recognition has always been one of the challenges in Automatic Speech Recognition (ASR) systems. While lots of ASR systems perform well in Mandarin, their performance significantly drops when handling dialect speech. This is mainly due to the obvious differences between dialects and Mandarin in pronunciation and the data scarcity of dialect speech. In this paper, we propose DialectMoE, a Chinese multi-dialects speech recognition model based on Mixture-of-Experts (MoE) in a low-resource conditions. Specifically, DialectMoE assigns input sequences to a set of experts using a dynamic routing algorithm, with each expert potentially trained for a specific dialect. Subsequently, the outputs of these experts are combined to derive the final output. Due to the similarities among dialects, distinct experts may offer assistance in recognizing other dialects as well. Experimental results on the Datatang dialect public dataset show that, compared with the baseline model, DialectMoE reduces Character Error Rate (CER) for Sichuan, Yunnan, Hubei and Henan dialects by 23.6%, 32.6%, 39.2% and 35.09% respectively. The proposed DialectMoE model demonstrates outstanding performance in multi-dialects speech recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Dynamic routing algorithms

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：