检索结果-内蒙古大学图书馆

18th International Conference on Nano/Micro Engineered and Molecular Systems, NEMS 2023

作者： Shi, Qiongfeng Sun, Zhongda Le, Xianhao Xie, Jin Lee, Chengkuo Southeast University Joint International Research Laboratory of Information Display and Visualization School of Electronic Science and Engineering Nanjing China National University of Singapore Department of Electrical and Computer Engineering Singapore Singapore Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou China

ISBN: (纸本)9798350333480

Here we report an intelligent soft robotic gripper enabled by the integration of an ultrasonic remote sensor and triboelectric sensors. Due to the noncontact distance sensing ability, the ultrasonic sensor is used to find the object's visual information including position and height by lateral scanning. The information is then used for adjusting the robotic gripper to an appropriate grasp location, after which grasp operation is performed to obtain the object's tactile information through triboelectric bending and tactile sensors. To efficiently analyze the multimodal information, a deep-learning neural network based on feature-level data fusion is constructed, which is able to achieve a high accuracy of 99.3% in classifying 14 objects, enabling the intelligent soft robotic gripper for various smart applications. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks based Muti-Label Deep Cross-Modal Hashing 13

Graph Convolutional Networks based Muti-Label Deep Cross-Mod...

引用

13th International Conference on information Science and Technology, ICIST 2023

作者： Peng, Yi Zhang, Nian Jiang, Xin Xiong, Jiang School of Electronic and Information Engineering Chongqing Three Gorges University Chongqing40044 China Department of Electrical and Computer Engineering University of the District of Columbia WashingtonDC20008 United States Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Chongqing40044 China College of Mathematics and Statistics Chongqing Three Gorges University Chongqing40044 China

ISBN: (纸本)9798350313925

Recently, multi-label deep cross-modal hashing (MDCH), which incorporates deep neural networks, hashing and multi-label learning for cross-modal retrieval tasks, has achieved excellent cross-modal retrieval results and thus became a highly popular area of research. Nevertheless, many existing MDCH methods concentrate on extracting information from multi-modal data, while neglecting the abundant semantic information in multiple labels. Few MDCH methods incorporate multi-label information, but they often treat labels as independent entities, ignoring the relationships between categories, which hinders the establishment of semantic connections among multi-modal data. In order to tackle the aforementioned challenges, we propose a graph convolutional networks based multi-label deep cross-modal hashing method (GMCH) in this paper. GMCH leverages two deep neural networks to generate hash representations from the original image-text pairs, during this process, a graph convolutional network is introduced to capture the category correlations of multi-labels and supervise the training of hash mapping. Experimental results on two commonly employed datasets validate the efficacy of the proposed GMCH method. You can find the code for our proposed GCMH at https://***/licher12/***. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Real-Time Tunable Gas Sensing Platform Based on SnO_(2) Nanoparticles Activated by Blue Micro-Light-Emitting Diodes

引用

Nano-Micro Letters 2024年第12期16卷 103-119页

作者： Gi Baek Nam Jung-El Ryu Tae Hoon Eom Seung Ju Kim Jun Min Suh Seungmin Lee Sungkyun Choi Cheon Woo Moon Seon Ju Park Soo Min Lee Byungsoo Kim Sung Hyuk Park Jin Wook Yang Sangjin Min Sohyeon Park Sung Hwan Cho Hyuk Jin Kim Sang Eon Jun Tae Hyung Lee Yeong Jae Kim Jae Young Kim Young Joon Hong Jong-In Shim Hyung-Gi Byun Yongjo Park Inkyu Park Sang-Wan Ryu Ho Won Jang Department of Materials Science and Engineering Seoul National UniversitySeoul 08826Republic of Korea Research Laboratory of Electronics Department of Mechanical EngineeringMassachusetts Institute of TechnologyCambridgeMA 02139USA Ming Hsieh Department of Electrical and Computer Engineering University of Southern CaliforniaLos AngelesCA 90089USA Department of Display Materials Engineering Soonchunhyang UniversityAsan 31538Republic of Korea Department of Photonics and Nanoelectronics BK21 FOUR ERICA-ACE CenterHanyang University ERICAAnsan 15588Republic of Korea Department of Nanotechnology and Advanced Materials Engineering Sejong UniversitySeoul 05006Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok 25913Republic of Korea Advance Institute of Convergence Technology Seoul National UniversitySuwon 16229Republic of Korea Department of Mechanical Engineering Korea Advanced Institute of Science and TechnologyDaejeon 34141Republic of Korea Department of Physics Chonnam National UniversityGwangju 500-757Republic of Korea

Micro-light-emitting diodes(μLEDs)have gained significant interest as an activation source for gas sensors owing to their advantages,including room temperature operation and low power ***,despite these benefits,challenges still exist such as a limited range of detectable gases and slow *** this study,we present a blueμLED-integrated light-activated gas sensor array based on SnO_(2)nanoparticles(NPs)that exhibit excellent sensitivity,tunable selectivity,and rapid detection with micro-watt level power *** optimal power forμLED is observed at the highest gas response,supported by finite-difference time-domain ***,we first report the visible light-activated selective detection of reducing gases using noble metal-decorated SnO_(2)*** noble metals induce catalytic interaction with reducing gases,clearly distinguishing NH3,H2,and ***-time gas monitoring based on a fully hardwareimplemented light-activated sensing array was demonstrated,opening up new avenues for advancements in light-activated electronic nose technologies.

关键词： Micro-LED Gas sensor array Low power consumption Metal decoration Real-time detection

来源：评论

学校读者我要写书评

暂无评论

Optical scanning approach to image processing and holography

Optical scanning approach to image processing and holography

引用

Digital Optical Technologies 2023

作者： Poon, Ting-Chung Zhang, Yaping Yunnan Provincial Key Laboratory of Modern Information Optics Kunming University of Science and Technology Yunnan Kunming650500 China Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States

Optical scanning approach to image processing has advantages over frequency-plane architecture in terms of accuracy and flexibility. We will review an optical scanning approach to image processing that includes the ca... 详细信息

ISBN: (数字)9781510664586

ISBN: (纸本)9781510664579

关键词： Holography

来源：评论

学校读者我要写书评

暂无评论

A New Partial Task Offloading Method in a Cooperation Mode under Multi-Constraints for Multi-UE

引用

computers, Materials & Continua 2023年第9期76卷 2879-2900页

作者： Shengyao Sun Ying Du Jiajun Chen Xuan Zhang Jiwei Zhang Yiyi Xu School of Information Science and Technology Zhengzhou Normal UniversityZhengzhou450044China Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifeng475004China School of Geography and Tourism Zhengzhou Normal UniversityZhengzhou450044China Science and Engineering College South China University of TechnologyGuangzhou510641China Department of Electrical and Electronic Engineering Luohe Vocational Technology CollegeLuohe462002China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing100876China Cardiff School of Engineering Cardiff UniversityCardiffCF103XQ 15UK

In Multi-access Edge Computing(MEC),to deal with multiple user equipment(UE)’s task offloading problem of parallel relationships under the multi-constraints,this paper proposes a cooperation partial task offloading method(named CPMM),aiming to reduce UE’s energy and computation consumption,while meeting the task completion delay as much as *** first studies the task offloading of single-UE and then considers the task offloading ofmulti-UE based on single-UE task *** the critical path algorithmto divide the modules into key and non-key *** to some constraints of UE-self when offloading tasks,it gives priority to non-key modules for offloading and uses the evaluation decision method to select some appropriate key modules for *** on fully considering the competition between multiple UEs for communication resources and MEC service resources,CPMM uses the weighted queuing method to alleviate the competition for communication resources and uses the branch decision algorithm to determine the location of module offloading by BS according to the MEC servers’*** achieves its goal by selecting reasonable modules to offload and using the cooperation ofUE,MEC,andCloudCenter to determine the execution location of *** experiments demonstrate that CPMM obtains superior performances in task computation consumption reducing around 6%on average,task completion delay reducing around 5%on average,and better task execution success rate than other similar methods.

关键词： MEC partial task offloading parallel dependencies completion delay

来源：评论

学校读者我要写书评

暂无评论

RDVC: Efficient Deep Video Compression with Regulable Rate and Complexity Optimization

引用

IEEE Transactions on Multimedia 2025年

作者： Wei, Xiaojie Lin, Jielian Xu, Jiawei Gao, Wei Zhao, Tiesong Putian University School of Mechanical Electrical & Information Engineering PutianFujian China Shenzhen Graduate School Peking University School of Electronic and Computer Engineering Shenzhen518055 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou350108 China Tsinghua University Department of Electronic Engineering Beijing100084 China

Deep video coding has paved a way to break through the performance bottleneck of reigning hybrid video coding. However, unlike hybrid video codecs, existing deep video codecs cannot offer both flexible rates and regulable complexities within one single codec, which limits their applications. In this paper, we propose a Regulable Deep Video Codec (RDVC) to address the above issue. First, we propose an Adaptive Feature Compression (AFC) network that generates variable rates while ensuring Rate-Distortion (RD) performance. The network introduces a two-stage coarse-to-fine rate adjustment that can be controlled by a user-specified rate level. Second, we propose a Spatio-Temporal Feature Propagation (STFP) mechanism to provide high-quality reference information for AFC process. Third, we also utilize slimmable convolutional components in our framework to adjust decoding complexity constrained by user configuration. Experimental results demonstrate that RDVC can adjust the codec structure flexibly according to different user configurations while maintaining advanced performance. On average, it reduces the bit-per-pixel (bpp) by 9.35%/58.12% while maintaining the same PSNR/MS-SSIM as the reference software VTM-13.2. Sourcecode is available at: https://***/WXJ0001/RDVC. © 2025 IEEE.

关键词： Signal distortion

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Secure Crowdsourcing in Wireless IoT

引用

Journal of Communications and information Networks 2022年第1期7卷 23-36页

作者： Daquan Feng Long Zhang Shengli Zhang Qihui Wu Xianggen Xia Guangdong Province Engineering Laboratory for Digital Creative Technology Shenzhen UniversityShenzhen 518060China National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of ChinaChengdu 611731China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China Department of Electrical and Computer Engineering University of DelawareNewarkDE 19716USA

With the explosive growth of interconnected smart devices and sensors,the Internet has been entering the Internet of things(IoT)era and revolutionizing many aspects of our daily life. Meanwhile, crowdsourcing has been considered as a promising technology to realize collaborative intelligence. Therefore, more and more IoT-based crowdsourcing applications are emerged to take advantages of the widely distributed IoT devices to sense, collect, and analyze data with the aim to solve complex and nontrivial tasks. However,there exist many technical challenges to be addressed in the IoT-based crowdsourcing, such as security, privacy, and incentive provision. In this paper, we propose a blockchain-based architecture as an integrated solution to realize the secure and trustworthy crowdsourcing in wireless IoT. We first overview the challenges in the traditional crowdsourcing system. Then, we briefly introduce the background of the blockchain and smart contract, and propose a blockchain-based crowdsourcing architecture. In particular, we elaborate the utilization of smart contract on the specific phases of crowdsourcing. By deploying the smart contract instance, we confirm the proposed blockchain-based architecture is feasible.

关键词： crowdsourcing blockchain wireless IoT security privacy incentive

来源：评论

学校读者我要写书评

暂无评论

Dielectric Resonator Antenna Array With Extended Beam-Scanning Range Using Dielectric Superstrate

Dielectric Resonator Antenna Array With Extended Beam-Scanni...

引用

2023 IEEE Conference on Antenna Measurements and Applications, CAMA 2023

作者： Su, Zhi-Li Xiao, Fei Li, MingChao Lu, Kai Leung, Kwok Wa City University of Hong Kong State Key Laboratory of Terahertz and Millimeter Waves Department of Electrical Engineering Hong Kong CityU Shenzhen Research Institute Information and Communication Technology Centre Shenzhen China Limited Guangzhou China Sun Yat-sen University School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou China

ISBN: (纸本)9798350323047

An E-plane cylindrical dielectric resonator antenna (DRA) array with a dielectric superstrate is investigated for wide-angle scanning applications. Each slot-coupled DRA element operates at its fundamental HEM11δ mode. The dielectric superstrate is loaded above the DRA array. By adjusting its dimension and position properly, the beamwidth of the center active element pattern is significantly broadened. Meanwhile, the mutual coupling effect among various elements is effectively reduced. Both the wide-beam element pattern and reduced mutual coupling level contribute to the improvement of the array beam-steering capability. Finally, our proposed E-plane DRA array has a wide range of ±80° with a scan loss of 3 dB. © 2023 IEEE.

关键词： Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Oracle Character Prototype-Guided Cyclic Disentanglement for Oracle Bone Inscriptions Detection 4th

Oracle Character Prototype-Guided Cyclic Disentanglement for...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2024

作者： Li, Bang Zhang, Jingping Yu, Nana Zhang, Zihao Liu, Yongge Han, Yahong School of Computer and Information Engineering Anyang Normal University Anyang455000 China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education Anyang455000 China Digital Media Art Department Shanghai Theatre Academy Shanghai200040 China Key Laboratory of Integrated Innovation of Digital Performing Arts Ministry of Culture and Tourism Shanghai200040 China College of Intelligence and Computing Tianjin University Tianjin300072 China

ISBN: (纸本)9789819787043

Oracle Bone Inscriptions (OBI), as the oldest form of Chinese writing, bears the precious heritage of ancient Chinese civilization. Deciphering OBI has been a monumental challenge in archaeology and philology. However, the preservation method of OBI through rubbings faces significant challenges due to severe noise interference, adversely affecting the accuracy of OBI detection. Additionally, existing traditional object detection algorithms inadequately consider the unique characteristics of OBI, making it difficult to effectively identify Oracle characters on OBI rubbings. To address these challenges, this paper proposes a novel approach to OBI detection, Oracle Character Prototype-guided cyclic disentanglement for OBI detection. These features are amalgamated into distinct character structure prototypes by capturing shared character structure features among different Oracle characters. This approach highlights the distinctive forms of Oracle characters, enhancing feature clarity and recognition. The Oracle Character Prototypes enable the model to learn common features across different character forms, improving its adaptability to various Oracle character structures and enhancing its capability to handle complexity. Moreover, to mitigate the impact of noise on detection, we introduce a cyclic disentanglement method for Oracle Bone Inscriptions. This process, utilizing the Oracle Character Prototypes and contrastive loss as supervisory signals, cyclically decouples Oracle features, isolating information rich in character structure features. This effectively mitigates the influence of noise on OBI detection. Comprehensive evaluations were conducted, comparing our method with state-of-the-art object detection algorithms, validating its effectiveness both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A TMA-Seq2seq Network for Multi-Factor Time Series Sea Surface Temperature Prediction

引用

computers, Materials & Continua 2022年第10期73卷 51-67页

作者： Qi He Wenlong Li Zengzhou Hao Guohua Liu Dongmei Huang Wei Song Huifang Xu Fayez Alqahtani Jeong-Uk Kim Department of Information Technology Shanghai Ocean UniversityShanghai201306China State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of OceanographyMinistry of Natural ResourcesHangzhou310012China College of Computer Dong Hua UniversityShanghai200051China College of Information Technology Shanghai Jian Qiao UniversityShanghai201306China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh 12372Saudi Arabia Department of Electrical Engineering Sangmyung UniversitySouth KoreaKorea

Sea surface temperature (SST) is closely related to global climatechange, ocean ecosystem, and ocean disaster. Accurate prediction of SST isan urgent and challenging task. With a vast amount of ocean monitoring dataare continually collected, data-driven methods for SST time-series predictionshow promising results. However, they are limited by neglecting complexinteractions between SST and other ocean environmental factors, such as airtemperature and wind speed. This paper uses multi-factor time series SSTdata to propose a sequence-to-sequence network with two-module attention(TMA-Seq2seq) for long-term time series SST prediction. Specifically, TMASeq2seq is an LSTM-based encoder-decoder architecture facilitated by factorand temporal-attention modules and the input of multi-factor time series. Ittakes six-factor time series as the input, namely air temperature, air pressure,wind speed, wind direction, SST, and SST anomaly (SSTA). A factor attentionmodule is first designed to adaptively learn the effect of different factors onSST, followed by an encoder to extract factor-attention weighted features asfeature representations. And then, a temporal attention module is designedto adaptively select the hidden states of the encoder across all time steps tolearn more robust temporal relationships. The decoder follows the temporalattention module to decode the feature vector concatenated from the weightedfeatures and original input feature. Finally, we use a fully-connect layer tomap the feature into prediction results. With the two attention modules, ourmodel effectively improves the prediction accuracy of SST since it can notonly extract relevant factor features but also boost the long-term *** experiments on the datasets of China Coastal Sites (CCS) demonstrate that our proposed model outperforms other methods, reaching 98.29%in prediction accuracy (PACC) and 0.34 in root mean square error (RMSE).Moreover, SST prediction experiments in China’s East, South,

关键词： Sea surface temperature multi-factor attention long short-term memory

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：