检索结果-内蒙古大学图书馆

AMTrans:Auto-Correlation Multi-Head Attention Transformer for Infrared Spectral Deconvolution

清华大学学报自然科学版（英文版） 2025年第3期30卷 1329-1341页

作者： Lei Gao Liyuan Cui Shuwen Chen Lizhen Deng Xiaokang Wang Xiaohong Yan Hu Zhu College of Electronic and Optical Engineering & College of Flexible Electronics(Future Technology) Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China National Engineering Research Center of Communication and Network Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China School of Computer Science and Technology Hainan UniversityHaikou 570228China

Infrared spectroscopy analysis has found widespread applications in various fields due to advancements in technology and industry *** improve the quality and reliability of infrared spectroscopy signals,deconvolution is a crucial preprocessing *** by the transformer model,we propose an Auto-correlation Multi-head attention Transformer(AMTrans)for infrared spectrum sequence *** auto-correlation attention model improves the scaled dot-product attention in the *** utilizes attention mechanism for feature extraction and implements attention computation using the auto-correlation *** auto-correlation attention model is used to exploit the inherent sequence nature of spectral data and to effectively recovery spectra by capturing auto-correlation patterns in the *** proposed model is trained using supervised learning and demonstrates promising results in infrared spectroscopic *** comparing the experiments with other deconvolution techniques,the experimental results show that the method has excellent deconvolution performance and can effectively recover the texture details of the infrared spectrum.

关键词： spectroscopy spectral deconvolution transformer auto-correlation mechanism

来源：评论

学校读者我要写书评

暂无评论

DetSpace:Distributed Congestion Free Routing for Global Deterministic Network in Mega-Constellations

引用

China Communications 2024年第12期21卷 203-216页

作者： Li Jihao Li Hewu Lai Zeqi Wang Xiaomo Beijing National Research Center for Information Science and Technology(BNRist) Beijing 100084China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Institute of Network Science and Cyberspace Tsinghua UniversityBeijing 100084China Zhongguancun Laboratory Beijing 100095China China Academy of Electronics and Information Technology Beijing 100040China

Emerging long-range industrial IoT applications(e.g.,remote patient monitoring)have increasingly higher requirements for global deterministic *** many existing methods have built deterministic networks in small-scale networks through centralized computing and resource reservation,they cannot be applied on a global *** emerging mega-constellations enable new opportunities for realizing deterministic delay *** one constellation(e.g.,Starlink)might be managed by a single operator(e.g.,SpaceX),packets can be routed within deterministic number of ***,the path diversity brought by the highly symmetrical network structure in mega-constellations can help to construct a congestion free network by *** paper leverages these unique characteristics of mega-constellations to avoid the traditional network congestion caused by multiple inputs and single output,and to determine the routing hops,and thus realizing a global deterministic network(DETSPACE).The model based on the 2D Markov chain theoretically verifies the correctness of *** effectiveness of DETSPACE in different traffic load con-ditions is also verified by extensive simulations.

关键词： congestion free deterministic network mega-constellations path diversity

来源：评论

学校读者我要写书评

暂无评论

Sparse Reduced-dimension Clutter Suppression Method Based on Multi-domain Joint Processing 4

Sparse Reduced-dimension Clutter Suppression Method Based on...

引用

4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

作者： Wang, Qiang Min, Gang Xue, Bin Song, Dan Liu, Jianbin Zhang, Yani National University of Defense Technology Test Center Xi'an China National University of Defense Technology School of Information and Communication Wuhan China Xi'an Jiaotong University School of Computer Science and Technology Xi'an China Tsinghua University Laboratory of Flexible Electronics Technology Beijing China

ISBN: (纸本)9798350394375

To improve the heterogeneous clutter suppression performance of airborne radar, a fast sparse reduced-dimension method based on multi-domain joint processing is proposed in this paper. Firstly, spatial diversity is adopted among transmitting sub-apertures to realize reduced dimension of spatial domain. Secondly, multiple equivalent samples are obtained by matching reconstruction. Thirdly, the dimension of these samples is further reduced based on energy transform domain. Finally, the clutter is suppressed by joint sparse recovery, and simulations demonstrate the effectiveness of proposal. © 2024 IEEE.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

3D hierarchical porous Cr2O3 nanomaterials for high performance dimethyl disulfide gas sensor

引用

Ceramics International 2025年第16期51卷 22067-22074页

作者： Guo, Wen Deng, Zanhong Zhang, Ruofan Klamchuen, Annop Horprathum, Mati Wang, Shimao Fang, Xiaodong You, Libing Meng, Gang Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Photonic Devices and Materials Anhui Institute of Optics and Fine Mechanics And Key Lab of Photovoltaic and Energy Conservation Materials Chinese Academy of Sciences Hefei230031 China Advanced Laser Technology Laboratory of Anhui Province Hefei230037 China Wan Jiang Emerging Industry Technology Development Center Tongling244000 China National Nanotechnology Center National Science and Technology Development Agency Pathum Thani12120 Thailand Opto-Electrochemical Sensing Research Team Spectroscopic and Sensing Devices Research Group National Electronics and Computer Technology Center Pathum Thani12120 Thailand College of New Materials and New Energies Shenzhen Technology University Shenzhen518118 China Shenzhen Shengfang Technology Company Limited Shenzheng518116 China

Dimethyl disulfide (DMDS) is one of the malodorous gases mandatorily monitored by the government. Developing highly sensitive and selective DMDS sensors based on metal oxide semiconductor (MOS) is an urgent requirement and remains a challenge. In this study, 3D hierarchical mesoporous Cr2O3 nanoparticles were successfully synthesized by a time- and cost-efficient solution combustion synthesis method. The sensing performances of the as-synthesized mesoporous Cr2O3 nanoparticles have been thoroughly investigated. The sensor demonstrated a high response of 102 to 10 ppm DMDS at working temperature of 140 °C, along with satisfactory selectivity and long-term stability, indicating a promising future in DMDS detection. © 2025

关键词： Combustion synthesis

来源：评论

学校读者我要写书评

暂无评论

On the Stability of Random Access with Congestion Control 14th

On the Stability of Random Access with Congestion Control

引用

14th EAI International Conference on Wireless and Satellite Systems, WiSATS 2024

作者： Xu, Yu Cui, Chen Wang, Zhenyong Guo, Qing School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China Songjiang Laboratory Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9783031861956

The random access protocol is a critical technique widely used in various wireless networks. A significant challenge is analyzing the stability of the random access system when a large number of users transmit packets independently. Although the congestion control policy can enhance the stability of the system, there is currently a lack of quantitative analysis on the stability of random access with congestion control. In this paper, we analyze the random access system with congestion control and quantify its stability. Specifically, we consider a congestion control scheme to enhance the stability of the random access system and present the graphical analytical model. Based on this graphical model, we qualitatively discuss the behavioral variations of the system as it works and quantify its stability. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

Structural RC computer aided intelligent analysis and computational performance via experimental investigations

引用

Structural Engineering and Mechanics 2024年第3期90卷 253-261页

作者： Huang, Y.C. Lulios, TuMuli Chang, Chu-Ho Noor, M. Nasir Shao, Jen-Chung Chiu, Chien-Liang Lee, Tsair-Fwu Wang, Renata Information Technology Faculty Duy Tân University 254 Nguyen Van Linh Danang Viet Nam Princess Margaret Hospital Funafuti Island Private Mail Bag Tuvalu College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan College of Maritime National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Medical Physics and Informatics Laboratory of Electronics Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Information and Research Center of China 1/9 Road: 2 Block: D Section: 15 Dhaka1216 Bangladesh

This research explores a new finite element model for the free vibration analysis of bi-directional functionally graded (BDFG) beams. The model is based on an efficient higher-order shear deformation beam theory that incorporates a trigonometric warping function for both transverse shear deformation and stress to guarantee traction-free boundary conditions without the necessity of shear correction factors. The proposed two-node beam element has three degrees of freedom per node, and the inter-element continuity is retained using both C1 and C0 continuities for kinematics variables. In addition, the mechanical properties of the (BDFG) beam vary gradually and smoothly in both the in-plane and out-of-plane beam’s directions according to an exponential power-law distribution. The highly elevated performance of the developed model is shown by comparing it to conceptual frameworks and solution procedures. Detailed numerical investigations are also conducted to examine the impact of boundary conditions, the bi-directional gradient indices, and the slenderness ratio on the free vibration response of BDFG beams. The suggested finite element beam model is an excellent potential tool for the design and the mechanical behavior estimation of BDFG structures. © 2024 Techno-Press, Ltd.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Pre-Equalization Aided Grant-Free Massive Access in Massive MIMO System

引用

IEEE Transactions on Vehicular technology 2025年第6期74卷 9979-9984页

作者： Wang, Yueqing Mei, Yikun Gao, Zhen Wan, Ziwei Ning, Boyu Mi, De Muhaidat, Sami School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing100081 China Yangtze Delta Region Academy Jiaxing314019 China Beijing Institute of Technology Advanced Technology Research Institute Jinan250307 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Birmingham City University School of Computing and Digital Technology BirminghamB55JU United Kingdom Khalifa University KU 6 G Research Center Department of Computer and Information Engineering Abu Dhabi United Arab Emirates

The spatial diversity and multiplexing advantages of massive multi-input-multi-output (mMIMO) can significantly improve the capacity of massive non-orthogonal multiple access (NOMA) in machine type communications. However, state-of-the-art grant-free massive NOMA schemes for mMIMO systems require accurate estimation of random access channels to perform activity detection and the following coherent data demodulation, which suffers from excessive pilot overhead and access latency. To address this, we propose a pre-equalization aided grant-free massive access scheme for mMIMO systems, where an iterative detection scheme is conceived. Specifically, the base station (BS) firstly activates one of its antennas (i.e., beacon antenna) to broadcast a beacon signal, which facilitates the user equipment (UEs) to perform downlink channel estimation and pre-equalize the uplink random access signal with respect to the channels associated with the beacon antenna. During the uplink transmission stage, the BS detects UEs' activity and data by using the proposed iterative detection algorithm, which consists of three modules: coarse data detection (DD), data-aided channel estimation (CE), and fine DD. In the proposed algorithm, the joint activity and DD is firstly performed based on the signals received by the beacon antenna. Subsequently, the DD is further refined by iteratively performing data-aided CE module and fine DD module using signals received by all BS antennas. Our simulation results demonstrate that the proposed scheme outperforms state-of-the-art mMIMO-based grant-free massive NOMA schemes with the same access latency. © 1967-2012 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Matching Thai Profession Descriptions from Different Sources Using English as Interlingual Language

Matching Thai Profession Descriptions from Different Sources...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Vorapon Luantangsrisuk Rattapoom Kedtiwerasak Kanchana Saengthongpattana Taneth Ruangrajitpakorn Language and Semantic Technology Laboratory National Electronics and Computer Technology Center (NECTEC) Pathumthani Thailand

This paper proposes a method to improve text matching for occupation descriptions from different standards in Thailand. To solve ambiguity from technical compound words from standards, we apply machine translation, and similarity calculation for matching occupation and profession from sources that focused on different aspects. Thus, despite mentioning on same occupation, the descriptions from different standards share very little terms for matching the job across standards. By translating terms from Thai to English, we solve the issue of synonym technical terms varily used in different sources to improve similarity scores. Furthermore, tree structure of the standards is considered to assist on limiting search space. From experiments, the results of the baseline is very low, and the proposed method averagely exceed the result from the baseline for more than 6 percents for top-3 matching and 5 percents for top-5 matching in terms of accuracy. The use of both Thai and English translated job descriptions for matching using similar terms can noticeably increase a capability of matching jobs that cannot be found using only original Thai job description by adding more features of English-translated terms.

关键词： Technological innovation Limiting Machine translation Compounds Standards Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Physically Based Bidirectional Path Tacing Algorithm on the Tianhe-2 Supercomputer 25

Physically Based Bidirectional Path Tacing Algorithm on the ...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data Science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Wu, Yijia Zhang, Congpin Xu, Zhengwei Li, Ligang Chinese Academy of Sciences National Space Science Center Key Laboratory of Electronics and Information Technology for Space System Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences China School of Computer and Information Engineering Henan Normal University Henan Xinxiang China

ISBN: (纸本)9798350330014

Physically based ray tracing is a technique that involves creating a photo-realistic image from a 3D scene description by utilizing the laws of physics to simulate the behavior of light and matter. However, due to the random length of light samples and irregular memory access patterns, it can suffer from low scalability and severe load imbalance. As a result, the development of a framework for multi-node parallelism algorithm in physically based ray tracing is a significant challenge. To tackle these issues, this paper introduces a novel algorithm named distributed parallel physically based bidirectional path tacing algorithm (DP-BDPT). Through analyzing the physical essence of bidirectional path tracing algorithm and the light transport equation, we have devised a framework that carefully divides tasks between inter-compute nodes and intra-compute nodes. To support high scalability, we have developed a physically based architecture. Additionally, we have proposed a hybrid scheduling method to achieve load balancing. To further enhance performance, we have analyzed several key factors that affect rendering performance and implemented adaptive optimization techniques. The experiments conducted on the Tianhe-2 Supercomputer involving typical and challenging 3D scenes, namely the Cornell-box, Veach-bidir, and Teapot-full experiments, have illustrated that DP-BDPT demonstrate near-linear speedups as the number of CPU cores scales from 1200 to 9600, thereby demonstrating their efficiency when operating on a ten-thousand-core system. © 2023 IEEE.

关键词： Ray tracing

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：