检索结果-内蒙古大学图书馆

2021 IEEE Conference on Telecommunications, Optics and computer Science, TOCS 2021

作者： Zeng, Changchang Li, Shaobo Chen, Bin Chengdu Institute of Computer Application in Chinese Academy of Sciences University of Chinese Academy of Sciences Chengdu China Guizhou University State Key Laboratory of Public Big Data Guiyang China Chongqing Research Institute of HIT Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9781665424981

Machine reading comprehension (MRC) is a challenging research hotspot in the field of Artificial Intelligence (AI). It can be applied to many scenarios, such as intelligent question answering, intelligent document retrieval, and so on. In this article, we focus on the machine reading comprehension of high-Tech industry policy texts in China. First, we create a cloze style machine reading comprehension dataset of Chinese high-Tech industrial policies. Next, we propose a new pre-Training objective named multi-segment ordering discriminator, and we also use domain-specific dictionary to improve the MLM pre-Training process. Finally, on our dataset, we trained a new pre-Trained language model for machine reading comprehension of Chinese industrial policies. Experiment results show that our pre-Trained language model surpasses existing models such as BERT and RoBERTa in the new dataset. © 2021 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Image Steganographic Analysis System Based on Deep Convolutional Neural Network

Adaptive Image Steganographic Analysis System Based on Deep ...

引用

作者： Ge Jiao College of Computer Science and Technology Hengyang Normal University Hunan Provincial Key Laboratory of Intelligent Information Processing and Application

Adaptive steganography emplaces the message into the hard-to-detect noise area or the complex texture area of the image, so the steganography analysis method based on artificial design features needs to design a very complex feature extraction algorithm to detect the steganography image. In view of the advantages of deep learning steganography in automatic extraction of image features and high detection accuracy, an image steganography analysis algorithm is designed by using deep convolutional neural network, and an image steganography analysis system based on deep learning is developed. The system realizes the functions of neural network structure analysis, image steganography and verification, steganography analysis and so on. The system simplifies the operation process of algorithm comparison, reduces the complexity of algorithm performance evaluation, and verifies the feasibility of the proposed algorithm.

关键词： Image steganographic analysis Feature extraction Deep learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Examining the Fourier Spectrum of Speech Signal from a Time-Frequency Perspective for Automatic Depression Level Prediction

引用

IEEE Transactions on Affective Computing 2025年

作者： Niu, Mingyue Tao, Jianhua He, Yongjun Zhang, Shiqing Li, Ming YanShan University School of Information Science and Engineering Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Taizhou University Institute of Intelligent Information Processing Taizhou318000 China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China

Currently, many studies use Fourier amplitude spectra of speech signals to predict depression levels. However, those works often treat Fourier amplitude spectra as images or sequences to capture depression cues using convolutional neural networks or multilayer perceptrons. Therefore, they ignore the complex element composition and time-frequency attributes of Fourier spectra, which is not conducive to capturing the differences among individuals with different depression levels. For this reason, we construct a Time-Frequency Self-Embedding (TFSE) module, which not only stores the correlation relationship among real (imaginary) parts of Fourier spectra of different subjects from the time-frequency perspective, but also maintain the physical properties of data through the weight embedding process. Besides, Global Average Pooling (GAP) or linear layers are difficult to balance both temporal and frequency dimensions in the vectorization process. Therefore, we construct a Time-Frequency Tensor Vectorization (TFTV) module, which summarizes each channel along time and frequency dimensions, and then generates the vectorization result by integrating various channels. In this way, we combine TFSE and TFTV modules to form our SpectrumFormer model for predicting depression levels. Evaluation indicators on AVEC 2013 and AVEC 2014 depression databases imply the progressiveness of our model. © 2010-2012 IEEE.

关键词： Depression level prediction Real and imaginary parts Tensor vectorization Time-frequency attributes

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Graph Transformer with Adaptive Node Sampling

arXiv

引用

arXiv 2022年

作者： Zhang, Zaixi Liu, Qi Hu, Qingyong Lee, Chee-Kong Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong Tencent America United States

The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision. However, when it comes to graph-structured data, transformers have not achieved competitive performance, especially on large graphs. In this paper, we identify the main deficiencies of current graph transformers: (1) Existing node sampling strategies in Graph Transformers are agnostic to the graph characteristics and the training process. (2) Most sampling strategies only focus on local neighbors and neglect the long-range dependencies in the graph. We conduct experimental investigations on synthetic datasets to show that existing sampling strategies are sub-optimal. To tackle the aforementioned problems, we formulate the optimization strategies of node sampling in Graph Transformer as an adversary bandit problem, where the rewards are related to the attention weights and can vary in the training procedure. Meanwhile, we propose a hierarchical attention scheme with graph coarsening to capture the long-range interactions while reducing computational complexity. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of our method over existing graph transformers and popular GNNs. Our code is open-sourced at https://***/zaixizhang/ANS-GT. © 2022, CC BY-SA.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Fast Latent Factor Analysis via a Fuzzy PID-Incorporated Stochastic Gradient Descent Algorithm

arXiv

引用

arXiv 2023年

作者： Li, Jinli Yuan, Ye School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

A high-dimensional and incomplete (HDI) matrix can describe the complex interactions among numerous nodes in various big data-related applications. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm learns a latent factor relying on the stochastic gradient of current instance error only without considering past update information. To address this critical issue, this paper innovatively proposes a Fuzzy PID-incorporated SGD (FPS) algorithm with two-fold ideas: 1) rebuilding the instance learning error by considering the past update information in an efficient way following the principle of PID, and 2) implementing hyper-parameters and gain parameters adaptation following the fuzzy rules. With it, an FPS-incorporated LFA model is further achieved for fast processing an HDI matrix. Empirical studies on six HDI datasets demonstrate that the proposed FPS-incorporated LFA model significantly outperforms the state-of-the-art LFA models in terms of computational efficiency for predicting the missing data of an HDI matrix with competitive accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

High-speed and long-reach PON employing PM-DQPSK signal and coherent receiver

引用

Journal of Optical Communications 2023年第s1期44卷 S97-S105页

作者： Qin, Panke Meng, Hui Zhang, Lei Chen, Guangxuan College of Computer Science and Technology Henan Polytechnic University Henan Jiaozuo454000 China Joint Logistics College National Defence University Beijing100858 China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public Security Zhejiang Police College Zhejiang Hangzhou310053 China

The development of communication technology requires a new type of passive optical network (PON) architecture. The architecture needs to be based on time division multiplexing (TDM) of 40 Gbit/s downstream and 10 Gbit/s upstream, and it can realize TDM PON prototype. The PON system achieved the system distance of 120 km supporting 128 ONU with power budget of 53.5 dB via polarization multiplexing differential quadrature phase shift keying format signal which employs the coherent receiver and the digital signal processing. © 2023 Walter de Gruyter GmbH. All rights reserved.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic Index Modulation With Spread Spectrum for Intra-Body Communications

Ultrasonic Index Modulation With Spread Spectrum for Intra-B...

引用

IEEE International Conference on Communications (ICC)

作者： Qianqian Wang Quansheng Guan Julian Cheng Xiangdong Jia Mangang Xie Yuankun Tang College of Computer Science and Engineering Northwest Normal University Lanzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural Resources Guangzhou China School of Engineering The University of British Columbia Kelowna BC Canada

Ultrasonic intra-body communication (IBC) is an emerging technique to enable revolutionary healthcare applications. This paper proposes an ultrasonic index modulation with spread spectrum (UsIM-SS) scheme for IBCs. The information bits consist of modulation bits and index bits. The core idea of UsIM-SS is that the modulation bits are spread by spreading codes and the index bits are leveraged to select the time-hoping sequence to transmit the spreading bits. We also find that the existing ultrasonic wideband (UsWB) and UsIM can be regarded as special cases of the proposed UsIM-SS. Furthermore, the soft decision-based maximum likelihood (S-ML) receiver and hard decision-based ML (H-ML) receiver are proposed for UsIM-SS, providing a trade-off between bit-error rate (BER) and complexity. Theoretical spectrum efficiency (SE) and BER expressions for UsIM-SS using S-ML and H-ML are also derived and verified by extensive Monte Carlo simulations. Both theoretical and simulation results show that UsIM-SS can achieve lower BER and higher SE than existing UsWB and Us 1M techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized and Lightweight Cross-Chain Transaction Scheme Based on Proxy Re-signature

Decentralized and Lightweight Cross-Chain Transaction Scheme...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Huiying Zou Jia Duan Xi Liu Wei Ren Tao Li Xianghan Zheng Kim-Kwang Raymond Choo School of Computer Science China University of Geosciences Wuhan China The Third Surveying and Mapping Institute of Hunan Province Hunan Engineering Research Center of Geographic Information Security and Application Hunan China Key Laboratory of Data Protection and Intelligent Management Sichuan University Ministry of Education China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR CASM Beijing China College of Computer and Big Data Fuzhou University School of Information and Intelligent Engineering Sanya College China Department of Information Systems and Cyber Security University of Texas at San Antonio San Antonio USA

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

With the widespread application of digital assets and the rapid development of blockchain technology, achieving secure and efficient transactions between different blockchain networks has become an urgent challenge. Existing cross-chain methods impose limitations, e.g., hash lock technology exhibits low scalability, side-chain technology is overly complex, and notary schemes pose centralization risks. In order to address these issues, we propose a cross-chain transaction solution based on proxy re-signature technology. To tackle the centralization concerns, we employ proxy re-signature technology to decentralize the authority of notaries among transaction participants, minimizing the potential for centralization at a low cost. We further present an extended scheme that can guarantee more requirements such as higher transaction amount and shorter transaction time. Furthermore, we analyze and compare the signature technologies used in the proposed solution and provide a systematic proof of our approach’s security.

关键词： Privacy Systematics Costs Scalability Blockchains Security

来源：评论

学校读者我要写书评

暂无评论

DAM: Degradation-aware Model for Ultrasound Image Quality Assessment

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Liu, Tuo Zhang, Xuan Ma, Xiuzhu Chen, Shuang Wang, Xuejuan Zhou, Ping Chen, Yang Zhou, Guangquan Lv, Faqin Southeast University School of Biological Science and Medical Engineering Nanjing 211189 China Chinese People's Liberation Army General Hospital Medical Center 3 Beijing 100039 China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing the Laboratory of Image Science and Technology the School of Computer Science and Engineering Nanjing 210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China Southeast University Jiangsu Key Laboratory of Biomaterials and Devices Nanjing 211189 China Southeast University State Key Laboratory of Digital Medical Engineering Nanjing 211189 China

One of the core challenges in ultrasound image quality assessment (IQA) is the entanglement of semantic content and quality-related information, such as blurring and shadows. Insufficient attention to the latter can easily lead to biased IQA results. Furthermore, fine-grained quality inconsistencies, i.e., subtle variations in ultrasound images that can impact quality interpretations, may further complicate the IQA tasks. To address these challenges, we propose a novel degradation-aware model (DAM) for the ultrasound IQA, which effectively perceives various and subtle variations of quality patterns, accurately assessing the quality of ultrasound images. The advanced degradation-derived augmentation (DDA) in DAM incorporates degradations that clinicians may focus on during IQA into the synthesis of appearance changes, promoting the disentanglement of quality-related representations from semantic contents. Subsequently, we present fine-grained degradation learning (FGDL), which encourages distinctions between image versions with diminishing quality inconsistencies, boosting the awareness of quality nuances from easy to hard for better ultrasound IQA performance. A universal boundary acquisition operator (UBAO) is also developed to suppress interferences from redundant information, achieving the standardization of ultrasound images from various devices. Extensive experimental results on an in-house ultrasound dataset demonstrate that DAM outperforms 14 baseline methods, achieving a PLCC of 0.760 and an SROCC of 0.766. © 2013 IEEE.

关键词： degradation-aware model degradation-derived augmentation fine-grained degradation learning Ultrasound image quality assessment universal boundary acquisition operator

来源：评论

学校读者我要写书评

暂无评论

Human-like adrenal features in Chinese tree shrews revealed by multi-omics analysis of adrenal cell populations and steroid synthesis

引用

Zoological Research 2024年第3期45卷 617-632页

作者： Jing-Hang Jiang Yi-Fu Wang Jie Zheng Yi-Ming Lei Zhong-Yuan Chen Yi Guo Ya-Jie Guo Bing-Qian Guo Yu-Fang Lv Hong-Hong Wang Juan-Juan Xie Yi-Xuan Liu Ting-Wei Jin Bi-Qi Li Xiao-Shu Zhu Yong-Hua Jiang Zeng-Nan Mo Center for Genomic and Personalized Medicine Guangxi Collaborative Innovation Center for Genomic and Personalized MedicineGuangxi Key Laboratory for Genomic and Personalized MedicineGuangxi Medical UniversityNanningGuangxi 530021China Department of Urology First Affiliated Hospital of Guangxi Medical UniversityNanningGuangxi 530021China Reproductive Medicine Center Jingmen People’s HospitalJingChu University of Technology Affiliated Central HospitalJingmenHubei 448000China School of Computer Science and Engineering Yulin Normal UniversityYulinGuangxi 537000China Collaborative Innovation Centre of Regenerative Medicine and Medical BioResource Development and Application Co-constructed by the Province and Ministry Guangxi Medical UniversityNanningGuangxi 530021China Department of Pathology Second Affiliated Hospital of Guangxi Medical UniversityNanningGuangxi 530007China Department of Obstetrics and Gynecology Second Affiliated Hospital of Guangxi Medical UniversityNanningGuangxi 530007China

The Chinese tree shrew(Tupaia belangeri chinensis)has emerged as a promising model for investigating adrenal steroid synthesis,but it is unclear whether the same cells produce steroid hormones and whether their production is regulated in the same way as in ***,we comprehensively mapped the cell types and pathways of steroid metabolism in the adrenal gland of Chinese tree shrews using single-cell RNA sequencing,spatial transcriptome analysis,mass spectrometry,and *** compared the transcriptomes of various adrenal cell types across tree shrews,humans,macaques,and *** showed that tree shrew adrenal glands expressed many of the same key enzymes for steroid synthesis as humans,including CYP11B2,CYP11B1,CYB5A,and *** analysis confirmed the production of aldosterone,cortisol,and dehydroepiandrosterone but not dehydroepiandrosterone sulfate in the tree shrew adrenal ***,genes in adrenal cell types in tree shrews were correlated with genetic risk factors for polycystic ovary syndrome,primary aldosteronism,hypertension,and related disorders in humans based on genome-wide association ***,this study suggests that the adrenal glands of Chinese tree shrews may consist of closely related cell populations with functional similarity to those of the human adrenal *** comprehensive results(publicly available at http://***:16245/scAGMap/)should facilitate the advancement of this animal model for the investigation of adrenal gland disorders.

关键词： Tree shrew Adrenal gland Dehydroepiandrosterone Genome-wide association studies Disease model

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：