检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sun, Shilin An, Wenbin Tian, Feng Nan, Fang Liu, Qidong Liu, Jun Shah, Nazaraf Chen, Ping School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an710049 China Institute for Future Transport and Cities Coventry University Priory Street CoventryCV1 5FB United Kingdom Department of Engineering University of Massachusetts Boston BostonMA02125 United States

Artificial intelligence (AI) has rapidly developed through advancements in computational power and the growth of massive datasets. However, this progress has also heightened challenges in interpreting the "black-box" nature of AI models. To address these concerns, eXplainable AI (XAI) has emerged with a focus on transparency and interpretability to enhance human understanding and trust in AI decision-making processes. In the context of multimodal data fusion and complex reasoning scenarios, the proposal of Multimodal eXplainable AI (MXAI) integrates multiple modalities for prediction and explanation tasks. Meanwhile, the advent of Large Language Models (LLMs) has led to remarkable breakthroughs in natural language processing, yet their complexity has further exacerbated the issue of MXAI. To gain key insights into the development of MXAI methods and provide crucial guidance for building more transparent, fair, and trustworthy AI systems, we review the MXAI methods from a historical perspective and categorize them across four eras: traditional machine learning, deep learning, discriminative foundation models, and generative LLMs. We also review evaluation metrics and datasets used in MXAI research, concluding with a discussion of future challenges and directions. A project related to this review has been created at https://***/ShilinSun/mxai_review. Copyright © 2024, The Authors. All rights reserved.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

Accelerated evolution of an Lhx2 enhancer shapes mammalian social hierarchies

引用

细胞研究（英文版） 2020年第5期30卷 408-420页

作者： Yuting Wang Guangyi Dai Zhili Gu Guopeng Liu Ke Tang Yi-Hsuan Pan Yujie Chen Xin Lin Nan Wu Haoshan Chen Su Feng Shou Qiu Hongduo Sun Qian Li Chuan Xu Yanan Mao Yong Edward Zhang Philipp Khaitovich Yan-Ling Wang Qunxiu Liu Jing-Dong Jackie Han Zhen Shao Gang Wei Chun Xu Naihe Jing Haipeng Li CAS Key Laboratory of Computational Biology CAS-MPG Partner Institute for Computational Biology Shanghai Institute of Nutrition and Health Chinese Academy of SciencesYueyang Road 320 200031 Shanghai China University of Chinese Academy of Sciences Beijing China Precise Genome Engineering Center School of Life SciencesGuangzhou University Guangzhou 510405 Guangdong China Key Laboratory of Brain Functional Genomics of Ministry of Education School of Life Science East China Normal University 200062 Shanghai China Bio-Med Big Data Center CAS Key Laboratory of Computational Biology CAS-MPG Partner Institute for Computational Biology Shanghai Institute of Nutrition and Health Chinese Academy of Sciences Yueyang Road 320 200031 Shanghai China Institute of Neuroscience CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Yueyang Road 320 200031 Shanghai China State Key Laboratory of Cell Biology Institute of Biochemistry and Cell Biology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Yueyang Road 320 200031 Shanghai China Key Laboratory of Zoological Systematics and Evolution & State Key Laboratory of Integrated Management of Pest Insects and Rodents Institute of Zoology Chinese Academy of Sciences 100101 Beijing China Center for Excellence in Animal Evolution and Genetics Chinese Academy of Sciences 650223 Kunming China State Key Laboratory of Stem cell and Reproductive Biology Institute of Zoology Chinese Academy of Sciences 100101 Beijing China Shanghai Zoological Park 200335 Shanghai China

Social hierarchies emerged during evolution,and social rank influences behavior and health of ***,the evolutionary mechanisms of social hierarchy are still unknown in *** we developed a new method and performed a genome-wide screening for identifying regions with accelerated evolution in the ancestral lineage of placental mammals,where mammalian social hierarchies might have initially *** functional analyses were conducted for the most accelerated region designated as placental-accelerated sequence 1 (PAS1,P=3.15 × 10-18).Multiple pieces of evidence show that PAS1 is an enhancer of the transcription factor gene Lhx2 involved in brain ***1s isolated from various amniotes showed different cis-regulatory activity in vitro,and affected the expression of Lhx2 differently in the nervous system of mouse ***1 knock-out mice lack social ***1 knock-in mouse models demonstrate that PAS1s determine the social dominance and subordinate of adult mice,and that social ranks could even be turned over by mutated *** homozygous mutant mice had normal huddled sleeping behavior,motor coordination and ***,PAS1-Lhx2 modulates social hierarchies and is essential for establishing social stratification in amniotes,and positive Darwinian selection on PAS1 plays pivotal roles in the occurrence of mammalian social hierarchies.

关键词： Bioinformatics Comparative genomics

来源：评论

学校读者我要写书评

暂无评论

Ecas: an efficient and conditional privacy preserving collision warning system in fog-based vehicular ad hoc networks

引用

CCF Transactions on networking 2020年第3期3卷 205-217页

作者： Qin, Zhiguang Li, Yuedi Ye, Xin Zhou, Jin Cao, Minsheng Chen, Dajiang Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China Peng Cheng Laboratory Shenzhen China

VANET is a prominent way to provide road security and prevent vehicles from collision by using various methods, such as message dissemination, traffic management, etc. However, the traditional vehicular network faces some problems related to high latency, low bandwidth, and communication in open wireless environment. Thus, some researchers have attempted to combine fog computing with vehicular ad hoc networks to overcome these problems. In this paper, we design an efficient and conditional privacy preserving collision warning system for fog-based vehicular ad hoc networks without using bilinear pairing. The fog nodes collect the speed violation reports from the speed sensor of vehicles. This protocol achieves privacy protection, message authentication, and revocate malicious vehicles. We also provide strict security proof and illustrate how to reach the security requirements in the proposed protocol. Moreover, the experiment demonstrates that the proposed protocol provides better efficiency in computation overhead and communication overhead, and makes it more applicable for adoption in the VANET collision warning systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User Profiling for CSDN:keyphrase Extraction,User Tagging and User Growth Value Prediction

引用

data Intelligence 2019年第2期1卷 137-159页

作者： Guoliang Xing Hao Gao Qi Cao Xinyu Yue Bingbing Xu Keting Cen Huawei Shen Key Laboratory of Network Data Science and Technology Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

The Chinese Software Developer network(CSDN)is one of the largest information technology communities and service platforms in *** paper describes the user profiling for CSDN,an evaluation track of SMP Cup *** contains three tasks:(1)user document keyphrase extraction,(2)user tagging and(3)user growth value *** the first task,we treat keyphrase extraction as a classification problem and train a Gradient-Boosting-Decision-Tree model with comprehensive *** the second task,to deal with class imbalance and capture the interdependency between classes,we propose a two-stage framework:(1)for each class,we train a binary classifier to model each class against all of the other classes independently;(2)we feed the output of the trained classifiers into a softmax classifier,tagging each user with multiple *** the third task,we propose a comprehensive architecture to predict user growth *** contributions in this paper are summarized as follows:(1)we extract various types of features to identify the key factors in user value growth;(2)we use the semi-supervised method and the stacking technique to extend labeled data sets and increase the generality of the trained model,resulting in an impressive performance in our *** the competition,we achieved the first place out of 329 teams.

关键词： User profiling keyphrase extraction User tagging Growth value prediction Word embedding

来源：评论

学校读者我要写书评

暂无评论

Toward the Understanding of Deep Text Matching Models for Information Retrieval

arXiv

引用

arXiv 2021年

作者： Chen, Lijuan Lan, Yanyan Pang, Liang Guo, Jiafeng Cheng, Xueqi Sogou Inc. Beijing China Institute for AI Industry Research Tsinghua University Beijing China Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is hard to understand what happened in the matching process, due to the poor interpretability of deep learning. This paper aims at tackling this problem. The key idea is to test whether existing deep text matching methods satisfy some fundamental heuristics in information retrieval. Specifically, four heuristics are used in our study, i.e., term frequency constraint, term discrimination constraint, length normalization constraints, and TF-length constraint. Since deep matching models usually contain many parameters, it is difficult to conduct a theoretical study for these complicated functions. In this paper, We propose an empirical testing method. Specifically, We first construct some queries and documents to make them satisfy the assumption in a constraint, and then test to which extend a deep text matching model trained on the original dataset satisfy the corresponding constraint. Besides, a famous attribution based interpretation method, namely integrated gradient, is adopted to conduct detailed analysis and guide for feasible improvement. Experimental results on LETOR 4.0 and MS Marco show that all the investigated deep text matching methods, both representation and interaction based methods, satisfy the above constraints with high probabilities in statistics. We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models. These empirical findings give clear understandings on why deep text matching models usually perform well in information retrieval. We believe the proposed evaluation methodology will be useful for testing future deep text matching models. © 2021, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

arXiv

引用

arXiv 2022年

作者： Duan, Yue Zhao, Zhen Qi, Lei Wang, Lei Zhou, Luping Shi, Yinghuan Gao, Yang The National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Electrical and Information Engineering The University of Sydney SydneyNSW2006 Australia The School of Computer Science and Engineering The Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples. In this paper, we aim to utilize low-confidence samples in a novel way with our proposed mutex-based consistency regularization, namely MutexMatch. Specifically, the high-confidence samples are required to exactly predict "what it is" by conventional True-Positive Classifier, while low-confidence samples are employed to achieve a simpler goal — to predict with ease "what it is not" by True-Negative Classifier. In this sense, we not only mitigate the pseudo-labeling errors but also make full use of the low-confidence unlabeled data by consistency of dissimilarity degree. MutexMatch achieves superior performance on multiple benchmark datasets, i.e., CIFAR-10, CIFAR-100, SVHN, STL-10, mini-ImageNet and Tiny-ImageNet. More importantly, our method further shows superiority when the amount of labeled data is scarce, e.g., 92.23% accuracy with only 20 labeled data on CIFAR-10. Our code and model weights have been released at https://***/NJUyued/MutexMatch4SSL. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

EnGAN: Enhancement Generative Adversarial network in Medical Image Segmentation

Research Square

引用

Research Square 2022年

作者： Deng, ErQiang Qin, ZhiGuang Chen, DaJiang Qin, Zhen Ding, Yi Geng, Ji Zhang, Ning Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Jianshe Road SiChuan Chengdu610054 China Department of Electrical and Computer Engineering University of Windsor 401 Sunset Avenue WindsorONN9B 3P4 Canada

Deep learning has been widely used in medical image segmentation, although the accuracy is affected by the problems of small sample space, data imbalance, and cross-device differences. Aiming at such issues, a enhancement GAN network is proposed by using the domain transferring of the adversarial generation network to enhance the original medical images. Specifically, based on retaining the transferability of the original GAN network, a new optimizer is added to generate a sample space with a continuous distribution, which can be used as the target domain of the original image transferring. The optimizer back-propagates the labels of the supervised data set through the segmentation network and maps the discrete distribution of the labels to the continuous image distribution, which has a high similarity to the original image but improves the segmentation efficiency. On this basis, the optimized distribution is taken as the target domain, and the generator and discriminator of the GAN network are trained so that the generator can transfer the original image distribution to the target distribution. extensive experiments are conducted based on MRI, CT, and ultrasound data sets. The experimental results show that, the proposed method has a good generalization effect in medical image segmentation, even when the data set has limited sample space and data imbalance to a certain extent. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

FLDDoS: DDoS Attack Detection Model based on Federated Learning

FLDDoS: DDoS Attack Detection Model based on Federated Learn...

引用

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

作者： Jiachao Zhang Peiran Yu Le Qi Song Liu Haiyu Zhang Jianzhong Zhang Institute of Systems and Networks Nankai University College of Computer Science Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Shijiazhuang Huayan Traffic Technology Co. Ltd.

ISBN: (纸本)9781665416597

Recently, DDoS attack has developed rapidly and become one of the most important threats to the Internet. Traditional machine learning and deep learning methods can-not train a satisfactory model based on the data of a single client. Moreover, in the real scenes, there are a large number of devices used for traffic collection, these devices often do not want to share data between each other depending on the research and analysis value of the attack traffic, which limits the accuracy of the model. Therefore, to solve these problems, we design a DDoS attack detection model based on federated learning named FLDDoS, so that the local model can learn the data of each client without sharing the data. In addition, considering that the distribution of attack detection datasets is extremely imbalanced and the proportion of attack samples is very small, we propose a hierarchical aggregation algorithm based on K-Means and a data resampling method based on SMOTEENN. The result shows that our model improves the accuracy by 4% compared with the traditional method, and reduces the number of communication rounds by 40%.

关键词： Deep learning Privacy data privacy Computational modeling Clustering algorithms Denial-of-service attack Collaborative work

来源：评论

学校读者我要写书评

暂无评论

Long-term variations of X-ray pulse profiles for the Crab pulsar:data analysis and modeling

引用

science China(Physics,Mechanics & Astronomy) 2020年第10期63卷 111-131页

作者： LunHua Shang YuanJie Du XiangQun Cui ShiJun Dang JiGuang Lu JunTao Bai QiJun Zhi YouLi Tuo LinLi Yan LiangWei Huang XinYuan Zhang XiaoMin Bei QingQing Lin GuoJun Qiao Hua Shen RiHong Zhu School of Electronic and Optical Engineering Nanjing University of Science and TechnologyNanjing 210094China Qian Xuesen Laboratory of Space Technology Beijing 100094China Nanjing Institute of Astronomical Optics and Technology National Astronomical ObservatoriesChinese Academy of SciencesNanjing 210042China XinJiang Astronomical Observatory Chinese Academy of SciencesUrumqi 830011China University of Chinese Academy of Sciences Beijing 100049China CAS Key Laboratory of FAST National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China Guizhou Radio Astronomy Observatory Chinese Academy of SciencesGuiyang 550025China School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550001China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal UniversityGuiyang 550001China Key Laboratory of Particle Astrophysics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China School of Physics Peking UniversityBeijing 100871China Key Laboratory of Advanced Solid Laser Nanjing University of Science and TechnologyNanjing 210094China

The pulse profiles of the Crab pulsar(as well as some other pulsars)vary with *** can lead to a major source of intrinsic timing noise,which lacks a detailed physical *** phase separation?between the first left peak(P1)and the second right peak(P2)is a key parameter that shows the variations of pulse profiles for the Crab *** was found that the evolution of?has a tendency with increasing rates of 0.82?±0.25?,0.80?±0.54?,and 0.77?±0.28?per century for the 2-6,6-15,and15-60 ke V bands,***,the flux ratios(P2/P1)of X-ray pulse profiles in the three bands were calculated,and the derived flux ratios were consistent with the radio and X-ray measurements of the *** addition to discovering the physical origin of the pulse changes,the high-SNR X-ray pulse profiles were simulated in the annular gap model,and two model parameters(e.g.,the maximum emission heights of the two peaks)were observed to slightly affect the variations of peak *** fitted the long-term variations of emission heights of the two peaks and discovered that the emission heights showed increasing tendencies with *** of these emission heights induced a characteristic period derivative,and a complete formula for both the magnetic dipole radiation and wind-particle-induced variations of the moment of inertia was used for the pulsar’s spin-down to obtain the variation rate˙αof the magnetic inclination angle,which was-1.60?per *** timing noise is observed to be mainly induced by the variations of pulse profiles,which might correlate with a characteristic spin period derivative arising from the fluctuations of the emission *** work will lay a foundation for understanding the origin of intrinsic timing noise and making high-precision timing models in the future.

关键词： radiation mechanisms pulsars X-ray

来源：评论

学校读者我要写书评

暂无评论

VEIN: High Scalability Routing Algorithm for Blockchain-based Payment Channel networks

VEIN: High Scalability Routing Algorithm for Blockchain-base...

引用

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

作者： Qianyun Gong Chengjin Zhou Le Qi Jianbin Li Jianzhong Zhang Jingdong Xu Institute of Systems and Networks College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Shijiazhuang Huayan Traffic Technology Co. Ltd.

ISBN: (纸本)9781665416597

The payment channel networks (PCNs), as the main method of blockchain off-chain expansion, have received extensive attention in recent years. Using the PCNs, two unconnected parties in a transaction can forward payments through existing payment channels of other nodes, which dramatically reduces interactions with the blockchain. But in large-scale dynamic PCNs, the routing mechanism is a challenge. Existing PCNs routing algorithms have some limitations. The landmark routing destroys the decentralization of blockchain. The static routing requires nodes having a global view and ultra-high computing power, which can not be applied to light nodes. We propose VEIN, a dynamic multi-path source routing algorithm, which is suitable for not only full nodes but also light nodes. We present an ingenious routing protocol, a modified max-flow algorithm to find edge-disjoint paths, and a path selection algorithm to deal with the NP-hard multi-path selection problem. Extensive experiments show that VEIN increases the transaction success ratio by 34% with the state-of-art algorithm, and realizes multiple orders of magnitude reduction in storage. In addition, we implement a prototype of VEIN on the Ethereum testnet to verify its feasibility.

关键词： Privacy Heuristic algorithms Veins Scalability Conferences Prototypes Routing

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：