检索结果-内蒙古大学图书馆

2020 International Conference on Networking and Network Applications, NaNA 2020

作者： Xiang, Kang Tian, Youliang Gao, Sheng Peng, Changgen Tan, Weijie Institute of Cryptography and Data Security Guizhou University Guiyang550025 China School of Information Central University of Finance and Economics Beijing100081 China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9781728189543

At present, many enterprises or individuals with a lot of data are limited by their own computing power, so can't mine useful information from the data. To address this problem, this paper proposes a rational delegation machine learning pattern. In the proposed pattern, we firstly construct a reliable game model, and then derive a formal model of rational delegation machine learning according to delegation computation thought. Finally, we design an outsourcing scheme for decision tree model. We analyze the security and performance of the proposed scheme, the analysis results show that the proposed scheme can not disclose any useful information. Last but not least, the experimental result demonstrates that the proposed scheme can obtain a decision tree model with high accuracy. © 2020 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

arXiv

引用

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TPDNet: Triple phenotype deepen networks for monocular 3D object detection of melons and fruits in fields

引用

Plant Phenomics 2025年第2期7卷

作者： Yazhou Wang Tianhan Zhang Xingcai Wu Qinglei Li Yuquan Li Qi Wang School of Information Guizhou University of Finance and Economics Guiyang 550025 China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang 550025 China

The growth of the global population has increased the demand for fruits and vegetables, while high harvesting labor costs severely constrain industry development. Currently, relevant personnel primarily utilize 2D object detection technology to facilitate automated harvesting, aiming to reduce labor costs. However, 2D detection technology is limited to providing planar information and cannot meet the requirements of scenarios that need 3D spatial data, whereas 3D object detection technology can effectively address these needs, including point cloud-based methods and monocular-based methods. Since point cloud-based object detection methods require expensive equipment, they are not suitable for low-cost agricultural harvesting scenarios. In contrast, monocular 3D object detection methods have the advantage of only requiring a camera and being easy to deploy. However, there is a lack of specialized monocular 3D object detection datasets and algorithms suited for natural scenes in the agricultural field, which limits the application and development of this technology in agricultural automation. To address this, we construct a 3D object detection dataset for wax gourds and propose a network called TPDNet, which aims to capture the 3D information of objects from a single RGB image for fruits and vegetables in fields. Specifically, we construct a depth estimation and enhance module that introduces depth information into the model with the help of depth auxiliary labels, and improves the representation of depth information by utilizing weight information across spatial and channel dimensions. Meanwhile, since depth features and image features are heterogeneous, we design the phenotype aggregation and phenotype intensify module to capture the correspondence between image and depth features, promoting the effective fusion of image and depth information. The experimental results show that our method significantly outperforms others in terms of mAP 3 D and mAP BEV metrics, demo

关键词： 3D object detection Monocular Melons and fruits in fields

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-assisted niacin skin flush screening in early psychosis identification and prediction

引用

General Psychiatry 2022年第2期35卷 76-78页

作者： Tao Chen Haichun Liu Renfang Tian Ranpiao Gan Wenzuo Xu Tianhong Zhang Jijun Wang Department of Economics University of WaterlooWaterlooOntarioCanada Depatment of Statistics and Actuarial Science(Cross Appointed) University of Waterloo WaterlooOntarioCanada Big Data Research Lab Universty of WaterlooWaterlooOntarioCanada Shanghai Niacin Tech Co. LtdShanghal China Labor and Worklife Program Harvard UniversityCambridgeMassachusettsUSA Department of Automation Shanghai Jao Tong UniversityShanghaiChina Ningbo Artificial Intelligent Institute Shanghai Jiao Tong UniversityNingboChina School of Management Economicsand MathematicsKing's University CollegeLondon0ntarioCanada Shanghai Intelligent Psychological Evaluaton and Intervention Engineering Technology Research Center Shanghai Key Laboratory of Psychotic DisordersShanghai Mental Health CenterShanghai Jiao Tong University School of MedicineShanghaiChina Bio-X Institutes Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders(Ministry of Education)ShanghaiChina CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghaiChina Institute of Psychology and Behavioral Science Shanghai Jiao Tong UniversiyShanghaiChina

Schizophrenia is a devastating mental disorder affecting 20 million people *** diagnosis is crucial for disease management and improvement in prognosis,and diagnostic biomarkerscan serveasobjective indicators for the early screening of the *** on the observation of diminished flush responses to niacin in patients with schizophrenia Horrobin proposed anoninvasive niacin skin flush screening for schizophrenia.

关键词： diagnosis prognosis prediction

来源：评论

学校读者我要写书评

暂无评论

Tailor: Inter-Feature Distinction Filter Fusion Pruningtailor: Inter-Feature Distinction Filter Fusion Pruning

SSRN

引用

SSRN 2023年

作者： Han, Xuming Chu, Yali Wang, Ke Wang, Limin Yue, Lin Ding, Weiping Gu, Tianlong Weng, Jian College of Information and Science Jinan University Guangzhou510632 China School of Mathematics and Statistics Changchun University of Technology Jilin130000 China Trusted AI Engineering Research Center Ministry of Education Jinan University Guangzhou510632 China School of Artificial Intelligence and Digital Economy Industry Guangdong University of Finance and Economics Guangzhou510320 China University of Newcastle Australia School of Information and Science Nantong University Nantong China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Jinan University Guangzhou510632 China

Filter pruning is an effective compression method for slimming deep convolutional neural networks by removing the partial structure of the network without sacrificing performance. The pruning criteria directly affect the performance of the network model after compression. Currently, pruning criteria mainly measure the norm of a filter weight matrix (L1 norm and L2 norm)and the matrix rank of a feature map. These criteria are based on the amount of filtered information. We found that inter-feature distinction among filters is also a significant factor in directing filter pruning, in contrast to previous methods. We propose a pruning method that fuses distinction between the output feature maps of filters, namely inTer-feAture distinctIon fiLter fusiOn pRuning (TAILOR). The TAILOR method was implemented by randomly selecting multiple filter combinations in the convolutional layer through the pruning rate and calculating the output feature maps of the next convolutional layer of these combinations. An intelligent distinction optimization scheme was proposed. The approximate optimal solution yields a filter combination, which then supplants the original convolutional layer to facilitate filter pruning. The results indicate that the inter-feature distinctions among filters significantly affect filter pruning. In addition, TAILOR outperforms state-of-the-art filter-pruning methods in terms of model prediction accuracy, floating-point operations, and parameter scale. For example, with VGG-16, we achieve a 70.93% FLOPs reduction by removing 90.05% of the parameters, with a loss of 0.44% in accuracy on CIFAR-10. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Aggregative Clustering Based on Principal Component Radius

SSRN

引用

SSRN 2022年

作者： Cheng, Mingchang Liu, Liu Ma, Tiefeng Du, Jinchao Yan, Qijing V.C.&V.R. Key Lab of Sichuan Provence Sichuan Normal University Chengdu610066 China College of Mathematics and Physics Chengdu University of Technology Chengdu610059 China School of Statistics Southwestern University of Finance and Economics Chengdu611130 China China Electric Power Research Institute of State Grid Beijing100192 China School of Statistics and Data Science Faculty of Science Beijing University of Technology Beijing100124 China

Center-based clustering algorithms such as k-means have strict requirements on data distribution and need to accurately specify the number of clusters. In order to overcome the above limitations, this paper proposes an effective aggregation clustering framework based on the principle component radius (PCR) called PCR-AC. First, k-means++ is used to be the embedding algorithm for initialization. Then, PCR can accurately characterize the core region of clusters to guide cluster merging. On this foundation, a graph based aggregation process can quickly complete cluster identification and improve the local convergence of the embedding algorithm. Experimental results verify the superiority of the proposed algorithm and its high tolerance to initialization. © 2022, The Authors. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Towards Long-Range ENSO Prediction with an Explainable Deep Learning Model

arXiv

引用

arXiv 2025年

作者： Chen, Qi Cui, Yinghao Hong, Guobin Ashok, Karumuri Pu, Yuchun Zheng, Xiaogu Zhang, Xuanze Zhong, Wei Zhan, Peng Wang, Zhonglei Department of Ocean Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science School of Economic Xiamen University Xiamen361005 China MOE Key Laboratory of Econometrics Xiamen University Xiamen361005 China Centre for Earth Ocean and Atmospheric Sciences University of Hyderabad Hyderabad India Baidu Inc. Beijing100085 China Shanghai Zhangjiang Institute of Mathematics Shanghai201203 China International Global Change Institute Hamilton New Zealand Key Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China Wang Yanan Institute for Studies in Economics Xiamen University Xiamen361005 China

El Niño-Southern Oscillation (ENSO) is a prominent mode of interannual climate variability with far-reaching global impacts. Its evolution is governed by intricate air-sea interactions, posing significant challenges for long-term prediction. In this study, we introduce CTEFNet, a multivariate deep learning model that synergizes convolutional neural networks and transformers to enhance ENSO forecasting. By integrating multiple oceanic and atmospheric predictors, CTEFNet extends the effective forecast lead time to 20 months while mitigating the impact of the spring predictability barrier, outperforming both dynamical models and state-of-the-art deep learning approaches. Furthermore, CTEFNet offers physically meaningful and statistically significant insights through gradient-based sensitivity analysis, revealing the key precursor signals that govern ENSO dynamics, which align with well-established theories and reveal new insights about inter-basin interactions among the Pacific, Atlantic, and Indian Oceans. The CTEFNet’s superior predictive skill and interpretable sensitivity assessments underscore its potential for advancing climate prediction. Our findings highlight the importance of multivariate coupling in ENSO evolution and demonstrate the promise of deep learning in capturing complex climate dynamics with enhanced interpretability. © 2025, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Minimal Binary Linear Codes from Vectorial Boolean Functions

arXiv

引用

arXiv 2022年

作者： Li, Yanjun Peng, Jie Kan, Haibin Zheng, Lijing Institute of Statistics and Applied Mathematics Anhui University of Finance & Economics Anhui Bengbu233030 China Mathematics and Science College of Shanghai Normal University Guilin Road #100 Shanghai200234 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Engineering Research Center of Blockchain Shanghai Institute for Advanced Communication and Data Science Shanghai200433 China School of Mathematics and Physics University of South China Hunan Hengyang421001 China

Recently, much progress has been made to construct minimal linear codes due to their preference in secret sharing schemes and secure two-party computation. In this paper, we put forward a new method to construct minimal linear codes by using vectorial Boolean functions. Firstly, we give a necessary and sufficient condition for a generic class of linear codes from vectorial Boolean functions to be minimal. Based on that, we derive some new three-weight minimal linear codes and determine their weight distributions. Secondly, we obtain a necessary and sufficient condition for another generic class of linear codes from vectorial Boolean functions to be minimal and to be violated the AB condition. As a result, we get three infinite families of minimal linear codes violating the AB condition. To the best of our knowledge, this is the first time that minimal liner codes are constructed from vectorial Boolean functions. Compared with other known ones, in general the minimal liner codes obtained in this paper have higher dimensions. © 2022, CC BY-NC-SA.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

METER: An Ensemble DWT-based Method for Identifying Low-rate DDoS Attack in SDN

METER: An Ensemble DWT-based Method for Identifying Low-rate...

引用

IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC

作者： Cong Wang Yunhe Cui Qing Qian Guowei Shen Hongfeng Gao Saifei Li Guizhou Provincial Key Laboratory of Public Big Data School of Computer Science and Technology Guizhou University Guiyang China School of information GuiZhou University of Finance and Economics Guiyang China School of Information Science and Technology Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781665400374

As one of the next generation of network architectures, Software-Defined Networking (SDN) decouples the forwarding and control function of the traditional network device. However, it also faces new threats from network attacks, such as the Low-rate Distributed Denial of Service (L-DDoS) attack. To resist L-DDoS attack in SDN, this work proposes METER, an enseMble discrEte wavelet Transform-based method for idEntifying low-Rate DDoS attack in SDN. The rationale for METER is to identify L-DDoS attacks based on a new metric referred to as the Ensemble Wavelet Energy Entropy set (EWEEs), which is calculated by a novel ensemble DWT method. Firstly, the ensemble wavelet coefficients matrix is attained by METER using the ensemble DWT method. After that, METER combines the related entropy values with wavelet energy of the ensemble wavelet coefficients matrix to obtain EWEEs. Furthermore, to increase the precision of the L-DDoS detection method, machine learning methods are used to mine the correlation between EWEEs and L-DDoS attacks for identifying L-DDoS. The experiments were implemented on the RYU controller and Mininet, which demonstrates that METER outperforms the baseline method, in terms of precision, accuracy, F -score, recall, ROC curve, and P-R curve.

关键词： Meters Measurement Support vector machines Resists Denial-of-service attack Ubiquitous computing Entropy

来源：评论

学校读者我要写书评

暂无评论

Distribution regression with censored selection

引用

Journal of Econometrics 2025年 251卷

作者： Songnian Chen Nianqing Liu Hanghui Zhang Tsingshan Institute for Advanced Business Studies Zhejiang University Hangzhou China School of Economics Zhejiang University Hangzhou China MOE Key Laboratory of Econometrics and Fujian Key Lab of Statistics Xiamen University Xiamen China Paula and Gregory Chow Institute for Studies in Economics Xiamen University Xiamen China Department of Statistics and Data Science School of Economics Xiamen University Xiamen China School of Economics The Shanghai University of Finance and Economics Shanghai China Key Laboratory of Mathematical Economics (SUFE) Ministry of Education Shanghai 200433 China

Chernozhukov, Fernández-Val, and Luo (2023, CFL (2023) hereafter) considered a distribution regression model subject to sample selection with a binary selection mechanism. In this paper, we show how to identify and estimate a semi-parametric distribution regression model subject to a censored selection rule. With censored selection, we do not need to impose the usual outcome exclusion restriction or exclusion of the level of the latent selection variable from the selection sorting function for model identification, unlike CFL (2023). We propose new semiparametric estimators and corresponding inference procedures for model parameters and related functional parameters. We apply our method to investigate wage inequality in the UK for the period 1978–2000 using the Family Expenditure Survey (FES) data. Our findings reveal that (i) the selection sorting exclusion and outcome exclusion restrictions imposed by CFL (2023) are rejected; (ii) there is negative selection into work at most quantile levels for females, but not for males; (iii) in contrast to CFL (2023), our selection sorting effect pattern does not offer clear evidence on assortative matching or glass ceiling in the UK labor market; (iv) the latent gender wage gaps after correcting for selection bias are about 25%–50% of CFL (2023)’s estimates, and are also significantly smaller than the observed wage gaps; (v) similar to CFL (2023), there exists some strong evidence on gender discrimination in the UK labor market.

关键词：

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：