检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Tong Wei Zhen Mao Zi-Hao Zhou Yuanyu Wan Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China School of Software Technology Zhejiang University Ningbo China

Long-tail learning primarily focuses on mitigating the label distribution shift between longtailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing longtail learning approaches, consistently improving their performance. The source code is available at https://***/Stomach-ache/label-shift-correction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Blockchain-Based Access Control Scheme with Attribute Update

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Zuo, Yuting Xu, Li Li, Jiguo Li, Jie Wang, Xiaoding Piran, Md. Jalil Fujian Normal University College of Computer and Cyber Security Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou350117 China Lab Shanghai200240 China Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of

Secure data access control is widely concerned in Cyber Physical Systems (CPSs) to protect consumer rights. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) is an ideal solution that supports fine-grained access control. It is a pity that they fail to consider the attribute control and the verifiable legitimacy when consumer's attributes are updated. Additionally, the existing revocable CP-ABE schemes are unsuitable for resource-constrained consumer electronic devices due to their high computational and storage overhead. This paper proposes a blockchain-based access control scheme with attribute update. A new revocation mechanism is designed to guarantee the forward/backward security of the attribute update. The lightweight ciphertext update protocol is proposed to optimize the computation cost. To realize secure and efficient attribute management, this paper designs the on-chain/off-chain separation storage mode, and proposes the traceability-based attribute set generation and validation algorithm. This paper performs the formal security proof. The experimental results demonstrate that the scheme is efficient in terms of encryption and decryption. © 1975-2011 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Expert with Outlier Exposure for Continual Learning of New Diseases

Expert with Outlier Exposure for Continual Learning of New D...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Xu, Zhengjing Chen, Kanghao Zheng, Wei-Shi Tan, Zhijun Yang, Xiaobo Wang, Ruixuan Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE China State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou China Peng Cheng Laboratory Department of Network Intelligence Shenzhen China

ISBN: (纸本)9781665468190

Current intelligent diagnosis systems struggle to continually learn to diagnose more and more diseases due to catastrophic forgetting of old knowledge when learning new knowledge. Although storing small old data for subsequent continual learning can effectively help alleviate the forgetting issue, the heavy data imbalance between old classes and to-be-learned new classes in classifier training often causes biased prediction towards the new classes just learned by the updated classifier. In this study, an outlier detection technique is novelly applied to train an additional expert classifier for new classes to help alleviate the class imbalance issue and discriminate the learned new classes from old classes during inference (instead of the training phase). Specially, the stored small data of old classes are considered as outliers during training the expert classifier, such that the output probability distributions from the expert classifier are expected to be obviously different between test data of the old classes and those of the new classes. Such difference between old classes and new classes can be used to fine-tune the original output from the updated classifier which is responsible for prediction of all learned (old and new) classes. During inference, a novel ensemble strategy is proposed to combine the predictions from the updated classifier, the expert classifier, and the previously learned old classifier. The proposed learning and inference framework can be easily combined with existing continual learning strategies. Empirical evaluations on three medical image datasets and one natural image dataset show that the proposed framework can effectively improve continual learning performance. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhanced Vgg16 for Medical Image Zero Watermarking: Integrating Attention, Skip Connections, Depth-Separated Convolution, and Dual-Logistic Encryption

SSRN

引用

SSRN 2024年

作者： Li, Jingyou Rongle, Wei Xi, Xiaotian Zhang, Guangda Yang, Zixin Zhang, Fengshan 1. School of Computer and Control Engineering Qiqihar University 2. Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar University

The paper proposes an enhanced VGG16 network((referred to as DS-ResVGG16 with CBAM)) that incorporates the attention mechanism CBAM, skip connections, and depth-separable convolution to solve the medical image content protection problem. The three innovative improvements of the enhanced VGG16 network are reflected in the following: first, replacing the regular convolution with depth-separable convolution substantially improves the computational efficiency and parameter utilization of the network;second, the introduction of the CBAM after the 2nd, 3rd, 4th, and 5th max-pooling layers further strengthens the network's capability to recognize and respond to crucial features.;and lastly, by adding a skip connection after the 2nd, 3rd, and 4th CBAM modules followed by the addition of skip connections, the transfer and integration of features were enhanced, improving the learning ability and generalization of the model. The improved network extracts Deep features from the original medical images, and binary feature vectors are generated using the mean hash algorithm. To further strengthen content protection security, this study innovatively adopts an encryption technique based on dual-logistics mapping and Joseph's ring for high-strength encryption of watermarks. During the generation of the zero watermark, the encrypted watermark and the feature vectors of the medical image are subjected to an iso-orthogonal operation, which ensures the concealment and security of the embedding. The validity and reasonableness of the modules and locations added by the scheme are verified and compared through experiments. The experimental results show that the scheme is robust enough to handle typical and geometric attacks. The medical image content protection problem is realized. © 2024, 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

Scheduling Model of Scenic Tour Task Based on Heuristic Intelligent Search Algorithm

Scheduling Model of Scenic Tour Task Based on Heuristic Inte...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Hongbo Wang Rong Fei Zilong Wang Aimin Li Yajun Liu Fuyu Zhu School of Computer Science and Engineering Xi'an University of Technology Xi’an China Shannxi Key Laboratory for Network Computing and Security Technology Xi'an University of Technology Xi’an China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

This paper constructs a scenic tour task scheduling model (hereinafter referred to as the model) based on heuristic intelligent search algorithm, puts forward the heuristic intelligent search solution scheme under single-task and multi-task scenarios, aims to unify the planning of tour routes according to the scenic spot flow situation, prevents the formation of attraction passenger flow peaks, and can effectively solve the problem of the traditional scheduling model's dynamic scheduling ability lack. In particular, the performance of different scheduling algorithms is compared and simulation tests are designed to verify that the proposed model and solution method are effective for solving the optimal path problem of scenic tour, which is of practical significance for realizing the intelligent management of scenic spots and promoting the intelligent development of tourism.

关键词： Scheduling algorithms Heuristic algorithms Dynamic scheduling Search problems Multitasking Planning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

RDGFuzz: A directed greybox fuzzing optimization method based on Rich-Branch nodes 22

RDGFuzz: A directed greybox fuzzing optimization method base...

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and computer engineering

作者： Zejun Wu Li Lu Qiong Jia Zhihao Chen State Key Laboratory of Mathematical Engineering and advanced Computing China National Local Joint Engineering Laboratory of Network Space Security Technology China Beijing Institute of Computer Technology and Application China

ISBN: (纸本)9781450397148

Directed fuzzing technology is one of the key technologies to quickly reach a specific location of software, and to conduct targeted testing or bug recurrence. However, directed fuzzing technology has some problems, such as unreasonable seed energy allocation, low code coverage and incomplete testing. To solve the above problems, this paper proposes an optimization method of directed fuzzing based on Rich-Branch nodes. In this method, the concept of Rich-Branch nodes is defined and the algorithm of extracting Rich-Branch nodes is given. The optimization method collects the coverage information of the target program in the running process, calculates the weights of covered functions and nodes in real time by combining CG and CFG of the target program, and generates a list of Rich-Branch nodes. According to the weights of Rich-Branch nodes, the seed energy allocation algorithm of AFLGo is optimized and improved. Compared with AFLGo, this optimization method improves the average code coverage of each targeted point by 56.79%, and has the same target reaching ability as AFLGo.

关键词： Rich-Branch nodes Directed fuzzing Code coverage rate Vulnerability discovery

来源：评论

学校读者我要写书评

暂无评论

Zero Watermarking Algorithms for Medical Images Based on Cnn and Transformer with Dual-Branch network

SSRN

引用

SSRN 2024年

作者： Li, Jingyou Wei, Rongle Xi, Xiaotian Zhang, Guangda Yang, Zixin Zhang, Fengshan 1. School of Computer and Control Engineering Qiqihar University 2. Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar University

The current research proposes a new zero-watermarking approach that aims to protect medical images from tampering by utilizing the power of deep learning. In this paper, we construct an innovative dual-branch network to capture subtle features of pictures and use them efficiently. First, one of the branches of the dual-branch network is to analyze the local details of the medical images by an enhanced convolutional neural network (specifically the Skip-connected VGG16, i.e., Res-VGG16). In contrast, the other branch employs the state-of-the-art Swin transformer v2 structure to parse the global context of the medical images. Second, adding a spatial transform network and a Gaussian filter as preprocessing before the two-branch network can further overcome the low robustness of medical images to geometric and noise attacks. Thirdly, we use a feature fusion method with a maximum voting mechanism to merge the features extracted from the two-branch network. We generate feature vectors of medical images using the DCT method and achieve watermark encryption by utilizing logistic mapping and a hash function. Finally, we generate a zero watermark by applying logical operations to the encrypted watermark and the medical image feature vectors. The implementation results show that the algorithm can effectively overcome the tampering problem of medical images and can recover the original data from the encrypted watermark with good robustness under conventional and geometric attacks. © 2024, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Causal Prompting: Debiasing Large Language Model Prompting Based on Front-Door Adjustment 39

Causal Prompting: Debiasing Large Language Model Prompting B...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Congzhi Zhang, Linhai Wu, Jialong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)157735897X

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases. Traditional debiasing methods primarily focus on the model training stage, including approaches based on data augmentation and reweighting, yet they struggle with the complex biases inherent in LLMs. To address such limitations, the causal relationship behind the prompting methods is uncovered using a structural causal model, and a novel causal prompting method based on front-door adjustment is proposed to effectively mitigate LLMs biases. In specific, causal intervention is achieved by designing the prompts without accessing the parameters and logits of LLMs. The chain-of-thought generated by LLM is employed as the mediator variable and the causal effect between input prompts and output answers is calculated through front-door adjustment to mitigate model biases. Moreover, to accurately represent the chain-of-thoughts and estimate the causal effects, contrastive learning is used to fine-tune the encoder of chain-of-thought by aligning its space with that of the LLM. Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets on both open-source and closed-source LLMs. © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Natural Human Skin‑Inspired Wearable and Breathable Nanofiber‑based Sensors with Excellent Thermal Management Functionality

引用

Advanced Fiber Materials 2024年第6期6卷 1955-1968页

作者： Peng Wang Xiaodan Li Guifen Sun Guoqing Wang Qing Han Chuizhou Meng Zhonghe Wei Yang Li School of Mechanical Engineering University of JinanJinan 250022China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China State Key Laboratory for Reliability and Intelligence of Electrical Equipment Engineering Research Center of Ministry of Education for Intelligent Rehabilitation Device and Detection TechnologyHebei Key Laboratory of Smart Sensing and Human‑Robot InteractionSchool of Mechanical EngineeringHebei University of TechnologyTianjin 300401China Shandong Provincial Key Laboratory of Network‑Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinan 250022China Network Information Center Department of Computer ScienceQilu University of Technology(Shandong Academy of Sciences)Jinan 250353China School of Integrated Circuits Shandong UniversityJinan 250101China

Wearable sensors have been rapidly developed for application in various human monitoring ***,the wearing comfort and thermal properties of these devices have been largely ignored,and these characteristics urgently need to be ***,we develop a wearable and breathable nanofiber-based sensor with excellent thermal management functionality based on passive heat preservation and active Joule heating *** multifunctional device consists of a micropatterned carbon nanotube(CNT)/thermoplastic polyurethane(TPU)nanofiber electrode,a microporous ionic aerogel electrolyte and a microstructured Ag/TPU nanofiber *** to the presence of a supercapacitive sensing mechanism and the appli-cation of microstructuration,the sensor shows excellent sensing performance,with a sensitivity of 24.62 ***,due to the overall porous structure and hydrophobicity of TPU,the sensor shows good breathability(62 mm/s)and water repellency,with a water contact angle of 151.2°.In addition,effective passive heat preservation is achieved by combining CNTs with high solar absorption rates(85%)as the top layer facing the outside,aerogel with a low thermal conductivity(0.063 W m-1 k-1)as the middle layer for thermal insulation,and Ag with a high infrared reflectance rate as the bottom layer facing the *** warming,this material yields a higher temperature than ***,the active Joule heat-ing effect is realized by applying current through the bottom resistive electrode,which can quickly increase the temperature to supply controlled warming on *** proposed wearable and breathable sensor with tunable thermal properties is promising for monitoring and heat therapy applications in cold environments.

关键词： Wearable sensor Breathable Personal thermal management Electrospun nanofibers Joule heating

来源：评论

学校读者我要写书评

暂无评论

MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading 39

MTGA: Multi-View Temporal Granularity Aligned Aggregation fo...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Wenhao Wang, Jun Luo, Yong Yu, Lei Yu, Wei He, Zheng Shen, Jialie School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Electronics and Information Wuhan University China Department of Computer Science City University of London United Kingdom

ISBN: (纸本)157735897X

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

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：