检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Zizheng Chen, Chen Chen, Hsin-Hung Liu, Xiang Hu, Yuchen Chng, Eng Siong School of Software and Microelectronics Peking University China School of Computer Science and Engineering Nanyang Technological University Singapore School of Electrical and Computer Engineering Georgia Institute of Technology United States

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background noise to each speaker. In this paper, we propose a noise-aware SS (NASS) method, which aims to improve the speech quality for separated signals under noisy conditions. Specifically, NASS views background noise as an additional output and predicts it along with other speakers in a mask-based manner. To effectively denoise, we introduce patch-wise contrastive learning (PCL) between noise and speaker representations from the decoder input and encoder output. PCL loss aims to minimize the mutual information between predicted noise and other speakers at multiple-patch level to suppress the noise information in separated signals. Experimental results show that NASS achieves 1 to 2dB SI-SNRi or SDRi over DPRNN and Sepformer on WHAM! and LibriMix noisy datasets, with less than 0.1M parameter increase. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Poisoning Actuation Attacks Against the Learning of an Optimal Controller

Poisoning Actuation Attacks Against the Learning of an Optim...

引用

American Control Conference (ACC)

作者： Filippos Fotiadis Aris Kanellopoulos Kyriakos G. Vamvoudakis Jérôme Hugues Daniel Guggenheim School of Aerospace Engineering Georgia Institute of Technology Atlanta GA USA Division of Information Science and Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Carnegie Mellon University/Software Engineering Institute Pittsburgh PA USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

In this paper, we study the problem of poisoning the learning of an optimal controller by means of an actuation attack. We specifically consider a user who is gathering data from a linear system in the form of input and state measurements, and who uses these data to learn an optimal controller. Nevertheless, these measurements are corrupted by an attacker who has access to the system's actuators, and who is using them to launch an actuation attack during the learning process. We design this actuation attack so that it optimally corrupts the data used by the user: it forces the user to learn as closely as possible a gain that the attacker has selected, and which is unrelated to the actual optimal control gain. We prove that this poisoning actuation attack design boils down to the solution of certain coupled matrix equations, which we solve using the block successive over-relaxation (SOR) iterative procedure. Simulations on an aircraft model demonstrate theoretical findings, showing how the poisoning attack is effective in misleading the user towards learning an incorrect gain for the system.

关键词： Linear systems Actuators Atmospheric modeling Optimal control Mathematical models Iterative methods Aircraft

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

BMRMIA:A Platform for Radiologists to Systematically Learn Automated Medical Image Analysis by Three Dimensional Medical Decision Support System

引用

computer Modeling in engineering & Sciences 2022年第5期131卷 851-863页

作者： Yankun Cao Lina Xu Zhi Liu Xiaoyan Xiao Mingyu Wang Qin Li Hongji Xu Geng Yang School of Software Shandong UniversityJinan250101China School of Information Science and Engineering Shandong UniversityQingdao266237China School of Computer Science and Technology Shandong Jianzhu UniversityJinan250012China Department of Nephrology Qilu Hospital of Shandong UniversityJinan250012China State Key Laboratory of ASIC&Systems The School of MicroelectronicsFudan UniversityShanghai200433China Shenzhen Institute of Information Technology Shenzhen518172China

Contribution:This paper designs a learning and training platform that can systematically help radiologists learn automated medical image analysis *** platform can help radiologists master deep learning theories and medical applications such as the three-dimensional medical decision support system,and strengthen the teaching practice of deep learning related courses in hospitals,so as to help doctors better understand deep learning knowledge and improve the efficiency of auxiliary ***:In recent years,deep learning has been widely used in academia,industry,*** increasing number of companies are starting to recruit a large number of professionals in the field of deep *** numbers of colleges and universities also offer courses related to deep learning to help radiologists learn automated medical image analysis *** now,however,there is no practical training platform that can help radiologists learn automated medical image analysis ***:The platform proposes the basic learning,model combat,business application(BMR)concept,including the learning guidance system and the assessment training system,which constitutes a closed-loop learning guidance mode of“learning-assessment-training-learning”.Findings:The survey results show that most of radiologists met their learning expectations by using this *** platform can help radiologists master deep learning techniques quickly,comprehensively and firmly.

关键词： BMR deep learning three dimensional medical decision support system deep learning engineer standard

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks for Image Classification 2

Convolutional Neural Networks for Image Classification

引用

2nd International Conference on Artificial Intelligence and computer engineering, ICAICE 2021

作者： Hao, Yiju School of Computer Science and Software Engineering Rose-Hulman Institute of Technology Terre Haute United States

ISBN: (纸本)9781665421867

computer Vision is a popular research area even though it is considered a simple concept. Over the past decades, a series of significant studies are conducted in this direction, for example, PCA, LDA, LBDA, etc. CNN model has been widely and effectively applied in various classification tasks such as image classification and text classification. It can be categorized into engineering and science since our goal is to make computer vision serve as a counter part of a human's vision system. Not only to make it look at the world like we do, but also to adapt to the environment. Image classification as a key concept in computer vision has plenty of applications that have a huge impact on human lives. Due to the fact that image classification is based on deep learning, it can process data without manual selections or designs. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Byzantine-Robust Federated Learning Based on the Multi-Message Shuffle Protocol for Consumer Internet of Things

引用

IEEE Internet of Things Journal 2025年

作者： Jin, Chunhua Li, Lulu Wang, Jiahao Li, Jinbiao Liu, Junyi Chen, Guanhua Zhang, Hao Weng, Jian Faculty of Computer Software Engineering with Huaiyin Institute of Technology Huai’an China Huaiyin Institute of Technology Faculty of Computer Software Engineering Huai’an China Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China Jinan University College of Information Science and Technology China

The accelerated advancement of consumer Internet of Things (CIoT) devices has resulted in their pervasive integration into the fabric of contemporary lifestyles. As these devices are capable of collecting vast quantities of data pertaining to users, they present a significant risk to the privacy and security of individuals. Federated learning is an advanced machine learning paradigm that prioritises the preservation of user data privacy and enhances security by eliminating the need for centralised data collection. As a result, it is a promising approach to address user data privacy and security concerns. However, federated learning still faces challenges such as privacy attacks, Byzantine attacks and high communication overheads. To address these challenges, we propose an efficient Byzantine-robust federated learning method based on multi-message shuffle protocol. To achieve privacy protection and Byzantine robustness, we introduce an innovative aggregation strategy inspired by the multi-message shuffle protocol for differential privacy. To improve communication efficiency, we develop an adaptive gradient compression scheme. Theoretical analysis indicates that our multi-message shuffle protocol is capable of satisfying the requisite differential privacy conditions. Compared with the state-of-the-art methods, our proposed scheme demonstrates superior convergence capabilities on the real-world dataset when approximately 40% of participants are Byzantine, achieving accuracies of 96.78%, which illustrates its strong robustness. Upon reduction of the transmitted model parameters to 1% of the original size, the proposed scheme exhibits a maximum accuracy degradation of 0.35%. which significantly reduces the communication overhead while achieving high accuracy. In addition, the scheme also achieves an accuracy of 88.73% on the Non-iid MotionSense dataset, which is superior to other schemes. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Progressive Self-Guided Hardness Distillation for Fine-Grained Visual Classification

Progressive Self-Guided Hardness Distillation for Fine-Grain...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yangdi Wang Wenming Guo Su Xiu Xu ShuoZhi Yuan School of Management and Economics Beijing Institute of Technology Beijing China School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Fine-grained visual classification (FGVC) is a challenging problem due to its inherently high intra-class variances and low inter-class variances. Recently, vision transformers (ViTs) have demonstrated their powerful performance in both traditional and FGVC cases. However, compared with most categories, some categories are difficult to classify because of their similar characteristics and postures and their strong background interference, impacting the performance improvement achieved by the utilizd model. In this work, we present a novel method named progressive self-guided hardness distillation (PS-GHD), which defines a classification hardness judgement criterion and utilizes different approaches for the corresponding categories according to this criterion. This method gradually and correctly classifies various categories in three stages through knowledge distillation, so it can correctly classify indistinguishable categories to some extent. We demonstrate the value of PS-GHD by experimenting on four popular fine-grained benchmarks: CUB-200-2011, Nabirds, Stanford Cars, and Stanford Dogs. Our method achieves very competitive results on the four datasets. We also present qualitative results to enhance the interpretability of our model.

关键词： Visualization computer vision Smoothing methods Neural networks Interference Dogs Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence: A Promising Prospect for Better Management of Diabetic Patients 5

Artificial Intelligence: A Promising Prospect for Better Man...

引用

5th IEEE International Conference on Artificial Intelligence and Big Data, ICAIBD 2022

作者： Hossin, Md Altab Islam, Md Safiqul Hassan, Sani Abubakar Ukwuoma, Chiagoziem Chima Nuri, Most. Miftahul Jannat Siddiquee, Md. Tofael Alam Chengdu University School of Innovation and Entrepreneurship Chengdu China Thakurgaon Polytechnic Institute Department of Computer Technology Thakurgaon Bangladesh University of Electronic Science and Technology of China School of Electronics Science and Engineering Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Hajee Mohammad Danesh Science and Technology University Department of Electronic and Communication Engineering Dinajpur Bangladesh Mymensingh Polytechnic Institute Department of Computer Science and Engineering Mymensingh Bangladesh

ISBN: (纸本)9781665499132

Diabetic as an incurable chronic disease is increasing rapidly over time, and its impacts on other diseases are also striking. Indeed, science and technology have drastically developed, and it is also in the healthcare section. Getting diabetes education to help self-management is essential to help patients enhance their metabolic control and quality of life. Using artificial intelligence (AI) technologies, we can make significant progress in transforming available genetic data and clinical information into valuable knowledge. In disease education, given its potential benefits in encouraging individualization and full-course education intervention, AI would be extremely advantageous based on the unique situations of different individuals. The use of AI in different facets of diabetes education was explored based on collected data. © 2022 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Distinguishability-based genuine nonlocality with genuine multipartite entanglement

引用

Physical Review A 2023年第2期108卷 022405-022405页

作者： Zong-Xing Xiong Mao-Sheng Li Zhu-Jun Zheng Lvzhou Li Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-Sen University Guangzhou 510006 China School of Mathematics South China University of Technology Guangzhou 510641 China

A set of orthogonal multipartite quantum states is said to be distinguishability-based genuinely nonlocal (also genuinely nonlocal, for abbreviation) if the states are locally indistinguishable across any bipartition of the subsystems. This form of multipartite nonlocality, although more naturally arising than the recently popular “strong nonlocality” in the context of local distinguishability, receives much less attention. In this work, we study the distinguishability-based genuine nonlocality of a typical type of genuine multipartite entangled states—the d-dimensional Greenberger-Horne-Zeilinger (GHZ) states, featuring systems with local dimension not limited to two. In the three-partite case, we find the existence of small genuinely nonlocal sets consisting of these states: we show that the cardinality can at least scale down to linear in the local dimension d, with the linear factor l=1. Specifically, the method we use is semidefinite programming and the GHZ states to construct these sets are special ones which we call “GHZ lattices”. This result might arguably suggest a significant gap between the strength of strong nonlocality and the distinguishability-based genuine nonlocality. Moreover, we put forward the notion of (s,n)-threshold distinguishability and, utilizing a similar method, we successfully construct (2,3)-threshold sets consisting of GHZ states in three-partite systems.

关键词： Nonlocality Quantum correlations in quantum information Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Explainable-AI-based two-stage solution for WSN object localization using zero-touch mobile transceivers

引用

Science China(Information Sciences) 2024年第7期67卷 27-45页

作者： Kai FANG Junxin CHEN Han ZHU Thippa Reddy GADEKALLU Xiaoping WU Wei WANG School of Mathematics and Computer Science Zhejiang A&F University School of Software Dalian University of Technology Faculty of Applied Sciences Macao Polytechnic University Department of Electrical and Computer Engineering Lebanese American University School of Information Engineering Huzhou University Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University

Artificial intelligence technology is widely used in the field of wireless sensor networks(WSN).Due to its inexplicability, the interference factors in the process of WSN object localization cannot be effectively eliminated. In this paper, an explainable-AI-based two-stage solution is proposed for WSN object localization. In this solution, mobile transceivers are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable,and the localization problem is highly nonlinear with respect to the unknown parameters. To address this,an explainable AI model is proposed to solve the localization problem. Since the relationship among the variables is difficult to fully include in the first-stage traditional model, we develop a two-stage explainable AI solution for this localization problem. The two-stage solution is actually a comprehensive consideration of the relationship between variables. The solution can continue to use the constraints unused in the firststage during the second-stage, thereby improving the performance of the solution. Therefore, the two-stage solution has stronger robustness compared to the closed-form solution. Experimental results show that the performance of both the two-stage solution and the traditional solution will be affected by numerical changes in unknown parameters. However, the two-stage solution performs better than the traditional solution, especially with a small number of mobile transceivers and sensors or in the presence of high noise. Furthermore,we have also verified the feasibility of the proposed explainable-AI-based two-stage solution.

关键词： explainable AI object localization semidefinite relaxation mobile transceiver two-stage solution closed-form solution

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：