检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Sun, Qiang Zhuang, Yifeng Chen, Zhengqing Fu, Yanwei Xue, Xiangyang Academy for Engineering and Technology Fudan University China School of Computer Science Fudan University China School of Data Science Fudan University China

ISBN: (纸本)9781665438643

Visual Language Navigation (VLN) is the grand goal of AI, which enables the agent to act by the language instructions from humans. In VLN task, the agent learns to search for a specific region described by the instructions in the training environments, and performs the navigation in the unseen environments. Normally, there exists a large domain gap between the seen and unseen environments. Numerous works have been put on data augmentation and designing new loss in such a multi-task navigation setting. However, as a spatial and temporal searching task, a valuable signal source for the navigation - depth has not yet fully explored and thus been ignored in previous efforts. Typically, the current models lack the ability to capture the relative spatial directions to the grounding view. To address these issues, we propose an environment adaptive method based on a Depth-guided Adaptive Instance Normalization (DG-AdaIN) module to adjust the RGB features in term of the depth features, and develop a shift attention module to model the relative direct information in the attention map. Extensive experiments have validated the efficacy of our method on the benchmark dataset. © 2021 IEEE

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

S2AC: ENERGY-BASED REINFORCEMENT LEARNING WITH STEIN SOFT ACTOR CRITIC

arXiv

引用

arXiv 2024年

作者： Messaoud, Safa Mokeddem, Billel Xue, Zhenghai Pang, Linsey An, Bo Chen, Haipeng Chawla, Sanjay Qatar Computing Research Institute Hamad Bin Khalifa University Qatar School of Computer Science and Engineering Nanyang Technological University Singapore SalesForce Skywork AI Singapore Data Science William & Mary

Learning expressive stochastic policies instead of deterministic ones has been proposed to achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy Reinforcement Learning (MaxEnt RL), the policy is modeled as an expressive Energy-Based Model (EBM) over the Q-values. However, this formulation requires the estimation of the entropy of such EBMs, which is an open problem. To address this, previous MaxEnt RL methods either implicitly estimate the entropy, resulting in high computational complexity and variance (SQL), or follow a variational inference procedure that fits simplified actor distributions (e.g., Gaussian) for tractability (SAC). We propose Stein Soft Actor-Critic (S2AC), a MaxEnt RL algorithm that learns expressive policies without compromising efficiency. Specifically, S2AC uses parameterized Stein Variational Gradient Descent (SVGD) as the underlying policy. We derive a closed-form expression of the entropy of such policies. Our formula is computationally efficient and only depends on first-order derivatives and vector products. Empirical results show that S2AC yields more optimal solutions to the MaxEnt objective than SQL and SAC in the multi-goal environment, and outperforms SAC and SQL on the MuJoCo benchmark. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Characterizing and Detecting Gas-Inefficient Patterns in Smart Contracts

引用

Journal of computer science & Technology 2022年第1期37卷 67-82页

作者： Que-Ping Kong Zi-Yan Wang Yuan Huang Xiang-Ping Chen Xiao-Cong Zhou Zi-Bin Zheng Gang Huang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China School of Software Engineering Sun Yat-sen UniversityZhuhai 519082China Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Communication and DesignSun Yat-sen UniversityGuangzhou 510006China Peking University Shenzhen Graduate School Shenzhen 518000China

Ethereum blockchain is a new internetware with tens of millions of smart contracts running on *** from general programs,smart contracts are decentralized,tamper-resistant and permanently ***,to avoid resource abuse,Ethereum charges users for deploying and invoking smart contracts according to the size of contract and the operations executed by *** is necessary to optimize smart contracts to save ***,since developers are not familiar with the operating environment of smart contracts(i.e.,Ethereum virtual machine)or do not pay attention to resource consumption during development,there are many optimization opportunities for smart *** fill this gap,this paper defines six gas-inefficient patterns from more than 25,000 posts and proposes an optimization approach at the source code level to let users know clearly where the contract is *** evaluate the prevalence and economic benefits of gas-inefficient patterns,this paper conducts an empirical study on more than 160,000 real smart *** promising experimental results demonstrate that 52.75%of contracts contain at least one gas-inefficient pattern proposed in this *** these patterns are removed from the contract,at least 0.30 can be saved per contract.

关键词： smart contract anti-pattern detection optimization empirical study

来源：评论

学校读者我要写书评

暂无评论

A Smart Greenhouse Prototype with an Edge Computing Internet of Things (IoT) Unit

A Smart Greenhouse Prototype with an Edge Computing Internet...

引用

Electrical engineering (ICEENG), 12th International Conference on

作者： Mohamed Naeem Hesham H. Aly Computer Networks and Data Centre-Cairo Arab Academy for Science Technology and Maritime Transport Cairo Egypt Electronics and Communication Engineering Department Arab Academy for Science Technology and Maritime Transport Giza Egypt

ISBN: (数字)9798350343427

ISBN: (纸本)9798350343434

Agriculture gained great interest in the last decade due to high demands from international societies and organizations. World countries are threatened by upcoming fountains due to secrecy, diseases, climate change, and leakage of water resources. Greenhouses are the key factor in mitigating climate change's effect on agriculture. However, it has some challenges that require a smart system to control and manage it effectively. The most erotic issues are environmental parameters, infections, irrigation control, and fertilizer control. This paper proposes a smart greenhouse prototype utilizing the Internet of Things and edge computing to maximize productivity and minimize losses. The results proved the willingness of the proposed system to solve the related issues at a low cost.

关键词： Climate change Salinity (geophysical) Prototypes Greenhouses Soil Internet of Things Water resources

来源：评论

学校读者我要写书评

暂无评论

Proximal Oracles for Optimization and Sampling

arXiv

引用

arXiv 2024年

作者： Liang, Jiaming Chen, Yongxin Goergen Institute for Data Science Department of Computer Science University of Rochester RochesterNY14620 United States School of Aerospace Engineering Georgia Institute of Technology AtlantaGA30332 United States

We consider convex optimization with non-smooth objective function and log-concave sampling with non-smooth potential (negative log density). In particular, we study two specific settings where the convex objective/potential function is either semi-smooth or in composite form as the finite sum of semi-smooth components. To overcome the challenges caused by non-smoothness, our algorithms employ two powerful proximal frameworks in optimization and sampling: the proximal point framework for optimization and the alternating sampling framework (ASF) that uses Gibbs sampling on an augmented distribution. A key component of both optimization and sampling algorithms is the efficient implementation of the proximal map by the regularized cutting-plane method. We establish the iteration-complexity of the proximal map in both semi-smooth and composite settings. We further propose an adaptive proximal bundle method for non-smooth optimization. The proposed method is universal since it does not need any problem parameters as input. Additionally, we develop a proximal sampling oracle that resembles the proximal map in optimization and establish its complexity using a novel technique (a modified Gaussian integral). Finally, we combine this proximal sampling oracle and ASF to obtain a Markov chain Monte Carlo method with non-asymptotic complexity bounds for sampling in semi-smooth and composite settings. © 2024, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Dynamic convolution with complementary attention for image classification

Dynamic convolution with complementary attention for image c...

引用

2024 International Conference on computer Application and Information Security, ICCAIS 2024

作者： Zheng, Chusan Liu, Jingming Fan, Haoru Li, Yafeng Li, Jian Li, Ning Fan, Pan Sun, Jieqi School of Mathematics and Information Sciences Baoji University of Arts and Science Baoji721013 China Cigarette Factory Shaanxi Tobacco Industry Co. Ltd. Baoji721013 China Chengdu University of Technology Oxford Brookes College Chengdu610051 China School of Computer Baoji University of Arts and Science Baoji721016 China School of Electrical and Control Engineering School of Mathematics and Data Science Shaanxi University of Science and Technology Xi’an710016 China

ISBN: (纸本)9781510689312

Convolution is the fundamental unit of operation in convolutional neural networks. However, traditional static convolution is subject to two significant limitations: a weak ability to effectively integrate global and local features and a high computational overhead. This paper introduces an innovative and efficient approach, the Complementary Attention Dynamic Convolution (CADC), to tackle the limitations of traditional static convolution in convolutional neural networks. CADC comprises a three-part architecture: two branches of attention and a fusion module. The dynamic convolution kernels are generated by integrating the results of the two branches of attention, which are weighted and fused. CADC is correlated with the input samples, efficiently integrates global and local features, and generates convolution kernels specific to the spatial location and channel domain. Extensive experiments have been conducted on popular benchmark datasets, and the experimental results demonstrate that the CADC method exhibits excellent performance in terms of the number of model parameters, computational complexity, and classification accuracy. © The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

2021 2nd International Conference on Artificial Intelligence, computer Networks and Communications

引用

Journal of Physics: Conference Series 2022年第1期2146卷

作者： Wang, Tao Yang, Shuanghua School of Data Science and Computer Sun Yat-Sen University China Engineering College Southern University of Science and Technology China

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Transmitting RIS-Aided Receiver for Collaborative Jamming and Anti-Jamming Networks

引用

IEEE Transactions on Wireless Communications 2025年

作者： Li, Junjie Yang, Liang Hao, Wanming Ahmad, Ishtiaq Liu, Hongwu Shu, Feng Niyato, Dusit Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan University College of Computer Science and Electronic Engineering China Jishou University School of Communication and Electronic Engineering China Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China Czech Technical University in Prague Faculty of Electrical Engineering Department of Telecommunication Engineering Prague166 27 Czech Republic Shandong Jiaotong University School of Information Science and Electrical Engineering Jinan250357 China Hainan University School of Information and Communication Engineering Haikou570228 China Nanyang Technological University College of Computing and Data Science Singapore

In this paper, we propose a novel architecture for a multi-layer active-passive cascade transmitting reconfigurable intelligent surface (RIS)-aided receiver. We aim at enhancing the scalability of antenna dimensions and energy efficiency for user equipment (UE), as well as improving the amplitude freedom of antenna gain. This architecture integrates reflecting RIS for applications in both jamming and anti-jamming scenarios. We formulate a problem to maximize the worst-case spectral efficiency (SE) of the UE, based on imperfect channel state information (CSI) of the malicious device, thereby ensuring the SE of our UE while disrupting the signal reception of the illegal UE. To address the inherently non-convex nature of the formulated problem, we propose an alternating optimization framework, which decomposes the main problem into several subproblems. Specifically, we uniformly discretize the uncertain domains to obtain robust CSI, allowing us to determine an optimal receiver vector. To balance computational complexity and performance, we propose solutions for the subproblems of base station beamforming and coefficients with different patterns of RIS. Furthermore, to effectively disrupt malicious inter-device communication while avoiding detection and localization, we develop a collaborative interference pattern incorporating silent interference and non-interference protocols. Importantly, the pattern carefully balances performance with the overhead of CSI acquisition. Finally, simulation results validate the efficiency of the proposed algorithms, demonstrating that the proposed architecture achieves better jamming and anti-jamming performance. © 2002-2012 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

Using data Mining Techniques to Analyze Facial Expression Motion Vectors 6th

Using Data Mining Techniques to Analyze Facial Expression Mo...

引用

6th International Conference on Dynamics of Information Systems, DIS 2023

作者： Roshanzamir, Mohamad Alizadehsani, Roohallah Roshanzamir, Mahdi Shoeibi, Afshin Gorriz, Juan M. Khosravi, Abbas Nahavandi, Saeid Acharya, U. Rajendra Department of Computer Engineering Faculty of Engineering Fasa University Fasa74617-81189 Iran Deakin University GeelongVIC Australia Department of Electrical and Computer Engineering University of Tabriz Tabriz Iran Data Science and Computational Intelligence Institute University of Granada Granada Spain Department of Signal Theory Networking and Communications Universidad de Granada Granada Spain Swinburne University of Technology HawthornVIC3122 Australia School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia

ISBN: (纸本)9783031503191

Automatic recognition of facial expressions is a common problem in human-computer interaction. While humans can recognize facial expressions very easily, machines cannot do it as easily as humans. Analyzing facial changes during facial expressions is one of the methods used for this purpose by the machines. In this research, facial deformation caused by facial expressions is considered for automatic facial expression recognition by machines. To achieve this goal, the motion vectors of facial deformations are captured during facial expression using an optical flow algorithm. These motion vectors are then used to analyze facial expressions using some data mining algorithms. This analysis not only determined how changes in the face occur during facial expressions but can also be used for facial expression recognition. The facial expressions investigated in this research are happiness, sadness, surprise, fear, anger, and disgust. According to our research, these facial expressions were classified into 12 classes of facial motion vectors. We applied our proposed analysis mechanism to the extended Cohen-Kanade facial expression dataset. Our developed automatic facial expression system achieved 95.3%, 92.8%, and 90.2% accuracy using Deep Learning (DL), Support Vector Machine (SVM), and C5.0 classifiers, respectively. In addition, based on this research, it was determined which parts of the face have a greater impact on facial expression recognition. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

data Hybrid Attacks Based on Sensitive Users in Recommender Systems

Data Hybrid Attacks Based on Sensitive Users in Recommender ...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Hongwei Zhou Min Gao Meiling Chao Yuqi Song Qingyu Xiong Junhao Wen Yi Zhang Big Data and Software Engineering Chongqing University Chongqing China Computer Science and Engineering University of South Carolina Columbia SC USA

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

Recommender systems, which make precise recommendations through historical interaction data of users and items, have been widely used in real life. But at the same time, because of the open nature of the systems, they are vulnerable to malicious attacks. To explore the robustness of recommender systems, researchers have proposed various attack methods and analyzed their adverse effects. Although the current attack methods can make good results on rating-based recommender systems, they lack thinking about an attack for a social recommendation. Social relationships have a non-negligible role in recommender systems, but there is still little related research, which only constructs fake rating profiles and fake relationship profiles with simple rules, without considering the mutual influence of rating and social information. To address the above problem, we study the attack method with deeply hidden features and propose a hybrid attack method based on sensitive users. It can further enhance the hidden features of fake users, and then use social attacks to assist in attacking social recommendation methods. Empirical results on three public datasets show that our method outperforms traditional methods in terms of attack effectiveness and has excellent anti-detection capability. Ultimately, we hope that our method could enable more analysis for such a hybrid attack and guides for investigating effective prevention measures.

关键词： Deep learning Robustness Artificial intelligence Recommender systems

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：