检索结果-内蒙古大学图书馆

2024 7th International Conference on computer Information science and Artificial Intelligence, CISAI 2024

作者： Wu, Jiawei Liang, Shuaishuai Feng, Huibin College of Computer and Data Science Fuzhou University Fujian Fuzhou China School of Computer and Big Data Minjiang University Fujian Fuzhou China

ISBN: (纸本)9798400707254

The development of the aerospace technology enables countries around the world to launch a large number of satellites to carry out extraterrestrial missions. This also poses greater challenges to the control of satellites. The extremely long communication time between satellites and the ground has led to the necessity of autonomous onboard control capability for satellites. The rise of reinforcement learning (RL) technology has driven research on applying RL technology to satellite control problems. This paper attempts to apply the Distributed Soft Actor Critic with Three Improvements (DSAC-T) algorithm to the adaptive continuous control problem of satellite attitude. The problem is described as a reinforcement learning model that controls the satellite to perform a large-angle slew maneuvers and maintain a desired orientation. By setting up rotation experiments, the results show that the DSAC-T algorithm can control satellite to perform rotation tasks more quickly and smoothly than existing continuous control algorithms. © 2024 Copyright held by the owner/author(s).

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generalized Learning of Coefficients in Spectral Graph Convolutional Networks 15

Generalized Learning of Coefficients in Spectral Graph Convo...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Coskun, Mustafa Grama, Ananth Koyuturk, Mehmet Ankara University Department of Ai and Data Engineering Ankara Turkey Purdue University Department of Computer Science IN United States Case Western University Department of Data and Computer Science OH United States

ISBN: (纸本)9798331508821

Spectral Graph Convolutional Networks (GCNs) have gained popularity in graph machine learning applications due, in part, to their flexibility in specification of network propagation rules. These propagation rules are often constructed as polynomial filters whose coefficients are learned using label information during training. In contrast to learned polynomial filters, explicit filter functions are useful in capturing relationships between network topology and distribution of labels across the network. A number of algorithms incorporating either approach have been proposed;however the relationship between filter functions and polynomial approximations is not fully resolved. This is largely due to the ill-conditioned nature of the linear systems that must be solved to derive polynomial approximations of filter functions. To address this challenge, we propose a novel Arnoldi orthonormalization-based algorithm, along with a unifying approach, called G-Arnoldi-GCN that can efficiently and effectively approximate a given filter function with a polynomial. We evaluate G-Arnoldi-GCN in the context of multi-class node classification across ten datasets with diverse topological characteristics. Our experiments show that G-Arnoldi-GCN consistently outperforms state-of-the-art methods when suitable filter functions are employed. Overall, G-Arnoldi-GCN opens important new directions in graph machine learning by enabling the explicit design and application of diverse filter functions. Code link: https://***/mustafaCoskunAgu/GArnoldi-GCN © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

dTEE: A Declarative Approach to Secure IoT Applications Using TrustZone 23

dTEE: A Declarative Approach to Secure IoT Applications Usin...

引用

23rd ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2024

作者： Sun, Tong Li, Borui Teng, Yixiao Gao, Yi Dong, Wei Zhejiang University The State Key Laboratory of Blockchain and Data Security College of Computer Science China Southeast University School of Computer Science and Engineering China

ISBN: (纸本)9798350362015

Internet of Things (IoT) applications have recently been widely used in safety-critical scenarios. To prevent sensitive information leaks, IoT device vendors provide hardware-assisted protections, called Trusted Execution Environments (TEEs), like ARM Trust-Zone. Programming a TEE-based application requires separate code for two components, significantly slowing down the development process. Existing solutions tackle this issue by automatic code partition while not successfully applying it in two complicated scenarios: adding trusted logic and interactions with secure *** propose dTEE, a declarative approach to secure IoT applications based on TrustZone. dTEE proposes a rapid approach that enables developers to declare tiered-sensitive variables and functions of existing applications. Besides, dTEE automatically transforms device drivers into trusted ones. We evaluate dTEE on four real-world IoT applications and seven micro-benchmarks. Results show that dTEE achieves high expressiveness for supporting 50% more applications than existing approaches and reduces 90% of the lines of code against handcrafted development. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Distortion risk measures for tail-risk multicriteria decision-making based on a probabilistic linguistic environment

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8389-8409页

作者： Chen, Jie Yin, Chuancun School of Statistics and Data Science Qufu Normal University Qufu China School of Mathematics and Computer Applied Technology Jining University Qufu China

Probabilistic linguistic term sets (PLTSs) provide a flexible tool to express linguistic preferences, and several multi-criteria decision models based on PLTSs have been recently developed. In this framework, distortion risk measures are extensively used in finance and insurance applications, but are rarely applied in fuzzy systems. In this paper, distortion risk measures are applied to fuzzy tail decisions. In particular, three tail risk measurement methods are put forward, referred to as probabilistic linguistic VaR (PLVaR), expected probability linguistic VaR (EPLVaR), and Wang tail risk measure and extensively study their properties. Our novel methods help to clarify the connections between distortion risk measure and fuzzy tail decision-making. In particular, the Wang tail risk measure is characterized by consistency and stability of decision results. The criteria and expert weights are unknown or only partially known during the decision making process, and the maximising PLTSs deviations are showed how to determine them. The theoretical results are showcased on an optimal stock fund selection problem, where the three tail risk measures are compared and analyzed. © 2024 - IOS Press. All rights reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

REVISITING ROBUSTNESS IN GRAPH MACHINE LEARNING 11

REVISITING ROBUSTNESS IN GRAPH MACHINE LEARNING

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Gosch, Lukas Sturm, Daniel Geisler, Simon Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: i) for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption;ii) surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Geometric prior guided hybrid deep neural network for facial beauty analysis

引用

CAAI Transactions on Intelligence Technology 2024年第2期9卷 467-480页

作者： Tianhao Peng Mu Li Fangmei Chen Yong Xu David Zhang The School of Computer Science and Technology Guizhou UniversityGuiyangChina Department of Automation Moutai InstituteRenhuaiGuizhouChina The School of Computer Science and Technology Harbin Institute of TechnologyShenzhenShenzhenChina The Information and Communication Engineering Department Dalian Minzu UniversityDalianChina The School of Data Science The Chinese University of Hong KongShenzhenShenzhenChina

Facial beauty analysis is an important topic in human *** may be used as a guidance for face beautification applications such as cosmetic *** neural networks(DNNs)have recently been adopted for facial beauty analysis and have achieved remarkable ***,most existing DNN-based models regard facial beauty analysis as a normal classification *** ignore important prior knowledge in traditional machine learning models which illustrate the significant contribution of the geometric features in facial beauty *** be specific,landmarks of the whole face and facial organs are introduced to extract geometric features to make the *** by this,we introduce a novel dual-branch network for facial beauty analysis:one branch takes the Swin Transformer as the backbone to model the full face and global patterns,and another branch focuses on the masked facial organs with the residual network to model the local patterns of certain facial ***,the designed multi-scale feature fusion module can further facilitate our network to learn complementary semantic information between the two *** model optimisation,we propose a hybrid loss function,where especially geometric regulation is introduced by regressing the facial landmarks and it can force the extracted features to convey facial geometric *** performed on the SCUT-FBP5500 dataset and the SCUT-FBP dataset demonstrate that our model outperforms the state-of-the-art convolutional neural networks models,which proves the effectiveness of the proposed geometric regularisation and dual-branch structure with the hybrid *** the best of our knowledge,this is the first study to introduce a Vision Transformer into the facial beauty analysis task.

关键词： deep neural networks face analysis face biometrics image analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal trained ensemble of classification model for satellite image classification

引用

Multimedia Tools and Applications 2025年第7期84卷 3745-3766页

作者： Singh, Sarabjeet Kundra, Harish Kundra, Sheetal Pratima, P. Venkata Devi, M. V. Anjana Kumar, Sushil Hassan, Mariya Department of Computer Science and Engineering Chandigarh College of Engineering and Technology Chandigarh160019 India Department of Computer Science and Engineering Guru Nanak Institutions Technical Campus Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Artificial Intelligence and Data Science Guru Nanak Institute of Technology Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Computer Science and Engineering Central University of Haryana Jant-Pali Mahendergarh123031 India

Satellite image classification is the most significant remote sensing method for computerized analysis and pattern detection of satellite data. This method relies on the image's diversity structures and necessitates a thorough validation of the training data using the chosen classification algorithm. The classifying of remotely sensed images refers to the process of classifying pixels into a fixed set of distinct classes based on their data values. The pixel is categorized into that class if it complies with a specific set of requirements. A new SIC scheme is suggested in this work, where, Contrast limited adaptive histogram equalization (CLAHE) is deployed for pre-processing the image. Further, statistical features, Vegetation Indices (VI) and Improved Hybrid Vegetation Index (IHVI) are extracted from the preprocessed image. Then, we deploy 2 phase classification process for classifying the image. In the first phase, Bi-Directional Gated Recurrent Unit (BI-GRU), Convolutional Neural Network (CNN) and Deep Max Out (DMO) are used. In 2nd phase, optimized RNN is used for determining the final classification result. Also, the training of the model is done by the new Chaotic Opposition Behavior Improvised Coot Algorithm (COBI-CA) optimization via tuning the optimal weights. The COOT method has been enhanced and is now the suggested algorithm. Lastly, we conduct an analysis to compare the suggested Satellite Image Classification (SIC) model's performance to the traditional approaches in terms of statistical analysis, precision, accuracy, and error measure. In comparison to other conventional methods, the accuracy of the suggested model is 97%. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

SAMPLING-FREE INFERENCE FOR AB-INITIO POTENTIAL ENERGY SURFACE NETWORKS 11

SAMPLING-FREE INFERENCE FOR AB-INITIO POTENTIAL ENERGY SURFA...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Gao, Nicholas Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Recently, it has been shown that neural networks not only approximate the ground-state wave functions of a single molecular system well but can also generalize to multiple geometries. While such generalization significantly speeds up training, each energy evaluation still requires Monte Carlo integration which limits the evaluation to a few geometries. In this work, we address the inference shortcomings by proposing the Potential learning from ab-initio Networks (PlaNet) framework, in which we simultaneously train a surrogate model in addition to the neural wave function. At inference time, the surrogate avoids expensive Monte-Carlo integration by directly estimating the energy, accelerating the process from hours to milliseconds. In this way, we can accurately model high-resolution multi-dimensional energy surfaces for larger systems that previously were unobtainable via neural wave functions. Finally, we explore an additional inductive bias by introducing physically-motivated restricted neural wave function models. We implement such a function with several additional improvements in the new PESNet++ model. In our experimental evaluation, PlaNet accelerates inference by 7 orders of magnitude for larger molecules like ethanol while preserving accuracy. Compared to previous energy surface networks, PESNet++ reduces energy errors by up to 74 %. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Wave functions

来源：评论

学校读者我要写书评

暂无评论

Language Identification System: Employing ReLu for India's Regional Languages (ReLu) 2

Language Identification System: Employing ReLu for India's R...

引用

2nd International Conference for Advancement in Technology, ICONAT 2023

作者： Saini, Lekhraj Defence Institute of Advanced Technology School of Computer Science and Data Science Pune India

ISBN: (纸本)9781665475174

In this paper, I provide a model for language identification that makes use of neural networks. The approach is intended to distinguish between Indian regional and dialectal languages. Individuals of Indian descent are the target population for this model. I train the model using a variety of data sources, including corpora of written and spoken material in a variety of languages. In addition, I use a variety of additional data sources. As a result, we can train the model to be more accurate. When I compare the performance of our model to that of a naive Bayes classifier, I find that the results produced by our model are superior to those produced by the naive Bayes classifier. This is because our model considers more information than the naïve Bayes classifier. The ReLu activation function is employed on each neuron throughout our simulation, and the neural network design comprises several layers. Each neuron receives the ReLu activation function. This allows the model to capture the relationships and correlations that exist between the input data, which improves its capacity to recognize the language employed in a specific sentence. Furthermore, our technology can deal with ambiguous cases, such as sentences written in the devnagri script, which is utilized in a number of Indian languages. This is a benefit provided by our software. Using our system has several advantages, and this is only one of them. © 2023 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

SEGMENT+: Long Text Processing with Short-Context Language Models

SEGMENT+: Long Text Processing with Short-Context Language M...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Shi, Wei Li, Shuang Yu, Kerun Chen, Jinglei Liang, Zujie Wu, Xinhui Qian, Yuxi Wei, Feng Zheng, Bo Liang, Jiaqing Chen, Jiangjie Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Columbia University United States MYbank Ant Group China School of Data Science Fudan University China

ISBN: (纸本)9798891761643

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks, such as understanding extensive documents and extracting detailed information from lengthy and noisy data. In response, we introduce SEGMENT+, a general framework that enables LMs to handle extended inputs within limited context windows efficiently. SEGMENT+ utilizes structured notes and a filtering module to manage information flow, resulting in a system that is both controllable and interpretable. Our extensive experiments across various model sizes, focusing on long-document question-answering and Needle-in-a-Haystack tasks, demonstrate the effectiveness of SEGMENT+ in improving performance. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：