检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Zhaoliang Wu, Zhihao Sadikaj, Ylli Plant, Claudia Dai, Hong-Ning Wang, Shiping Cheung, Yiu-Ming Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Department of Computer Science Hong Kong Baptist University Hong Kong Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science and with the research network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention in the literature. Among the existing GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges. Consequently, the effectiveness of message passing is weakened. In this paper, we propose a novel adversarial edgedropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on eight graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Learning Approach 12

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Le...

引用

12th International Conference on Smart Grid, icSmartGrid 2024

作者： Oyucu, Saadin Sagiroglu, Seref Aksoz, Ahmet Bicer, Emre Faculty of Engineering Department of Computer Engineering Adiyaman Turkey Gazi University Artificial Intelligence and Big Data Analytics Security R&d Center Ankara Turkey Sivas Cumhuriyet University Mobilers Team Sivas Turkey Sivas University of Science and Technology Faculty of Engineering and Natural Sciences Battery Research Laboratory Sivas Turkey

ISBN: (纸本)9798350361612

Smart grids are faced with a range of challenges, such as the development of communication infrastructure, cybersecurity threats, data privacy, and the protection of user information, due to their complex structure. Another key challenge faced by smart grids is the stability issues arising from variable energy sources and consumption patterns. In these complex grid systems where energy demand and supply need to be balanced instantly, stability predictions play a significant role in foreseeing potential disruptions and optimizing energy flow. Therefore, within the scope of this study, a hybrid structure utilizing Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks is employed for stability classification to predict grid stability. This hybrid model combines the ability of RNN to recognize relationships between consecutive data points with LSTM's capability to preserve long-term dependencies. The results obtained indicate that the model exhibited stable performance with accuracy rates of 98.06% and 98.02% at 50 and 100 epochs, respectively. The findings of this study contribute valuable insights to research on the management and stability of smart grids, enabling energy systems to be operated more reliably and efficiently. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Multilayer perceptron ensembles in a truly sparse training context

引用

Neural Computing and Applications 2025年

作者： van der Wal, Peter R. D. Strisciuglio, Nicola Azzopardi, George Mocanu, Decebal Constatin Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Data Management and Biometrics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 19 Enschede7522 NH Netherlands Department of Computer Science Faculty of Science Technology and Medicine University of Luxembourg Maison du Nombre 6 avenue de la Fonte Esch4364 Luxembourg

Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization. © The Author(s) 2025.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Approach to Security Games with Signaling 31

Evolutionary Approach to Security Games with Signaling

引用

31st International Joint Conference on Artificial Intelligence, IJCAI 2022

作者： Żychowski, Adam Mańdziuk, Jacek Bondi, Elizabeth Venugopal, Aravind Tambe, Milind Ravindran, Balaraman Faculty of Mathematics and Information Science Warsaw University of Technology Poland Center for Research on Computation and Society Harvard University United States Robert Bosch Centre for Data Science and AI IIT Madras India Department of Computer Science and Engineering IIT Madras India

ISBN: (纸本)9781956792003

Green Security Games have become a popular way to model scenarios involving the protection of natural resources, such as wildlife. Sensors (e.g. drones equipped with cameras) have also begun to play a role in these scenarios by providing real-time information. Incorporating both human and sensor defender resources strategically is the subject of recent work on Security Games with Signaling (SGS). However, current methods to solve SGS do not scale well in terms of time or memory. We therefore propose a novel approach to SGS, which, for the first time in this domain, employs an Evolutionary Computation paradigm: EASGS. EASGS effectively searches the huge SGS solution space via suitable solution encoding in a chromosome and a specially-designed set of operators. The operators include three types of mutations, each focusing on a particular aspect of the SGS solution, optimized crossover and a local coverage improvement scheme (a memetic aspect of EASGS). We also introduce a new set of benchmark games, based on dense or locally-dense graphs that reflect real-world SGS settings. In the majority of 342 test game instances, EASGS outperforms state-of-the-art methods, including a reinforcement learning method, in terms of time scalability, nearly constant memory utilization, and quality of the returned defender's strategies (expected payoffs). © 2022 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

Sparse graph counting and Kelley–Meka bounds for binary systems

arXiv

引用

arXiv 2023年

作者： Filmus, Yuval Hatami, Hamed Hosseini, Kaave Kelman, Esty The Henry & Marilyn Taub Faculty of Computer Science Faculty of Mathematics Technion School of Computer Science McGill University Canada Department of Computer Science University of Rochester United States Department of Computer Science Department of Computing & Data Sciences Boston University CSAIL Massachusetts Institute of Technology United States

In a recent breakthrough, Kelley and Meka (FOCS 2023) obtained a strong upper bound on the density of sets of integers without non-trivial three-term arithmetic progressions. In this work, we extend their result, establishing similar bounds for all linear patterns defined by binary systems of linear forms, where "binary" indicates that every linear form depends on exactly two variables. Prior to our work, no strong bounds were known for such systems even in the finite field model setting. A key ingredient in our proof is a graph counting lemma. The classical graph counting lemma, developed by Thomason (Random Graphs 1985) and Chung, Graham, and Wilson (Combinatorica 1989), is a fundamental tool in combinatorics. For a fixed graph H, it states that the number of copies of H in a pseudorandom graph G is similar to the number of copies of H in a purely random graph with the same edge density as G. However, this lemma is only non-trivial when G is a dense graph. In this work, we prove a graph counting lemma that is also effective when G is sparse. Moreover, our lemma is well-suited for density increment arguments in additive number theory. As an immediate application, we obtain a strong bound for the Turán problem in abelian Cayley sum graphs: let Γ be a finite abelian group with odd order. If a Cayley sum graph on Γ does not contain any r-clique as a subgraph, it must have at most 2−Ωr(log1/16 |Γ|) · |Γ|2 edges. These results hinge on the technology developed by Kelley and Meka and the follow-up work by Kelley, Lovett, and Meka (STOC 2024). © 2023, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Optimization of Feature Selection to Improve Order Transaction Performance in the Manufacturing Industry

Optimization of Feature Selection to Improve Order Transacti...

引用

International Conference on Electrical Engineering, computer science and Informatics (EECSI)

作者： Ery Hartati Deris Stiawan Wijang Widhiarso Faculty of Engineering Universitas MDP Faculty of Engineering Universitas Sriwijaya Palembang Palembang Indonesia Computer Engineering Department Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Computer Engineering Department Faculty of Computer Science Universitas Multi Data Palembang Palembang Indonesia

The development of business processes that occur in Industry 4.0 requires the optimization of processes in the system, especially in the process of order transactions. To optimize the transaction process, the assistance of the rank and weight system on dataset features, called the feature selection process, can be employed. Feature selection aims to improve the elimination of redundant and irrelevant features, which can reduce computation time and improve accuracy. In this research using multivariate datasets. Feature selection is used to eliminate some attributes that are irrelevant to the label class, resulting in improved performance of the classification algorithm. The author compares three algorithms: information gain, ratio gain, and chi-square. These are algorithms to find the rank and weight of data. In this research to measure feature selection performance using the Naïve Bayes classifier algorithm. The evaluation is performed by observing the level of classification accuracy generated without feature selection versus the classification accuracy generated after the implementation of feature selection. The experimental results showed that 14 features were included in the selection of features, and four relevant and best features were produced using the Chi-square binary classification algorithm. Classification using naïve Bayes algorithm reached 97.56%, while using ratio gain and information gain resulted in classification values of 75.57% and 92.69%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pyramid Scene Parsing Net Model for Automated Paddy Field Map using SPOT 6 Satellite Images 5

Pyramid Scene Parsing Net Model for Automated Paddy Field Ma...

引用

5th IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology, AGERS 2022

作者： Heryadi, Yaya Irwansyah, Edy Miranda, Eka Soeparno, Haryono Herlawati Hashimoto, Kiyota Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Faculty of Technology and Environment Phuket83120 Thailand

ISBN: (纸本)9798350398212

Food sustainability is still one of the main priorities for many countries as it contributes to the economy and stability of the nation. For government in many countries whose peoples consumes rice as its staple food, food self-sufficiency initiatives highly depend on accurate prediction of paddy field map. Mapping paddy field task is a challenging problem which cannot be handled manually especially when the paddy fields are spread out in very wide geographical areas such as those in Indonesia. Fortunately, wide availability of satellite imagery and the advent of deep learning technology in the past ten years have made it possible to improve efficiency of most parts of those manual works involving image semantic segmentation tasks. However, satellite image-based semantic segmentation is a challenging task. High object complexity, cloud partial occlusion, larger image size than a computer memory can stored can hinder accuracy of the image segmentation results. This paper presents a method for paddy field map generating using semantic image segmentation approach in which Pyramid Scene Parsing Net model is used for segmenting satellite imagery. The generated paddy map can be used as a basis for decision-making, especially in the agricultural sector. Analysis of local land use/land cover dynamics. The results of his experiments using SPOT 6 satellite imagery from the Pahung region of Central Kalimantan achieved average training accuracy, best training accuracy and test accuracy of 0.85, 0.86 and 0.89 respectively. These results indicated that the semantic segmentation model is suitable for addressing the same task in different crops. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language Models

arXiv

引用

arXiv 2024年

作者： Villena, Fabián Miranda, Luis Aracena, Claudio Department of Computer Science University of Chile Chile Millennium Institute for Foundational Research on Data Chile Department of Computer Science Catholic University of Chile Chile Faculty of Physical and Mathematical Sciences University of Chile Chile

Large language models (LLMs) allow us to generate high-quality human-like text. One interesting task in natural language processing (NLP) is named entity recognition (NER), which seeks to detect mentions of relevant information in documents. This paper presents llmNER, a Python library for implementing zero-shot and few-shot NER with LLMs;by providing an easy-to-use interface, llmNER can compose prompts, query the model, and parse the completion returned by the LLM. Also, the library enables the user to perform prompt engineering efficiently by providing a simple interface to test multiple variables. We validated our software on two NER tasks to show the library’s flexibility. llmNER aims to push the boundaries of in-context learning research by removing the barrier of the prompting and parsing steps. © 2024, CC BY-NC-ND.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Note on a New Construction of Kantorovich Form q-Bernstein Operators Related to Shape Parameter λ

引用

computer Modeling in Engineering & sciences 2022年第3期130卷 1479-1493页

作者： Qingbo Cai Resat Aslan Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information ProcessingSchool of Mathematics and Computer ScienceQuanzhou Normal UniversityQuanzhou362000China Department of Mathematics Faculty of Sciences and ArtsHarran UniversitySanlıurfa63300Turkey

The main purpose of this paper is to introduce some approximation properties of a Kantorovich kind q-Bernstein operators related to B′ezier basis functions with shape parameterλ∈[−1,1].Firstly,we compute some basic results such as moments and central moments,and derive the Korovkin type approximation theorem for these ***,we estimate the order of convergence in terms of the usual modulus of continuity,for the functions belong to Lipschitz-type class and Peetre’s K-functional,***,with the aid of Maple software,we present the comparison of the convergence of these newly defined operators to the certain function with some graphical illustrations and error estimation table.

关键词： q-calculus (λ,q)-Bernstein polynomials order of convergence Lipschitz-type function Peetre’s K-functional

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Information Transmission in Sensory Neuromorphic Circuit Networks 6

Design and Analysis of Information Transmission in Sensory N...

引用

6th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Su, Jing He, Huaguang Peng, Kangbai Chen, Ni City University of Macau Faculty of Data Science Macao SAR Macao China Guangxi Medical University College of Information and Management Nanning China Guangxi University College of Computer and Electronic Information Nanning China Guangxi Medical University Life Sciences Institute Nanning China

ISBN: (纸本)9798350316520

To elucidate the information transmission characteristics of a sensory neuromorphic circuit network, a feedforward circuit network comprising 20 nodes was established using previously proposed neuromorphic circuits as nodes. The average number of emitted pulses and the transmission delay time at each node were used to measure the information transmission. Simulations were conducted under both direct current (DC) and alternating current (AC) input conditions. The findings indicate that pulses emitted under DC and AC inputs could be transmitted in each network node, and the transmission delay time was inversely proportional to the intensity of the input signal, as well as the width and amplitude of the driving pulse. Fluctuations were observed in the average number of pulses during transmission under DC input, whereas a gradual decrease was observed under AC input. These research results provide a basis for developing artificial sensory systems based on neuromorphic circuits. © 2024 IEEE.

关键词： Timing circuits

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：