检索结果-内蒙古大学图书馆

8th International Conference on Engineering of computer-Based Systems, ECBS 2023

作者： Herrera, Francisco Department Computer Sciences and Artificial Intelligence Andalusian Research Institute on Data Science and Computational Intelligence University of Granada Granada Spain

ISBN: (纸本)9783031492518

This short paper associated to the invited lectures introduces two key concepts essential to artificial intelligence (AI), the area of trustworthy AI and the concept of responsible AI systems, fundamental to understand the technological, ethical and legal context of the current framework of debate and regulation of AI. The aim is to understand their dimension and their interrelation with the rest of the elements involved in the regulation and auditability of AI algorithms in order to achieve safe and trusted AI. We highlight concepts in bold in order to fix the moment when they are described in context. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Deep learning at the service of metaheuristics for solving numerical optimization problems

引用

Neural Computing and Applications 2025年 1-36页

作者： Oyelade, Olaide N. Ezugwu, Absalom E. Saha, Apu K. Thieu, Nguyen V. Gandomi, Amir H. School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Bangladesh Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 United States Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Faculty of Computer Science Phenikaa University Yen Nghia Hanoi Ha Dong12116 Viet Nam Department of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Integrating deep learning methods into metaheuristic algorithms has gained attention for addressing design-related issues and enhancing performance. The primary objective is to improve solution quality and convergence speed within solution search spaces. This study investigates the use of deep learning methods as a generative model to learn historical content, including global best and worst solutions, solution sequences, function evaluation patterns, solution space characteristics, population modification trajectories, and movement between local and global search processes. An LSTM-based architecture is trained on dynamic optimization data collected during the metaheuristic optimization process. The trained model generates an initial solution space and is integrated into the optimization algorithms to intelligently monitor the search process during exploration and exploitation phases. The proposed deep learning-based methods are evaluated on 55 benchmark functions of varying complexities, including CEC 2017 and compared with 13 biology-based, evolution-based, and swarm-based metaheuristic algorithms. Experimental results demonstrate that all the deep learning-based optimization algorithms achieve high-quality solutions, faster convergence rates, and significant performance improvements. These findings highlight the critical role of deep learning in addressing design issues, enhancing solution quality, trajectory, and performance speed in metaheuristic algorithms. © The Author(s) 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Classification on High- Dimensional data Using Swarm Optimization Algorithms 7

Feature Selection for Classification on High- Dimensional Da...

引用

7th IEEE International Conference on Computational Systems and Information Technology for Sustainable Solutions, CSITSS 2023

作者： Pradeep Kumar, D. Bj, Sowmya Kanavalli, Anitha Deeptashree, D. Ramaiah Institute of Technology Department of Computer Science and Engineering Bangalore India Ramaiah Institute of Technology Department of Artificial Intelligence and Data Science Bangalore India

ISBN: (纸本)9798350343144

Feature selection plays a crucial role in classification by identifying relevant features. Bio-inspired algorithms, such as genetic algorithms, particle swarm optimization, and ant colony optimization, have gained popularity due to their ability to mimic natural processes and explore high-dimensional feature spaces efficiently. The analysis includes evaluating classification accuracy, and computational efficiency as performance metrics. The experimental setup involves dataset selection, choosing a classification algorithm, implementing bio-inspired feature selection, evaluation, parameter tuning, and comparative analysis. The findings provide valuable insights into the effectiveness and efficiency of bio-inspired algorithms for feature selection in classification. The project focuses on reducing high- dimensional datasets to low-dimensional ones using feature selection through classification with swarm optimization algorithms. It aims to validate the effectiveness of the Jellyfish Search algorithm (JSA), Horse Herd Optimization algorithm (HOA), and Binary Bat algorithm (BBA) on real-world datasets. The objectives include evaluating the algorithms' performance, conducting a comprehensive performance analysis, execution of classifiers like RF, DT, KNN, Voting Classifier and SVM, obtaining and tuning the results, and publishing the findings. The research outcomes contribute to the knowledge of feature selection for classification and provide guidance in selecting appropriate algorithms for specific classification tasks. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

FedDAD: Federated Domain Adaptation for Object Detection

引用

IEEE Access 2023年 11卷 51320-51330页

作者： Lu, Peggy Joy Jui, Chia-Yung Chuang, Jen-Hui National Yang Ming Chiao Tung University Department of Computer Science Hsinchu30010 Taiwan National Center for High-Performance Computing Data Science and Technology Division Taichung40763 Taiwan

Training an object detection model often requires numerous annotated images on a centralized host, which may violate user privacy and data confidentiality. Federated learning (FL) resolves this issue by allowing multiple clients, e.g., cameras, to collaboratively train a model while protecting user privacy. However, models trained with FL may fail to be generalized for new target domain due to domain shift when the data between source and target domains are statistically different. In this work, we formulate a real-world object detection problem as a source-free multi-domain adaptation problem in FL architecture. Moreover, we propose an adaptive FL algorithm, called FedDAD (Federated Domain Adaptive Detector), which aggregates models with dynamic attention targeting the unsupervised domain on server, and utilize instance-level alignment to alleviate the effects of scene variation on clients. Experimental results show that FedDAD improves the average precision (AP) by up to 10.05% and 19.15% compared to the popular FedAvg for specific object classes in the KAIST and MI3 datasets, respectively. © 2013 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Robust and Space-Efficient Dual Adversary Quantum Query Algorithms 31

Robust and Space-Efficient Dual Adversary Quantum Query Algo...

引用

31st Annual European Symposium on Algorithms, ESA 2023

作者： Czekanski, Michael Kimmel, Shelby Witter, R. Teal Department of Statistics and Data Science Cornell University IthacaNY United States Department of Computer Science Middlebury College VT United States Department of Computer Science and Engineering New York University BrooklynNY United States

ISBN: (纸本)9783959772952

The general adversary dual is a powerful tool in quantum computing because it gives a query-optimal bounded-error quantum algorithm for deciding any Boolean function. Unfortunately, the algorithm uses linear qubits in the worst case, and only works if the constraints of the general adversary dual are exactly satisfied. The challenge of improving the algorithm is that it is brittle to arbitrarily small errors since it relies on a reflection over a span of vectors. We overcome this challenge and build a robust dual adversary algorithm that can handle approximately satisfied constraints. As one application of our robust algorithm, we prove that for any Boolean function with polynomially many 1-valued inputs (or in fact a slightly weaker condition) there is a query-optimal algorithm that uses logarithmic qubits. As another application, we prove that numerically derived, approximate solutions to the general adversary dual give a bounded-error quantum algorithm under certain conditions. Further, we show that these conditions empirically hold with reasonable iterations for Boolean functions with small domains. We also develop several tools that may be of independent interest, including a robust approximate spectral gap lemma, a method to compress a general adversary dual solution using the Johnson-Lindenstrauss lemma, and open-source code to find solutions to the general adversary dual. © Michael Czekanski, Shelby Kimmel, and R. Teal Witter;licensed under Creative Commons License CC-BY 4.0.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

Spectral Normalized-Cut Graph Partitioning with Fairness Constraints 26

Spectral Normalized-Cut Graph Partitioning with Fairness Con...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Li, Jia Wang, Yanhao Merchant, Arpit School of Data Science and Engineering East China Normal University Shanghai China Department of Computer Science University of Helsinki Helsinki Finland

ISBN: (纸本)9781643684369

Normalized-cut graph partitioning aims to divide the set of nodes in a graph into k disjoint clusters to minimize the fraction of the total edges between any cluster and all other clusters. In this paper, we consider a fair variant of the partitioning problem wherein nodes are characterized by a categorical sensitive attribute (e.g., gender or race) indicating membership to different demographic groups. Our goal is to ensure that each group is approximately proportionally represented in each cluster while minimizing the normalized cut value. To resolve this problem, we propose a two-phase spectral algorithm called FNM. In the first phase, we add an augmented Lagrangian term based on our fairness criteria to the objective function for obtaining a fairer spectral node embedding. Then, in the second phase, we design a rounding scheme to produce k clusters from the fair embedding that effectively trades off fairness and partition quality. Through comprehensive experiments on nine benchmark datasets, we demonstrate the superior performance of FNM compared with three baseline methods. © 2023 The Authors.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

I/O Steganography for Audio and Images in Secure data Transmission 3

I/O Steganography for Audio and Images in Secure Data Transm...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Jebakumar Immanuel, D. Prakash, A. Mugundhan, M. Keerthivasan, U. Uma Makesan, A. Karpagam Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Sns College of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350322842

There are several uses for information concealing today. The use of data hiding knowledge may be morally or immorally acceptable. data hiding methods, however, are difficult to classify into either the steganography or the watermarking categories because there is no clear distinction between these two concepts, and classification mostly depends on algorithmic application. Hence, regardless of how data concealing is classified, the most popular data hiding applications include copyright protection, covert communication, safe storage, and fingerprinting. Messages are altered by cryptography so they can't be understood. Secured data, varied size keys for data concealment, and quick and flexible ease of design are some of cryptography's main benefits. The biggest drawback of cryptography is that it is not suitable for the internet and is only compatible with devices like mobile phones, has complicated hardware, and uses unusual cypher patterns. Steganography is a centuries-old technique for obscuring data. In this essay, a survey of current audio steganography research is presented. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Joint Communication and Synchronization Performance Optimization in Digital Twin Enabled Networks

Joint Communication and Synchronization Performance Optimiza...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Yu, Hanzhi Liu, Yuchen Chen, Mingzhe University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral GablesFL33146 United States North Carolina State University Department of Computer Science RaleighNC27695 United States

ISBN: (纸本)9798350351255

In this paper, we investigate an accurate synchronization between a physical network and its digital network twin (DNT) that is a virtual representation of the physical network. The considered network includes a physical network where a base station (BS) serves a set of users, and a DNT that evolves with the status of both DNT and the physical network. The BS must use its limited spectrum resources to serve the users, as well as transmit the physical network information to the cloud server for DNT synchronization. Since the DNT can predict the physical network status, the BS may not need to transmit physical network information to the server at each time slot thus saving spectrum resources to serve users. However, if the BS does not transmit physical information to the DNT over a long period of time, the DNT may not be able to represent the physical network accurately. To this end, the BS must determine whether to send physical network information to the server to update DNT and the spectrum resources used for physical network information transmission and serving users. We formulate this resources allocation problem as an optimization problem aiming to maximize the sum of data rates of all users, while minimizing the gap between the states of the physical network and the DNT. The formulated problem is challenging to solve by conventional optimization methods, since the BS may not be able to know the future status of the DNT. To solve this problem, we design a gate recurrent unit (GRU) and soft action-critic (SAC) based algorithm. The GRU enables the DNT to predict its future states by using historical state data, and updating the DNT when the BS does not transmit physical network information. The SAC based algorithm enables the BS to learn the relationship between the physical network information transmission and the future status estimation accuracy of the DNT thus determining whether to transmit physical network information to the cloud server, ensuring an accurac

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Tree-Structure Enhanced Transformer for Cardinality Estimation

A Tree-Structure Enhanced Transformer for Cardinality Estima...

引用

2024 International Conference on Machine Learning and Intelligent Computing, MLIC 2024

作者： Hu, Mingjie Zhang, Qihang Ren, Jing Liu, Hengzhu Department of Intelligent Data Science National University of Defense Technology China College of Computer National University of Defense Technology China

Accurate cardinality estimation is crucial for query optimization by guiding plan selection. Traditional cardinality estimation approaches often fail to provide precise estimates, leading to suboptimal query plans. In recent years, learning-based methods have emerged as a promising alternative. For tree-based learning methods, a conventional way to simply encode nearby parent-child pairs and learn by iteratively training hampers the performance. But it leads to a significant loss of structural information and incurs substantial computational overhead by the iterative training process. In this paper, we proposed a tree-structure positional encoding scheme. It can not only extract effective features for each node, but also capture the inherent structural characteristics of the tree. Based on the tree-based feature, we designed a novel transformer-based cardinality estimation model, which enhances the parallelism of the model training process and reduces the overhead caused by iterative training. On real-world datasets, our method beats the current state-of-the-art techniques, QF, by 25% in terms of mean qerror. © 2024 M. Hu, Q. Zhang, J. Ren & H. Liu.

关键词： Cardinality estimation Positional Encoding Tree Transformer

来源：评论

学校读者我要写书评

暂无评论

ResPho(SC)Net: A Zero-Shot Learning Framework for Norwegian Handwritten Word Image Recognition 11th

ResPho(SC)Net: A Zero-Shot Learning Framework for Norwegian...

引用

11th Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2023

作者： Gurav, Aniket Jensen, Joakim Krishnan, Narayanan C. Chanda, Sukalpa Department of Computer Science and Communication Østfold University College Halden1757 Norway Department of Data Science Indian Institute of Technology Palakkad Kerala India

ISBN: (纸本)9783031366154

Recent advances in deep Convolutional Neural Networks (CNNs) have established them as a premier technique for a wide range of classification tasks, including object recognition, object detection, image segmentation, face recognition, and medical image analysis. However, a significant drawback of utilizing CNNs is the requirement for a large amount of annotated data, which may not be feasible in the context of historical document analysis. In light of this, we present a novel CNN-based architecture ResPho(SC)Net, to recognize handwritten word images in a zero-shot learning framework. Our method proposes a modified version of the Phosc(Net) architecture with a much lesser number of trainable parameters. Experiments were conducted on word images from two languages (Norwegian and English) and encouraging results were obtained. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Optical character recognition

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：