检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qing Liu Qian Gao Jun Fan Zhiqiang Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Ltd Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN— a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model’s effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets.

关键词： Measurement Bridges Contrastive learning Signal processing data processing Vectors Space exploration Resource management Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Impact of AI and Machine Learning on data Access Optimization

Quantifying the Impact of AI and Machine Learning on Data Ac...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Khandari, Harsimrat Sahoo, Girija Shankar Tr, Mahesh Rajeswari, M. Jadhav, Prranjali Meena, Mansingh Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka 562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India

ISBN: (纸本)9798350329773

Quantifying the impact of synthetic Intelligence (AI) and machine getting to know (ML) on information access Optimization (DAO) and its ability to enhance overall performance and performance inside organizations has been a topic of research for decades. This newsletter investigates how such technology is essential in optimizing records access and its effect on the rate and accuracy of operations. We speak about how cutting-edge advances in AI and ML can be utilized to detect patterns in facts, reduce latency, and improve the general quality of data. Furthermore, we discuss how that technology can reduce manual techniques and get rid of errors due to human mistakes, hence enhancing performance and productiveness. Sooner or later, we talk about the main challenges associated with enforcing AI and ML within a company and identify capacity areas of development. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Competitive Facility Location under Cross-Nested Logit Customer Choice Model: Hardness and Exact Approaches

arXiv

引用

arXiv 2024年

作者： Le, Ba Luat Mai, Tien Ta, Thuy Anh Ha, Minh Hoang Vu, Duc Minh ORLab Faculty of Computer Science Phenikaa University Hanoi Ha Dong Viet Nam School of Computing and Information Systems Singapore Management University 80 Stamford Rd Singapore178902 Singapore Faculty of Data Science and Artificial Intelligence NEU College of Technology Hai Ba Trung Hanoi Viet Nam ORLab-SLSCM National Economics University Hai Ba Trung Hanoi Viet Nam

We study the competitive facility location problem, where a firm aims to establish opening facilities in a market already occupied by competitors. In this problem, customer behavior is a crucial factor in making optimal location decisions. We explore a general class of customer choice models, known as the cross-nested logit model, which is recognized for its flexibility and generality in predicting people’s choice behavior. To explore the problem, we first demonstrate that it is NP-Hard, even when there is only one customer class. We further show that this hardness result is tight, as the facility location problem under any simpler choice models (such as the logit or nested logit) is polynomial-time solvable when there is one customer class. To tackle the resulting facility location problem, we demonstrate that the objective function under a general cross-nested structure is not concave. Interestingly, we show that by a change of variables, the objective function can be converted to a convex program (i.e., a maximization problem with a concave objective and convex constraints), enabling it to be solved to optimality via an outer-approximation algorithm. Extensive experiments show the efficiency of our approach and provide analyses on the benefits of using the cross-nested model in the facility location context. Copyright © 2024, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Enhancing Coarse-Grained and Fine-Grained Image-Text Retrieval Models via Multi-Scale Modal Distance Learning

Enhancing Coarse-Grained and Fine-Grained Image-Text Retriev...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Kaili Zhou Yushui Geng Jing Zhao Yiyun Xing Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

The current image-text cross-modal retrieval faces challenges due to the heterogeneous nature of different modalities. This paper proposes an improved model based on multi-scale modal distance learning to enhance the performance of coarse-grained and fine-grained image-text matching. In the image encoding part, an improved ResNet architecture is adopted, utilizing upsampling techniques to better preserve key semantic information. For text encoding, BERT and Bi-LSTM models are combined to extract shallow and deep textual features, respectively. We design a coarse-fine granularity interaction mechanism, leveraging a bidirectional stacked Transformer to achieve local similarity interaction between image regions and text words, while also using Bi-LSTM-extracted contextual features to interact with global image features for global similarity matching. Additionally, this paper introduces a novel multi-scale modal contrastive loss, which dynamically adjusts the distance between samples of different modalities, thereby improving the model's sensitivity to semantic similarity. Experimental results on the COCO 5K and Flickr30K datasets demonstrate that the proposed method outperforms existing mainstream methods in both retrieval accuracy and efficiency, achieving complementary advantages between coarse- and fine-grained features. This provides an effective solution and new research direction for cross-modal retrieval.

关键词： computer aided instruction Image coding Accuracy Sensitivity Semantics Bidirectional control Feature extraction Transformers Encoding Cross modal retrieval

来源：评论

学校读者我要写书评

暂无评论

Comparison of IDS in IoT, Mobile and Cloud based Systems

Comparison of IDS in IoT, Mobile and Cloud based Systems

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Görkem Gök Aytuğ Boyacı Mustafa Ulaş Department of Software Engineering Faculty of Technology Fırat University Elazığ Türkiye Department of Computer Engineering Air Force Academy National Defence University İstanbul Türkiye Department of Artificial Intelligence and Data Science Engineering Faculty Of Engineering Fırat University Elazığ Türkiye

ISBN: (数字)9798350330366

ISBN: (纸本)9798350330373

This study is meant to research the evolution of intrusion detection and network monitoring within computer, cloud-based systems, IIoT, and mobile environments. The source has outlined the novel technologies in IDS, from “Fast Learning Network” to hybrid classifiers aiming at protecting cloud computing. The findings highlight innovation IDS technologies that provide flexible and peculiar solutions to ward off potential cyber threats. In addition, it presented with the use of Nagios, NConf, the state of the art in network traffic monitoring, and deep learning as tools for advanced management and network protection. Besides, the research also reviewed concepts of Big data Analytics and Federated Learning in bettering direct integration and anomaly detection in IIoT. A good comparison of the two would show that recent technological advancements are much needed for network efficiency and its cybersecurity. Based on the findings, the scope of networked system security develops dynamically amid current challenges.

关键词： Deep learning Performance evaluation Cloud computing Technological innovation Federated learning computer hacking Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Acceleration of FM-index Queries Through Prefix-free Parsing

arXiv

引用

arXiv 2023年

作者： Hong, Aaron Oliva, Marco Köppl, Dominik Bannai, Hideo Boucher, Christina Gagie, Travis Department of Computer and Information Science and Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Institut für Informatik der Univeristät Münster Münster48149 Germany M&D Data Science Center Tokyo Medical and Dental University Tokyo Japan Faculty of Computer Science Dalhousie University HalifaxNS Canada

FM-indexes are a crucial data structure in DNA alignment, for example, but searching with them usually takes at least one random access per character in the query pattern. Ferragina and Fischer [5] observed in 2007 that word-based indexes often use fewer random accesses than character-based indexes, and thus support faster searches. Since DNA lacks natural word-boundaries, however, it is necessary to parse it somehow before applying word-based FM-indexing. Last year, Deng et al. [3] proposed parsing genomic data by induced suffix sorting, and showed the resulting word-based FM-indexes support faster counting queries than standard FM-indexes when patterns are a few thousand characters or longer. In this paper we show that using prefix-free parsing-which takes parameters that let us tune the average length of the phrases-instead of induced suffix sorting, gives a significant speedup for patterns of only a few hundred characters. We implement our method and demonstrate it is between 3 and 18 times faster than competing methods on queries to GRCh38. And was consistently faster on queries made to 25,000, 50,000 and 100,000 SARS-CoV-2 genomes. Hence, it is very clear that our method accelerates the performance of count over all state-of-the-art methods with a minor increase in the memory. The source code for PFP-FM is available at https://***/marco-oliva/afm. Copyright © 2023, The Authors. All rights reserved.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Optimal Privacy Preserving in Wireless Federated Learning Over Mobile Edge Computing

Optimal Privacy Preserving in Wireless Federated Learning Ov...

引用

IEEE International Conference on Communications (ICC)

作者： Hai M. Nguyen Nam H. Chu Diep N. Nguyen Dinh Thai Hoang Minh Hoàng Hà Eryk Dutkiewicz School of Electrical and Data Engineering University of Technology Sydney Australia JTIRC VNU University of Engineering and Technology Vietnam National University Hanoi Vietnam ORLab Faculty of Computer Science Phenikaa University Hanoi Vietnam

Federated Learning (FL) with quantization and deliberately added noise over wireless networks is a promising approach to preserve the user differential privacy while reducing the wireless resources. Specifically, an FL learning process can be fused with quantized Binomial mechanism-based updates contributed by multiple users to reduce the communication overhead/cost as well as to protect the privacy of participating users. However, the optimization of wireless transmission and quantization parameters (e.g., transmit power, bandwidth, and quantization bits) as well as the added noise while guaranteeing the privacy requirement and the performance of the learned FL model remains an open and challenging problem. In this paper, we aim to jointly optimize the level of quantization, parameters of the Binomial mechanism, and devices' transmit powers to minimize the training time under the constraints of the wireless networks. The resulting optimization turns out to be a Mixed Integer Non-linear Programming (MINLP) problem, which is known to be NP-hard. To tackle it, we transform this MINLP problem into a new problem whose solutions are proved to be the optimal solutions of the original one. We then propose an approximate algorithm that can solve the transformed problem with an arbitrary relative error guarantee. Intensive simulations show that for the same wireless resources the proposed approach achieves the highest accuracy, close to that of the conventional FL with no quantization and no noise added. This suggests the faster convergence/training time of the proposed wireless FL framework while optimally preserving users' privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperative Visual Inertial Odometry for Heterogeneous Swarm of Drones Navigating in Noisy Environments

Cooperative Visual Inertial Odometry for Heterogeneous Swarm...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Kamil Canberk Atik Enes Erdogan Ahmet Yusuf Yahsi Feyzullah Kara Baris Yalcin Gü rkan Cetin Nazim Kemal Ure Faculty of Aeronautics and Astronautics ITU Artificial Intelligence and Data Science Application and Research Center Istanbul Technical University Istanbul Turkey Faculty of Computer and Informatics Engineering ITU Artificial Intelligence and Data Science Application and Research Center Istanbul Technical University Istanbul Turkey Faculty of Electrical and Electronics ITU Artificial Intelligence and Data Science Application and Research Center Istanbul Technical University Istanbul Turkey Havelsan Ankara Turkey

This paper presents a methodology for enhancing the localization performance of drone swarms by collaborative propagation of the estimates of drones equipped with higher cost sensors to the drones with lower-cost sensors. Although recent advances in visual-inertial odometry (VIO) enabled good performance in GPS denied environments, the localization performance is still highly dependent on the accuracy of inertial sensors. Moreover, environmental effects that corrupt visual inputs also contribute to the error rate of VIO estimates thus localization in noisy environments with low-grade sensors is still widely an open problem. We show that this problem can be alleviated when drones are navigating in the form of a swarm, and the relative distance measurements between drones are available through ultra-wideband (UWB) signals. In particular, we develop a collaborative Kalman filtering and optimization framework, where the drones with lower grade sensors receive updates from drones that have access to higher-quality measurements. We validate our approach in a simulation environment with realistic visual representations and show that the proposed methodology can significantly improve the localization performance, especially for the scenarios where the camera measurements are corrupted with high noise. We further present results in simplistic flight tests to demonstrate the applicability of our approach to real hardware.

关键词： Location awareness Visualization Costs Navigation Surveillance Teamwork Trajectory

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Text Classification Method Driven by Dynamic Hierarchical Fusion and Prompt Embedding

Hierarchical Text Classification Method Driven by Dynamic Hi...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yiyun Xing Kaili Zhou Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Shandong Engineering Research Center of Big Data Applied Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Hierarchical Text Classification, as a critical task in natural language processing, has broad applications in scenarios with complex label structures and limited samples. However, existing methods still face challenges in capturing hierarchical label information and text interactions, resulting in suboptimal classification performance. This study proposes a few-shot hierarchical text classification method based on prompt embeddings and dynamically fused hierarchical features. Building on pre-trained language models, the method encodes hierarchical structure information as prompts through an adaptive prompt embedding model and dynamically fuses hierarchical features to generate more expressive text representations. Additionally, a positive sample generation strategy based on contrastive learning is introduced, enabling the model to effectively distinguish hierarchical features across different categories, further enhancing classification performance. Experimental results demonstrate that this method significantly improves classification accuracy on multiple public datasets, exhibiting stronger generalization ability and robustness compared to mainstream methods. This approach offers a novel and effective solution for hierarchical text classification tasks.

关键词： Adaptation models Accuracy Federated learning Computational modeling Text categorization Buildings Contrastive learning Robustness Natural language processing Faces

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Techniques for Necessary and Possible Winners

引用

ACM/IMS Transactions on data science 2021年第3期2卷 1–23页

作者： Chakraborty, Vishal Delemazure, Theo Kimelfeld, Benny Kolaitis, Phokion G. Relia, Kunal Stoyanovich, Julia Computer Science and Engineering Department Jack Baskin School of Engineering University of California Santa Cruz Santa CruzCA95064 United States Ecole Normale Superieure 45 Rue d'Ulm Paris75005 France Henry and Marilyn Taub Faculty of Computer Science Technion Haifa3200003 Israel Computer Science and Engineering Department Jack Baskin School of Engineering University of California Santa Cruz Santa CruzCA95064 United States Computer Science and Engineering Department Tandon School of Engineering New York University 370 Jay Street BrooklynNY11201 United States Center for Data Science New York University 60 5th Avenue New YorkNY10011 United States

We investigate the practical aspects of computing the necessary and possible winners in elections over incomplete voter preferences. In the case of the necessary winners, we show how to implement and accelerate the polynomial-time algorithm of Xia and Conitzer. In the case of the possible winners, where the problem is NP-hard, we give a natural reduction to Integer Linear Programming (ILP) for all positional scoring rules and implement it in a leading commercial optimization solver. Further, we devise optimization techniques to minimize the number of ILP executions and, oftentimes, avoid them altogether. We conduct a thorough experimental study that includes the construction of a rich benchmark of election data based on real and synthetic data. Our findings suggest that, the worst-case intractability of the possible winners notwithstanding, the algorithmic techniques presented here scale well and can be used to compute the possible winners in realistic scenarios. © 2021 Association for Computing Machinery.

关键词： Integer programming

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：