检索结果-内蒙古大学图书馆

End-to-end entity extraction from OCRed texts using summarization models

Neural Computing and Applications 2024年第35期36卷 22347-22363页

作者： Villa-García, Pedro A. Alonso-Calvo, Raúl García-Remesal, Miguel Biomedical Informatics Group Department of Artificial Intelligence Universidad Politécnica de Madrid Campus Montegancedo s/n Boadilla del Monte Madrid28660 Spain Biomedical Informatics Group Department of Languages Informatic Systems and Software Engineering Universidad Politécnica de Madrid Campus Montegancedo s/n Boadilla del Monte Madrid28660 Spain

A novel methodology is introduced for extracting entities from noisy scanned documents by using end-to-end data and reformulating the entity extraction task as a text summarization problem. This approach offers two significant advantages over traditional entity extraction methods while maintaining comparable performance. First, it utilizes preexisting data to construct datasets, thereby eliminating the need for labor-intensive annotation procedures. Second, it employs multitask learning, enabling the training of a model via a single dataset. To evaluate our approach against state-of-the-art methods, we adapted three commonly used datasets, namely, Conference on Natural Language Learning (CoNLL++), few-shot named entity recognition (Few-NERD), and WikiNEuRal domain adaptation (WikiNEuRal + DA), to the format required by our methodology. We subsequently fine-tuned four sequence-to-sequence models: text-to-text transfer transformer (T5), fine-tuned language net T5 (FLAN-T5), bidirectional autoregressive transformer (BART), and pretraining with extracted gap sentences for abstractive summarization sequence-to-sequence models (PEGASUS). The results indicate that, in the absence of optical character recognition (OCR) noise, the BART model performs comparably to state-of-the-art methods. Furthermore, the performance degradation was limited to 3.49–5.23% when 39–62% of the sentences contained OCR noise. This performance is significantly superior to that of previous studies, which reported a 10–20% decrease in the F1 score with texts that had a 20% OCR error rate. Our experimental results demonstrate that a single model trained via our methodology can reliably extract entities from noisy OCRed texts, unlike existing state-of-the-art approaches, which require separate models for correcting OCR errors and extracting entities. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Quality Inference in Federated Learning with Secure Aggregation

引用

IEEE Transactions on Big Data 2023年第5期9卷 1430-1437页

作者： Pejó, Balázs Biczók, Gergely Budapest University of Technology and Economics CrySyS Lab Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest1111 Hungary ELKH-BME Information Systems Research Group Budapest1111 Hungary

Federated learning algorithms are developed both for efficiency reasons and to ensure the privacy and confidentiality of personal and business data, respectively. Despite no data being shared explicitly, recent studies showed that the mechanism could still leak sensitive information. Hence, secure aggregation is utilized in many real-world scenarios to prevent attribution to specific participants. In this paper, we focus on the quality (i.e., the ratio of correct labels) of individual training datasets and show that such quality information could be inferred and attributed to specific participants even when secure aggregation is applied. Specifically, through a series of image recognition experiments, we infer the relative quality ordering of participants. Moreover, we apply the inferred quality information to stabilize training performance, measure the individual contribution of participants, and detect misbehavior. © 2015 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Incremental federated learning for traffic flow classification in heterogeneous data scenarios

引用

Neural Computing and Applications 2024年第32期36卷 20401-20424页

作者： Pekar, Adrian Makara, Laszlo Arpad Biczok, Gergely Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3. Budapest1111 Hungary HUN-REN-BME Information Systems Research Group Magyar Tudósok krt. 2 Budapest1117 Hungary

This paper explores the comparative analysis of federated learning (FL) and centralized learning (CL) models in the context of multi-class traffic flow classification for network applications, a timely study in the context of increasing privacy preservation concerns. Unlike existing literature that often omits detailed class-wise performance evaluation, and consistent data handling and feature selection approaches, our study rectifies these gaps by implementing a feed-forward neural network and assessing FL performance under both independent and identically distributed (IID) and non-independent and identically distributed (non-IID) conditions, with a particular focus on incremental training. In our cross-silo experimental setup involving five clients per round, FL models exhibit notable adaptability. Under IID conditions, the accuracy of the FL model peaked at 96.65%, demonstrating its robustness. Moreover, despite the challenges presented by non-IID environments, our FL models demonstrated significant resilience, adapting incrementally over rounds to optimize performance;in most scenarios, our FL models performed comparably to the idealistic CL model regarding multiple well-established metrics. Through a comprehensive traffic flow classification use case, this work (i) contributes to a better understanding of the capabilities and limitations of FL, offering valuable insights for the real-world deployment of FL, and (ii) provides a novel, large, carefully curated traffic flow dataset for the research community. © The Author(s) 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Assisting Visually Impaired Subjects Using Large Language Models: A Comprehensive Evaluation 6

Assisting Visually Impaired Subjects Using Large Language Mo...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Holiel, Heidi Ahmed Fawzi, Sahar Ali Al-Atabany, Walid Center for Informatics Science Nile University Medical Imaging and Image Processing Research Group Sheikh Zayed City Egypt Cairo University Systems and Biomedical Engineering Department Giza Egypt Helwan University Biomedical Engineering Department Helwan Egypt

ISBN: (纸本)9798350378511

Visual impairment significantly challenges an individual's ability to navigate and interact with their environment independently. While retinal prostheses have provided partial vision restoration, they offer limited support for complex visual tasks such as object recognition, text reading, and real-time navigation. Recent advancements in technology have introduced Large Language Models (LLMs) as promising tools to enhance these assistive technologies, potentially enhancing the capabilities of existing devices. This study explores the integration of LLMs into assistive devices for visually impaired individuals, evaluating several models, including MiniCPM-Llama3-V-2_5, PaliGemma, Blip2, Microsoft Git Large COCO, and LLaVA-Next. The models are assessed in tasks like image captioning, object detection, and optical character recognition (OCR), focusing on their effectiveness in enhancing user independence and quality of life. Our findings indicate that MiniCPM-Llama3-V-2_5 and PaliGemma excel in providing accurate, detailed, and practical outputs, crucial for real-world applications. These models demonstrate significant potential in transforming retinal prostheses from passive aids into interactive tools that enhance user engagement with their surroundings. The study concludes with discussions on the implications of these findings and suggests future research directions to further improve the integration of LLMs in assistive technologies for visually impaired individuals. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Inclusiveness of Artificial Intelligence software in Enhancing Project Management Efficiency - A review and examples of quantitative measurement methods

Evaluating the Inclusiveness of Artificial Intelligence Soft...

引用

2024 International Conference on Artificial Intelligence, Computer, Data Sciences, and Applications, ACDSA 2024

作者： Alevizos, Vasileios Georgousis, Ilias Simasiku, Akebu Messinis, Antonis Karypidou, Sotiria Malliarou, Dimitra Karolinska Institute Department of Learning Informatics Managament and Ethics Stockholm Sweden International Hellenic University Mlv Research Group Department of Computer Science Kavala Greece Zambia University Department of Computer Software Engineering Ndola Zambia Greece International Hellenic University Mlv Research Group Department of Computer Science Greece IntelliSolutions Athens Greece

ISBN: (纸本)9798350394528

The escalating integration of Artificial Intelligence (AI) in various domains, especially Project Management (PM), has brought to light the imperative need for inclusivity in AI systems. This paper investigates the role of AI software in augmenting both the inclusiveness and efficiency within the realm of PM. The research pivots around specific criteria that define and measure the inclusiveness of AI in PM, highlighting how AI, when developed with inclusiveness in mind, can significantly enhance project outcomes. However, there are inherent challenges in achieving this inclusiveness, primarily due to biases embedded in AI learning databases and the design and development processes of AI systems. The study offers a comprehensive examination of AI's potential to revolutionize PM by enabling managers to concentrate more on people-centric aspects of their work. This is achieved through AI's ability to perform tasks such as data collection, reporting, and predictive analysis more consistently and efficiently than human counterparts. However, the incorporation of AI in PM extends beyond mere efficiency;it represents a paradigm shift in the epistemology of PM, calling for a deeper understanding of AI's role and impact on society. Despite these advantages, the adoption of AI comes with significant challenges, particularly in terms of bias and inclusiveness. Biased AI learning databases, which use shared and reusable datasets, often perpetuate initially discriminatory algorithms. Moreover, unconscious biases and stereotypes of AI designers, developers, and trainers can inadvertently influence the behavior of the AI systems they create. This necessitates a paradigmatic shift in how AI systems are developed and governed to ensure they do not replicate or exacerbate existing social inequalities. The research proposes a methodological approach involving the development of criteria for inclusion and exclusion, alongside data extraction, to evaluate the inclusiveness and efficienc

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

FANET and MANET, a Support and Composition Relationship

引用

Computers, Materials & Continua 2025年第2期82卷 1699-1732页

作者： Carlos Andrés Tavera Romero Jesús Hamilton Ortiz Luis Carlos Rodríguez Timaná Fernando Vélez Varela Andrés Hernando Aristizábal Montufar Javier Gamboa-Cruzado COMBA R&D Laboratory Faculty of EngineeringUniversidad Santiago de CaliCali76001Colombia Development Department Closemobile R&D Telecommunications LSMadrid28070Spain GIEIAM Research Group Faculty of EngineeringUniversidad Santiago de CaliCali76001Colombia Faculty of Engineering Universidad LibreCali760031Colombia Faculty of Systems and Informatics Engineering Universidad Nacional Mayor de San MarcosLima15001Perú

This study investigates the design and implementation of Flying Ad Hoc Networks(FANETs),a network architec-ture inspired by the Mobile Ad Hoc Network(MANET)model,specifically tailored to support unmanned aerial vehicles(UAVs).As UAVs increasingly contribute to diverse fields,from surveillance to delivery,FANETs have emerged as essential in ensuring stable,dynamic communication channels among drones in *** research adopts a dual approach,combining rigorous theoretical analysis with detailed practical simulations to assess the performance,adaptability,and efficiency of FANETs in varying *** findings emphasize the ability of FANETs to manage network congestion effectively in densely populated areas,a critical feature for maintaining reliable communications in complex ***,FANETs demonstrate high potential to support critical applications,such as emergency response,disaster management,and public safety operations,where quick and coordinated action is *** study also underscores the importance of establishing a hierarchical structure among nodes within the network,which allows for more efficient data exchange and helps optimize the overall network *** this work,significant insights are offered into the design principles that can enhance UAV communication networks,providing a foundation for the development of more resilient,scalable,and efficient technological *** advancements could accelerate the deployment of UAVs across a variety of sectors,including logistics,agriculture,environmental monitoring,and *** such,this study not only contributes to the field of ad hoc networking but also holds potential for transformative impacts across industries where UAVs play an increasingly central role,promoting greater integration and operational success.

关键词： Ad hoc FANET MANET network UAV

来源：评论

学校读者我要写书评

暂无评论

Mode Division Multiplexing Bidirectional Transmission System using Double Clad Fiber for Mobile In-Building Solutions 46

Mode Division Multiplexing Bidirectional Transmission System...

引用

46th International Conference on Telecommunications and Signal Processing, TSP 2023

作者： Mohamed, Ahmed S. Udvary, Eszter Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services BudapestH-1111 Hungary ELKH-BME Information Systems Research Group Budapest1117 Hungary

ISBN: (纸本)9798350303964

This paper shows the conceptual model of the possibility of simultaneously transmitting data and power on the same optical fiber by adopting the Power Over Fiber PWoF concept and Mode Division Multiplexing MDM. MDM is the data transmission multiplexing scheme of choice where two modes of light are considered;one mode carries the downlink, while the other mode carries the uplink information. Adopting the PWoF, remote devices can be powered by the optical energy transferred on the same optical fiber. Double Clad Fibers DCF are introduced as the transmission medium. DCF consists of the core, which is a few-mode fiber core capable of handling the two needed modes, the inner cladding which has a relatively large diameter and is capable of handling the optical power, and the outer cladding. The proposed system can reduce the complexity and the operations cost, suitable to be used in In-Building Solutions IBS. © 2023 IEEE.

关键词： Transmissions

来源：评论

学校读者我要写书评

暂无评论

Separated Artificial Neural Network Based Distribution System State Estimation

Separated Artificial Neural Network Based Distribution Syste...

引用

2023 IEEE PES Generation, Transmission and Distribution International Conference and Exposition, GTD 2023

作者： Pasic, Lejla Pasic, Azra Pasic, Alija Vokony, Istvan Biro, Jozsef Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics BudapestH-1111 Hungary Department of Telecommunications and Media Informatics Budapest Hungary Department of Electric Power Engineering Budapest Hungary ELKH-BME Information Systems Research Group Budapest Hungary

ISBN: (纸本)9781728170251

Distribution system state estimation is becoming an increasingly important feature in the modern power grid, but the lack of real measurements makes its implementation particularly difficult. A solution for this problem could be the implementation of Artificial Neural Networks for direct distribution system state estimation. In our work, we created an ANN-based distribution system state estimation which can function based on sparse data, the accuracy of the ANN-based state estimation can be further improved utilizing a separated distribution system state estimation (S-ANN), which estimates the state of the network separately according to measurement type based on the same input data. With this method, the root mean square error and standard deviation of the state estimation can be significantly decreased. © 2023 IEEE.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Performance of a TDOA indoor positioning solution in real-world 5G network 36

Performance of a TDOA indoor positioning solution in real-wo...

引用

36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023

作者： Revisnyei, Péter Mogyorósi, Ferenc Papp, Zsófia Töros, István Pašić, Alija Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Telecommunications and Media Informatics Muegyetem rkp. 3. BudapestH-1111 Hungary Ericsson Research ELKH-BME Information Systems Research Group Budapest Hungary

ISBN: (纸本)9781665477161

Indoor localization is one of the most requested applications for 5G networks. With the continuous deployment of new 5G networks, the implementation of a reliable, robust, and accurate indoor positioning algorithm has become a widely and thoroughly researched topic. However, the solutions realized for real-world environments still do not meet all performance expectations. In this paper, a real-world 5G environment is investigated and the feasibility of the measurements collected for positioning is discussed. Based on these findings, a framework for indoor positioning is proposed and evaluated using Time Difference of Arrival (TDOA) measurements. Within the framework, an iterative algorithm is implemented to minimize a non-linear least squares function extended with four additional methods to mitigate the measurement errors caused mainly by non-line-of sight propagation. The best parameter settings are determined with hyperparameter optimization, and it is shown that with these settings, sub-meter positioning error is a viable goal in certain scenarios. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Towards an Automated Process for Adaptive Modelling of Orthoses and Shoe Insoles in Additive Manufacturing 12

Towards an Automated Process for Adaptive Modelling of Ortho...

引用

12th International Workshop on Innovative Simulation for Health Care, IWISH 2023

作者： Zwettler, Gerald A. Trixner, Martin Schartmüller, Clemens Bauernfeind, Sophie Stockinger, Thomas Praschl, Christoph Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria Granitweg 1 Kirchschlag bei Linz4202 Austria Pulvermühlstrasse 3 Linz4040 Austria

ISBN: (纸本)9788885741966

Although orthopedics is becoming increasingly important as a medical domain, especially in emerging countries, the level of automation is still marginal and hardly any Industry 4.0 paradigms have been implemented. In this scientific work, solution concepts for holistic process automation in orthopedics are introduced so that prosthetic covers and orthoses for different body regions can be automated by using AI and evaluated with sensor networks. In this process, body scan models are adapted to the conditions of the anatomy or prosthesis models, so that stability as well as fitting accuracy are given in comparison with the other half of the body. Automation in the field of orthopedics leads not only to a significant reduction in costs but can also help to close the research gap regarding objectifiability of results. The first partial aspects have already been successfully implemented for leg prostheses, arm prostheses and shoe insoles with the aid of machine learning processes and physical models for elastic form fitting. As soon as the overall process has been realized, the applicability will be validated in the following year of the project by means of clinical studies and evaluated by utilizing sensor networks for pressure and temperature measurements. © 2023 The Authors.

关键词： Sensor networks

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：