检索结果-内蒙古大学图书馆

22nd International Conference on Intelligent data Engineering and Automated Learning, IDEAL 2021

作者： Lenz, Marc Tashu, Tsegaye Misikir Horváth, Tomáš Faculty of Informatics Department of Data Science and Engineering Telekom Innovation Laboratories ELTE - Eötvös Loránd University Pázmány Péter Sétány Budapest1117 Hungary College of Informatics Wollo University Kombolcha Institute of Technology Kombolcha208 Ethiopia Faculty of Science Institute of Computer Science Pavol Jozef Šafárik University Jesenná 5 Košice040 01 Slovakia

ISBN: (纸本)9783030916077

In this work, we proposed a novel approach to derive inter-lingual document representations. The introduced methods aim to enhance the quality of content-based Multilingual Document Recommendation and information retrieval Systems. The main idea centers around creating inter-lingual representations by using mappings to align monolingual representation spaces. According to the experimental results carried out on JRC-Acquis and EU bookshop multilingual corpora, the proposed concept compression approach has outperformed the traditional cross-lingual retrieval and recommendations methods. © 2021, Springer Nature Switzerland AG.

关键词： Information retrieval systems

来源：评论

学校读者我要写书评

暂无评论

Context-based information classification on hungarian invoices 20

Context-based information classification on hungarian invoic...

引用

20th Conference Information Technologies - Applicationsand Theory, ITAT 2020

作者： Szegedi, Gábor Veres, Diána Bajdikné Lendák, Imre Horváth, Tomáš Department of Data Science and Engineering ELTE - Eötvös Loránd University Faculty of Informatics Budapest Pázmány Péter sétány 1/C BudapestH-1117 Hungary

The field of Artificial Intelligence has always strove towards solving problems with computers that were previously only solvable by humans. An interesting challenge we have these years is extracting information from printed documents. In this publication we focus on the sub-domain of classifying pieces of information on printed invoices. Our goal here was to create a solution capable of finding information on scanned invoices without knowing the template of the invoice. The template-less design is important as invoices can have many different structure based on the issuer. First we feed the invoice image to a commercially available Optical Character Recognition (OCR) engine which returns the extracted texts with their bounding boxes. This information itself wouldn't be enough so we enrich it with feature engineering. The engineered features give information about the content of the text and the context of the surrounding of the bounding box as well as meta information about the entire document. The main novelty of our work comes from how we store contextual information. We then classify the text fragments into 8 categories: Invoice Number, Issue Date, Transaction Date, Due Date, Seller tax number, Customer tax number, Total gross and Other. In this paper we measure the performance of several classification algorithms for our data. We achieved 0:93 macro average F1 measure with our best model. Copyright © 2020 for this paper by its authors.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A general sample size framework for developing or updating a clinical prediction model

arXiv

引用

arXiv 2025年

作者： Riley, Richard D. Whittle, Rebecca Sadatsafavi, Mohsen Martin, Glen P. Pate, Alexander Collins, Gary S. Ensor, Joie Department of Applied Health Sciences School of Health Sciences College of Medicine and Health University of Birmingham Birmingham United Kingdom Birmingham Biomedical Research Centre United Kingdom Respiratory Evaluation Sciences Program Faculty of Pharmaceutical Sciences The University of British Columbia Vancouver Canada Division of Informatics Imaging and Data Science Faculty of Biology Medicine and Health University of Manchester Manchester Academic Health Science Centre Manchester United Kingdom Centre for Statistics in Medicine Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford OxfordOX3 7LD United Kingdom

Background Existing sample size calculations for developing clinical prediction models rely on standard (unpenalised) regression-based formula. A general approach is needed for developing or updating a CPM using any statistical or machine learning method. Objectives To propose a general framework for sample size calculations applicable to any model development approach, based on drawing samples from anticipated sampling/posterior distributions and targeting minimal degradation in predictive performance compared to reference model. Methods Researchers must provide candidate predictors, their reference model (e.g., a regression equation matching outcome incidence, predictor weights and c-statistic of previous models), and a (synthetic) dataset reflecting the joint distribution of candidate predictors in the target population. Then, a fully simulation-based approach allows the impact of a chosen development sample size and modelling strategy to be examined. This generates thousands of models and, by applying each to the entire target population, leads to sampling/posterior distributions of individual predictions and model performance (degradation) metrics, to inform required sample sizes. To improve computational speed for penalised regression, we also propose a one-sample Bayesian analysis that combines shrinkage priors with a likelihood decomposed into sample size and Fisher’s unit information. Results The framework is illustrated when developing pre-eclampsia prediction models using logistic regression (unpenalised, uniform shrinkage, lasso or ridge) and random forests. It encompasses existing sample size calculation criteria whilst also providing model assurance probabilities, instability metrics, and degradation statistics about calibration, discrimination, clinical utility, prediction error and fairness. Crucially, the required sample size depends on the users’ key estimands of interest and planned model development or updating approach. Conclusions The new, flex

关键词： Size distribution

来源：评论

学校读者我要写书评

暂无评论

Implementation of Face Patterns and Smile Recognition for Intelligent Class Attendance Systems 6

Implementation of Face Patterns and Smile Recognition for In...

引用

6th International Conference on Computer and informatics Engineering, IC2IE 2023

作者： Miftakhurrokhmat Suparyanto, Teddy Elwirehardja, Gregorius Natanael Karimah, Shofiyati Nur Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Universitas Amikom Yogyakarta Faculty of Computer Science Department of Informatics Yogyakarta Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350345162

Students 'attendance in class is one important success parameter in face-to-face learning processes. Conventional attendance systems, such as paper-based attendance sheets or identity card systems, require a long time in the manual recapitulation process. Without additional verifications, even computer vision-based methods are prone to fraudulent practices by the students instead of gaining their excitement and attention in a class. To stimulate students' attention in a class, this work designs an intelligent class attendance system, in which facial pattern and smile recognition are implemented by using the latter as an additional task-based verification to reduce the risks of fake attendance. For the face recognition module, this pilot study used FaceNet as a feature extractor combined with SVM for classification, whereas the Haar cascade algorithm is used for recognizing smiles. This face recognition pipeline was implemented as a service installed on minicomputers or Internet of Things (IoT) devices in each classroom and connected to an IP camera. Every recorded attendance will be sent as a notification to a mobile application for students that requires their active participation to confirm it with a smiling self-photo. The proposed pipeline obtained 92.86% accuracy on the test data, and 66.67% accuracy when evaluated in a real-life simulation setting through the implemented system. The lower accuracy in the simulation indicated that further improvements are indispensable, especially since the model obtained 28.57% False Negative Rate. Future studies will need to acquire more data and experiment with more efficient methods of attendance verification. © 2023 IEEE.

关键词： class attendance convolutional neural network deep learning face recognition smile

来源：评论

学校读者我要写书评

暂无评论

Evolutionary federated learning on EEG-data 19

Evolutionary federated learning on EEG-data

引用

19th Conference Information Technologies - Applications and Theory, ITAT 2019

作者： Szegedi, Gábor Kiss, Péter Horváth, Tomáš Department of Data Science and Engineering ELTE – Eötvös Loránd University Faculty of Informatics Budapest Pázmány Péter sétány 1/C. BudapestH-1117 Hungary

With the spread of digitalization across every aspects of society and economy, the amount of data generated keeps increasing. In some domains, this generation happens in such a massively distributed fashion that poses challenges for even collecting the data to build machine learning (ML) models on it, not to mention the processing power necessary for training. An important aspect of processing information that has been generated at users is privacy concerns, that is, users might be unwilling to expose anything that would enable one to draw any conclusion regarding to confidential information they possess. In this work, we present a experiment on a genetic algorithm based federated learning (FL) algorithm, that reduces the data transfer from individual users to the learner to a single fitness value. Copyright ©2019 for this paper by its authors.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

The Space Complexity of Generating Random Tent Codes

The Space Complexity of Generating Random Tent Codes

引用

International Symposium on Information Theory and Its Applications, ISITA

作者： Naoaki Okada Shuji Kijima Department of Informatics Kyushu University Fukuoka Japan Faculty of Data Science Shiga University Hikone Japan

ISBN: (数字)9784885523519

ISBN: (纸本)9798331533335

This paper is motivated by a question of whether it is possible to calculate a chaotic sequence efficiently, e.g., is it possible to get the n-th bit of a bit sequence generated by a chaotic map, such as $\beta$ -expansion, tent map, and logistic map in $\mathrm{o}(n)\text{time}/\text{space}$ ? From the viewpoint of theoretical computer science, this paper gives an affirmative answer to the question about the space complexity of a tent map. We prove that a tent code of n-bits with an initial condition uniformly at random is exactly generated in $\mathrm{O}(\log^{2}n)$ space in expectation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Abstractive text summarization using transfer learning 20

Abstractive text summarization using transfer learning

引用

20th Conference Information Technologies - Applicationsand Theory, ITAT 2020

作者： Zolotareva, Ekaterina Tashu, Tsegaye Misikir Horváth, Tomáš ELTE- Eötvös Loránd University Faculty of Informatics Department of Data Science and Engineering Telekom Innovation Laboratories Pázmány Péter sétány 1/C Budapest1117 Hungary

Recently, abstractive text summarization has achieved success in switching from linear models via sparse and handcrafted features to nonlinear neural network models via dense inputs. This success comes from the application of deep learning models on natural language processing tasks where these models are capable of modeling intricate patterns in data without handcrafted features. In this work, the text summarization problem has been explored using Sequence-to-sequence recurrent neural networks and Transfer Learning with a Unified Textto- Text Transformer approaches. Experimental results showed that the Transfer Learning-based model achieved considerable improvement for abstractive text summarization. Copyright © 2020 for this paper by its authors.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Multi-modal Emotion Recognition from Art 25th

Attention-Based Multi-modal Emotion Recognition from Art

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Tashu, Tsegaye Misikir Horváth, Tomáš Faculty of Informatics Department of Data Science and Engineering Telekom Innovation Laboratories ELTE Eötvös Loránd University Pázmány Péter sétány 1/C Budapest1117 Hungary Kombolcha Institute of Technology College of Informatics Wollo University Kombolcha208 Ethiopia Faculty of Science Institute of Computer Science Pavol Jozef Šafárik University in Košice Jesenná 5 Košice040 01 Slovakia

ISBN: (纸本)9783030687953

Emotions are very important in dealing with human decisions, interactions, and cognitive processes. Art is an imaginative human creation that should be appreciated, thought-provoking, and elicits an emotional response. The automatic recognition of emotions triggered by art is of considerable importance. It can be used to categorize artworks according to the emotions they evoke, recommend paintings that accentuate or balance a particular mood, and search for paintings of a particular style or genre that represent custom content in a custom state of impact. In this paper, we propose an attention-based multi-modal approach to emotion recognition that aims to use information from both the painting and title channels to achieve more accurate emotion recognition. Experimental results on the WikiArt emotion dataset showed the efficiency of the model we proposed and the usefulness of image and text modalities in emotion recognition. © 2021, Springer Nature Switzerland AG.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Optimization in federated learning 19

Optimization in federated learning

引用

19th Conference Information Technologies - Applications and Theory, ITAT 2019

作者： Felbab, Vukasin Kiss, Péter Horváth, Tomáš Department of Data Science and Engineering ELTE Eötvös Loránd University Faculty of Informatics Budapest Pázmány Péter sétány 1/C. BudapestH-1117 Hungary

Federated learning (FL) is an emerging branch of machine learning (ML) research, that is examining the methods for scenarios, where individual nodes possess parts of the data, and the task is to form a single common model that fits to the whole distribution. In FL, we generally use mini batch gradient descent for optimizing weights of the models that appears to work very well for federated scenarios. For traditional machine learning setups, a number of modifications has been proposed to accelerate the learning process and to help to get over challenges posed by the high dimensionality and non-convexity of search spaces of the parameters. In this paper we present our experiments on applying different popular optimization methods for training neural networks in a federated manner. Copyright ©2019 for this paper by its authors.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Joint Learning for Clinical Named Entity Recognition and Relation Extraction Using Fourier Networks: A Use Case in Adverse Drug Events

arXiv

引用

arXiv 2023年

作者： Yazdani, Anthony Proios, Dimitrios Rouhizadeh, Hossein Teodoro, Douglas University of Geneva Faculty of medicine Department of radiology and medical informatics Data science for digital health Switzerland

Current approaches for clinical information extraction are inefficient in terms of computational costs and memory consumption, hindering their application to process large-scale electronic health records (EHRs). We propose an efficient end-to-end model, the Joint-NER-RE-Fourier (JNRF), to jointly learn the tasks of named entity recognition and relation extraction for documents of variable length. The architecture uses positional encoding and unitary batch sizes to process variable length documents and uses a weight-shared Fourier network layer for low-complexity token mixing. Finally, we reach the theoretical computational complexity lower bound for relation extraction using a selective pooling strategy and distance-aware attention weights with trainable polynomial distance functions. We evaluated the JNRF architecture using the 2018 N2C2 ADE benchmark to jointly extract medication-related entities and relations in variable-length EHR summaries. JNRF outperforms rolling window BERT with selective pooling by 0.42%, while being twice as fast to train. Compared to state-of-the-art BiLSTM-CRF architectures on the N2C2 ADE benchmark, results show that the proposed approach trains 22 times faster and reduces GPU memory consumption by 1.75 folds, with a reasonable performance tradeoff of 90%, without the use of external tools, hand-crafted rules or post-processing. Given the significant carbon footprint of deep learning models and the current energy crises, these methods could support efficient and cleaner information extraction in EHRs and other types of large-scale document databases. © 2023, CC BY.

关键词： Deep learning

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：