检索结果-内蒙古大学图书馆

ACS/IEEE international conference on Computer Systems and Applications

作者： Mohamed Ayachi Brini Hanae Touati Rafika Thabet Franck Fontanili Marie-Hélène Cleostrate Marie-Noëlle Cufi Marc Pruski Elyes Lamine CGI IMT Mines Albi Toulouse University Albi France ISITCom Sousse University Albi France MARS Laboratory Tunisia Centre Hospitalier Intercommunal Castres-Mazamet France Atout Majeur Concept Toulouse France Toulouse University ISIS Engineering INUC Castres France CGI IMT Mines Albi Toulouse University Castres France

ISBN: (数字)9798331518240

ISBN: (纸本)9798331518257

Optical Character Recognition (OCR) is extremely useful in various sectors for exploring massive archived data. This technology enables the digitization of printed and handwritten texts that are frequently present in the medical field. For instance, medication error (ME) reports were previously and still in some healthcare facilities written manually, this has led to the accumulation of numerous handwritten data that are unfortunately challenging to exploit. Their digitization through OCR allows extracting important data from these documents and using them to populate the database to implement future analysis techniques to optimize the medication error management process. This paper presents a transformer-based handwritten recognition architecture that employs the Transformer-Based Optical Character Recognition (TrOCR) model combined with image segmentation techniques. Although the TrOCR model provided by Microsoft performs reasonably well in handwritten recognition, it is limited to English text because its pretrained version was trained exclusively on English samples. This limitation is problematic for us, as our task involves digitizing French medication dictation errors. Additionally, its limitation to processing single-line text images impairs its ability to recognize paragraphs. To address these limitations, we will fine-tune the model on French handwritten data and integrate a single-line level segmentation technique, thereby overcoming these constraints. Therefore, the preliminary results from implementing our proposed architecture are promising for the digitization of medication error reports.

关键词： Deep learning Image segmentation Handwriting recognition Image recognition Text recognition Ultraviolet sources Optical character recognition Computer architecture Transformers Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

DistilKaggle: A Distilled dataset of Kaggle Jupyter Notebooks

DistilKaggle: A Distilled Dataset of Kaggle Jupyter Notebook...

引用

international Mining Software Repositories, MSR

作者： Mojtaba Mostafavi Ghahfarokhi Arash Asgari Mohammad Abolnejadian Abbas Heydarnoori Department of Computer Engineering Sharif University of Technology Department of Computer Science Bowling Green State University USA

ISBN: (数字)9798400705878

ISBN: (纸本)9798350363982

Jupyter notebooks have become indispensable tools for data analysis and processing in various domains. However, despite their widespread use, there is a notable research gap in understanding and analyzing the contents and code metrics of these notebooks. This gap is primarily attributed to the absence of datasets that encompass both Jupyter notebooks and extracted their code metrics. To address this limitation, we introduce DistilKaggle, a unique dataset specifically curated to facilitate research on code metrics in Jupyter notebooks, utilizing the Kaggle repository as a prime source. Through an extensive study, we identify thirty-four code metrics that significantly impact Jupyter notebook code quality. These features such as lines of code cell, mean number of words in markdown cells, performance tier of developer, etc., are crucial for understanding and improving the overall effectiveness of computational notebooks. The DistilKaggle dataset which is derived from a vast collection of notebooks constitutes two distinct datasets: (i) Code Cells and Markdown Cells dataset which is presen’ workflows as dataframes. It provides a granular view of the content structure within 542,051 Jupyter notebooks, enabling detailed analysis of code and markdown cells; and (ii) The Notebook Code Metrics dataset focused on the identified code metrics of notebooks. Researchers can leverage this dataset to access Jupyter notebooks with specific code quality characteristics, surpassing the limitations of filters available on the Kaggle website. Furthermore, the reproducibility of the notebooks in our dataset is ensured through the code cells and markdown cells datasets, offering a reliable foundation for researchers to build upon. Given the substantial size of our datasets, it becomes an invaluable resource for the research community, surpassing the capabilities of individual Kaggle users to collect such extensive data. For accessibility and transparency, both the dataset and the code uti

关键词： Measurement Deep learning Solid modeling Codes Software libraries Filters Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Recursive Additive Attention Based Convolutional Neural Network Model for Plant Disease Detection

Recursive Additive Attention Based Convolutional Neural Netw...

引用

IEEE India conference (INDICON)

作者： Subham Divakar Rojalina Priyadarshini Department of Electronics and Telecommunication C.V. Raman Global University Bhubaneswar India Department of Computer Science and Engineering C.V. Raman Global University Bhubaneswar India

ISBN: (数字)9798350391282

ISBN: (纸本)9798350391299

In recent years, the need for accurate and efficient image classification has become increasingly important across various domains, particularly in agriculture where early and precise identification of plant diseases can significantly impact crop yield and food security. Traditional Convolutional Neural Networks (CNNs) have proven effective in feature extraction but often struggle with capturing complex contextual relationships within images. To address this limitation, we present a novel approach that integrates a recursive additive attention mechanism within a CNN-based encoder-only architecture. Our approach leverages the power of attention mechanisms to focus on relevant features while recursively and additively refining this attention over multiple iterations, leading to more nuanced and contextaware feature extraction. This innovative combination enhances the model's ability to differentiate between subtle variations in plant disease symptoms, resulting in superior classification peformance. Evaluated on a comprehensive plant disease dataset, our model achieves an overall accuracy of 98.61 percent, a Cohen's Kappa Score of 0.9812, and high precision, recall, and F1 scores across all classes. Additionally, the model exhibits a low log loss of 0.0523, underscoring its robust probabilistic predictions. These results demonstrate the effectiveness of our approach in improving classification accuracy and reliability, offering significant advancements over traditional methods. This work not only contributes valuable insights to the field of image classification but also showcases the potential of advanced attention mechanisms in enhancing the performance of practical applications.

关键词： Deep learning Plant diseases Accuracy Attention mechanisms Additives Predictive models Feature extraction data models Reliability Image classification

来源：评论

学校读者我要写书评

暂无评论

Subject-Independent Classification of Meditative state from the Resting state Using EEG

Subject-Independent Classification of Meditative State from ...

引用

IEEE India conference (INDICON)

作者： Jerrin Thomas Panachakel Pradeep Kumar G. Suryaa Seran Kanishka Sharma Ramakrishnan Angarai Ganesan Dept. of Elect. and Comm. Engg. College of Engineering Trivandrum Trivandrum India Centre for Brain Research Indian Institute of Science Bangalore Bangalore India Language Technologies Institute Carnegie Mellon University Pennsylvania USA School of Psychology and Education Rishihood University Sonipat Sonipat India Dept. of Heritage Science and Technology Indian Institute of Technology Hyderabad Hyderabad India

ISBN: (数字)9798350391282

ISBN: (纸本)9798350391299

While it is beneficial to objectively determine whether a subject is meditating, most research in the literature reports good results only in a subject-dependent manner. This study aims to distinguish the modified state of consciousness experienced during Rajyoga meditation from the resting state of the brain in a subject-independent manner using EEG data. Three architectures have been proposed and evaluated: The CSP-LDA Architecture utilizes common spatial pattern (CSP) for feature extraction and linear discriminant analysis (LDA) for classification. The CSP-LDA-LstM Architecture employs CSP for feature extraction, LDA for dimensionality reduction, and long short-term memory (LstM) networks for classification, modeling the binary classification problem as a sequence learning problem. The SVD-NN Architecture uses singular value decomposition (SVD) to select the most relevant components of the EEG signals and a shallow neural network (NN) for classification. The CSP-LDA-LstM architecture gives the best performance with 98.2% accuracy for intra-subject classification. The SVD-NN architecture provides significant performance with 96.4% accuracy for inter-subject classification. This is comparable to the best-reported accuracies in the literature for intra-subject classification. Both architectures are capable of capturing subject-invariant EEG features for effectively classifying the meditative state from the resting state. The high intra-subject and inter-subject classification accuracies indicate these systems' robustness and their ability to generalize across different subjects.

关键词： Dimensionality reduction Accuracy Neural activity Feature extraction Electroencephalography Robustness Linear discriminant analysis Occipital Lobe Long short term memory Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Feature Regrouping for CCA-Based Feature Fusion and Extraction Through Normalized Cut

Feature Regrouping for CCA-Based Feature Fusion and Extracti...

引用

international conference on Information Fusion

作者： Wu Zuobin Mao Kezhi Gee-Wah Ng School of Electrical and Electronics Engineering Nanyang Technological University Singapore Cognition and Fusion Laboratory DSO National Laboratories Singapore

Feature fusion is important for providing enhancements of data authenticity in both traditional and deep learning pattern analysis. Classical serial fusion concatenates multiple feature sets followed by dimensionality reduction using principal component analysis (PCA), linear discriminant analysis (LDA), canonical correlation analysis (CCA) etc. CCA-based feature fusion is a main technique for exploring the mutual relationships of multiple feature sets. It considers the correlation of multiple feature sets during dimensionality reduction. In traditional CCA-based feature fusion and extraction, the natural groupings of features are directly used. It is still unclear whether the natural groupings of features are optimal for CCA-based fusion. In this paper, we propose a feature regrouping algorithm for CCA-based feature fusion and extraction through normalized cut (FR-NC). Feature correlation analysis is incorporated into normalized cut, in which the intra-group correlation is maximized, and the extra-group correlation is minimized simultaneously. CCA-based feature fusion is performed on the regrouped features. The proposed feature regrouping algorithm aims to provide enhanced fused features for pattern classification. Extensive experiments have proved its effectiveness.

关键词： Canonical correlation analysis Feature fusion Feature regrouping Normalized cut Pattern classification

来源：评论

学校读者我要写书评

暂无评论

intelligent Production Optimization Decisions: Prioritizing Production Optimization Through Machine learning Aided Uplift Quantification

Intelligent Production Optimization Decisions: Prioritizing ...

引用

Abu Dhabi international Petroleum Exhibition and conference 2022, ADIPEC 2022

作者： Sharma, Akriti Ahn, Alex Chonghyun Park, Jihoon Singh, Vikash Rodriguez-Buno, Mariana El-Bakry, Amr Kwong, John Garrison, Brett Gelowitz, Tyler ExxonMobil Imperial Oil Limited

ISBN: (纸本)9781613998724

Due to complexity and scale, managing and engineering a modern hydrocarbon asset is extremely challenging. The problem becomes more difficult if an asset has thousands of wells to manage because, most of the time, operation resource is limited (either manpower or tool) to achieve production optimization and the amount of information to process during decision making is enormous. Bringing necessary data from multiple different sources and analyzing it in a relatively short period of time to provide actionable/reliable insight to field operators' and engineers' is the key to enhance and optimize production performance. The production optimization best practice is shared amongst field operators and engineers given the geology, reservoir character, and operation strategy which include artificial lift, stimulation, and other workover. This approach has been applied and proven successful mostly in low well count assets by identifying opportunity and providing robust qualitative guidance towards optimum production condition. However, in high well count assets such as unconventional, it is impossible to execute traditional manual approach and it is essential to develop an integrated, flexible, and automated workflow that enhances the efficiency and effectiveness of production operation and achieve "operate-by-priority". Thus, to have efficient and optimized management of hydrocarbon production from individual well of a high well count asset requires prior, more certain and almost real time knowledge of production rates from the currently or upcoming production wells. Production data, thus, from individual well is very important. Well tests are carried out to obtain production rates and then utilize these rates to provide optimized production decisions and actions. In a well test, a test separator splits the production stream into oil, gas, and water using gravity and support in the management of hydrocarbon production. However, well test are infrequent and doesn't fit the p

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Pre-service teachers’ perception in integrating stEAM in chemistry learning

引用

AIP conference Proceedings 2021年第1期2331卷

作者： Nurma Yunita Indriyanti Elda Frediana Rety Kartika Elfi Susanti Master Program of Chemistry Education Faculty of Teacher Training and Education Universitas Sebelas Maret Jalan Ir. Sutami 36 Kentingan Jebres Surakarta Jawa Tengah 57126 Indonesia

In 21st century learning, individuals expect to have abilities such as transforming what they have learned into skills and using technology effectively and appropriately to face the globalization, international competition, and changing markets. For this reason integrating science, technology, engineering, art, and mathematics (stEAM) in education, which is considered to enable individuals multifaceted became necessary; therefore, teachers and pre-service teachers need to be equipped with stEAM in teaching. This study examined the pre-service teacher perception of integrating stEAM in chemistry learning. This study involved twenty-eight 3rd-year undergraduate students of chemistry education in a public university in Surakarta, Indonesia. A qualitative research design was applied to explore their perception of stEAM. data collected through surveys and interviews. The findings showed that the majority of pre- service teachers did not understand stEAM in depth. They have just known stEAM in general terms and found it challenging to choose a chemistry topic for integrating stEAM. Their perception of stEAM is still in the low-level category. It showed that the pre-service teachers did not familiar with stEAM. Parallel with the university vision becoming the top development center for science, knowledge, and art at the international level, which is based on the noble values of the national culture, pre-service teacher training program based on stEAM in chemistry education are needed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model for the formation of students’ interest in stEM through geometry learning based on visual spatial abilities using augmented reality technology

引用

AIP conference Proceedings 2022年第1期2633卷

作者： Nurul Anis Syuhada Adnan Sharifah Osman Jeya Amantha Kumar Hanifah Jambari Corrienna Abdul Talib 1Universiti Teknologi Malaysia Johor Bahru Malaysia 2Universiti Sains Malaysia Pulau Pinang Malaysia

stEM education is one of the primary priorities in the Malaysian Education Blueprint (PPPM) 2013-2025, in line with the relevance of stEM at the global level. In keeping with the educational needs of 21st-century learning, the use of technology in education is also highly encouraged. Unfortunately, the Malaysian government's goal of producing one million experts in Science, Technology, engineering, and Mathematics (stEM) by 2020 was not met because the 60:40 stEM: non-stEM policy failed to meet the goal. students' interest in different stEM disciplines has been linked to their interest in integrated stEM in previous studies. students' lack of interest in stEM fields appears to have an impact on their low mathematics achievement at the international assessment level, including in the field of geometry. Geometry is one of the most important branches of mathematics, and spatial thinking goes hand in hand with it. This paper presents the results of a critical review as well as a brief overview of ongoing research targeted at developing a model for the formation of interest among secondary school students in stEM through geometry learning based on augmented reality (AR) technology and visual-spatial abilities. The first part of the paper provides an in-depth review of these matters based on rather limited resources. The review revealed various difficulties and limitations in piquing students’ interest in stEM and mathematics. The second part describes research being conducted by the researchers to examine the implementation of using AR in geometry learning based on visual-spatial abilities. For the pilot and main stages of the study, pre-and post-test, observations, and semi-structured interviews will be conducted. The data will be analysed quantitatively and qualitatively, and the theory of change approach will be applied. The findings will be used to develop a model for the formation of interests among students as a result of geometry learning. The model aims to provid

关键词：

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：