检索结果-内蒙古大学图书馆

Advancements in computing (ICAC), International Conference on

作者： Farhath Ajmal Poorna Wijekoon Haritha Dhanamina Yasiru Ravishan Dasuni Nawinna Buddhima Attanayaka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

The automation of business process modelling has become crucial for organizations seeking to improve their operational efficiency. This research presents a novel methodology that leverages fine-tuned GPT models to automate the conversion of textual business process descriptions into Business Process Model and Notation (BPMN) diagrams. The study builds on previous work, addressing gaps related to the handling of unstructured text and the absence of anaphora resolution in our solution we use fine-tuned GPT models to accurately extract and structure business process activities from text input from end users, which are then converted into BPMN diagrams using a custom generation framework. The evaluation results demonstrate the system's accuracy with an average precision of 80%, recall of 76%, and F1 score of 78%. These findings outline the potential of using advanced language models to streamline business process modelling, offering significant improvements in accuracy and efficiency. The research concludes by suggesting enhancements for future iterations, including fine-tuning with advanced models and expanding support for complex BPMN elements, aiming to further optimize workflow for organizations.

关键词： Training Accuracy Process modeling Large language models Computational modeling Organizations Writing Logic gates User experience Robustness

来源：评论

学校读者我要写书评

暂无评论

Data engineering and AI-Powered Skin Cancer Identification for Healthcare Applications 28th

Data Engineering and AI-Powered Skin Cancer Identification f...

引用

28th International Conference on Knowledge Based and Intelligent information and engineering systems, KES 2024

作者： Ahmed, Imran Ahmad, Misbah Chehri, Abdellah Jeon, Gwanggil School of Computing and Information Science Anglia Ruskin University Cambridge United Kingdom Animal and Agriculture Department Hartpury University Gloucester United Kingdom Centre for Machine Vision Bristol Robotics Laboratory University of the West of England Bristol United Kingdom Canada Department of Embedded Systems Engineering Incheon National University Incheon Korea Republic of

Skin cancer diagnosis, a critical task in the medical domain, can be revolutionized through the application of advanced deep-learning techniques. This work investigates the efficacy of Convolutional Neural Networks (CNNs) in the automated classification of skin cancer. The process begins with a comprehensive explanation of key CNN layers: Conv2D, MaxPool2D, Dropout, and Dense. The Conv2D layers employ learnable filters that transform localized image segments, while MaxPool2D contributes to downsampling, effectively reducing computational cost and overfitting risk. Integrating these layers enables the network to capture local and global characteristics, which is crucial for accurate classification. Adding Dropout layers enhances generalization and mitigates overfitting by introducing randomness during training. ReLU activation functions infuse non-linearity, and the Flatten layer facilitates the transition to fully connected layers. The proposed CNN architecture is meticulously designed considering filter counts, kernel sizes, and pooling dimensions. The trained model demonstrates promising performance by utilizing the HAM10000 dataset, encompassing diverse skin lesion images across seven classes. The CNN model's parameters and architecture are systematically presented, offering insights into its design rationale. The model undergoes optimization with the Adam optimizer and annealing techniques to facilitate convergence. The model's effectiveness is evaluated on validation and test datasets, demonstrating an accuracy of 78.55% and 76.49%, respectively, for skin cancer classification. Data augmentation strategies are introduced to enhance model generalization further. The results underscore CNN's potential as a robust tool for automating skin cancer diagnosis, aligning with the broader trend of leveraging deep learning for medical image analysis © 2024 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Air Quality Monitoring: A Brief Review of Federated Learning Advances

arXiv

引用

arXiv 2025年

作者： Yarham, Sara Behjati, Mehran Alobaidy, Haider A.H. Abdul Majeed, Anwar P.P. Zheng, Yufan Department of Computing and Information Systems School of Engineering and Technology Sunway University 47500 Malaysia Department of Information and Communications Engineering College of Information Engineering Al-Nahrain University Baghdad64046 Iraq Taicang Suzhou215400 China

Monitoring air quality and environmental conditions is crucial for public health and effective urban planning. Current environmental monitoring approaches often rely on centralized data collection and processing, which pose significant privacy, security, and scalability challenges. Federated Learning (FL) offers a promising solution to these limitations by enabling collaborative model training across multiple devices without sharing raw data. This decentralized approach addresses privacy concerns while still leveraging distributed data sources. This paper provides a comprehensive review of FL applications in air quality and environmental monitoring, emphasizing its effectiveness in predicting pollutants and managing environmental data. However, the paper also identifies key limitations of FL when applied in this domain, including challenges such as communication overhead, infrastructure demands, generalizability issues, computational complexity, and security vulnerabilities. For instance, communication overhead, caused by the frequent exchange of model updates between local devices and central servers, is a notable challenge. To address this, future research should focus on optimizing communication protocols and reducing the frequency of updates to lessen the burden on network resources. Additionally, the paper suggests further research directions to refine FL frameworks and enhance their applicability in real-world environmental monitoring scenarios. By synthesizing findings from existing studies, this paper highlights the potential of FL to improve air quality management while maintaining data privacy and security, and it provides valuable insights for future developments in the field. Copyright © 2025, The Authors. All rights reserved.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Analysis of Skin Cancer Classification with Convolutional Neural Networks for E-Health Applications

Data-Driven Analysis of Skin Cancer Classification with Conv...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Ahmed, Imran Ahmad, Misbah Chehri, Abdellah Jeon, Gwanggil Anglia Ruskin University School of Computing and Information Science Cambridge United Kingdom Hartpury University Animal and Agriculture Department Gloucester United Kingdom University of the West of England Centre for Machine Vision Bristol Robotics Laboratory Bristol United Kingdom Department of Mathematics and Computer Science Canada Incheon National University Department of Embedded Systems Engineering Incheon Korea Republic of

ISBN: (纸本)9798350351255

This study explores the effectiveness of Convolutional Neural Networks (CNNs) in automatically classifying skin cancer for e-health applications. The trained model showcases impressive performance by leveraging the HAM10000 dataset, which includes a wide range of skin lesion images from seven different classes. The parameters and architecture of the CNN model are presented in a systematic manner, providing valuable insights into the reasoning behind its design. The model is optimized using the Adam optimizer and annealing techniques to ensure efficient convergence. The model's performance is assessed on validation and test datasets, showcasing an accuracy of 78.55% and 76.49%, respectively, for skin cancer classification. This study highlights the significant potential of CNN as a powerful tool for automating the diagnosis of skin cancer, which is in line with the growing trend of using deep learning for medical image analysis. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

FDD based Cell-free massive MIMO with angular reciprocity over rician fading channels

引用

Telecommunication systems 2025年第3期88卷 1-18页

作者： Hassan, Beenish Baig, Sobia Aslam, Saad Tahzeeb, Shahab Hasan, Syed Faraz Department of Electrical Engineering The Islamia University of Bahawalpur Bahawalpur Pakistan Electrical Engineering Department College of Engineering Qassim University Unaizah Saudi Arabia School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Malaysia Department of Computer and Information Systems Engineering NED University of Engineering and Technology Karachi Pakistan Directorate of Research Services University of New England Armidale Australia

We present a combined angle reciprocity and Rician K factor based feedback for up/downlink scenarios using MMSE estimator for frequency division duplex (FDD) based massive Multiple Input Multiple Output (MIMO) system. It considers phase variation for spatially correlated Rician fading channel and also takes into account the phase shift in the line-of-sight component of Rician channel that is incurred due to user mobility and/or phase noise. The cell-free massive MIMO system has largely been implemented in the context of time division duplex (TDD) systems. However, FDD is still prevalent in communication standards and therefore, it is essential to assess its performance for FDD based channel estimation schemes in a typical cell-free massive MIMO environment. To begin with, we present an analysis of estimation schemes including the minimum mean square error (MMSE), linear MMSE (LMMSE), and least-square (LS) in terms of their spectral efficiency, using prior channel knowledge at the access points. We also present an angle-based beamforming technique that combines the quantized channel feedback based on Rician K factor with angle reciprocity-based channel estimates. The multipath channel estimation for MMSE and LMMSE schemes is also presented and simulation results are provided that show the superior performance of proposed angle and feedback MMSE over the LMMSE and theoretical MMSE schemes. Numerical simulations of the overall system confirm that the combined angular reciprocity and feedback-based MMSE estimates perform better with a value of $$12.6\%$$ for spectral efficiency and $$27\%$$ for energy efficiency, thus, producing an overall improved system performance compared to the conventional FDD based estimation schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating large language model-based agents into a virtual patient chatbot for clinical anamnesis training

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2481-2491页

作者： Laverde, Nicolas Grévisse, Christian Jaramillo, Sandra Manrique, Ruben Department of Systems and Computing Engineering Universidad de los Andes Bogotá Colombia Department of Life Sciences and Medicine University of Luxembourg Esch-sur-Alzette Luxembourg Medicine Faculty Universidad de los Andes Bogotá Colombia

Effective communication is crucial for trust-building, accurate information gathering, and clinical decision-making in healthcare. Despite its emphasis in medical curricula, traditional training methods, such as role-playing with standardized patients, remain costly, logistically complex, and fail to replicate real-life scenarios. Simulation-based training enhances communication and reasoning skills, but novice learners often struggle due to underdeveloped reasoning processes. Furthermore, limited access to asynchronous, autonomous simulated patient interactions restricts personalized practice. Virtual patient models offer scalable solutions with interactive scenarios and tailored feedback, but high development costs and resource demands hinder their widespread adoption. To address these challenges, virtual patient systems powered by Large Language Models (LLMs) have emerged as a promising tool. These generative agents simulate human-like behavioral responses by leveraging LLM capabilities, cognitive mechanisms, and contextual memory retrieval. A tool was developed allowing students to select clinical cases and interact with a chatbot simulating a patient role. Teachers can also create custom cases. Evaluations showed that the agent provided consistent, plausible responses aligned with case descriptions and achieved a Chatbot Usability Questionnaire (CUQ) score of 86.25/100. Our results show that this approach enables flexible, repetitive, and asynchronous practice while offering real-time feedback. © 2025 The Authors

关键词： Medical education

来源：评论

学校读者我要写书评

暂无评论

Case-based Explanation of Classification Models for the Detection of SQL Injection Attacks 31

Case-based Explanation of Classification Models for the Dete...

引用

Workshops at the 31st International Conference on Case-Based Reasoning, ICCBR-WS 2023

作者： Recio-Garcia, Juan A. Orozco-Del-Castillo, Mauricio G. Soladrero, Jose A. Tecnológico Nacional de México IT de Mérida Department of Systems and Computing Merida Mexico Association for the Advancement of Artificial Intelligence Mexico Department of Software Engineering and Artificial Intelligence Instituto de Tecnologías del Conocimiento Universidad Complutense de Madrid Spain

This paper investigates the interpretability of various machine learning models in the context of detecting SQL injection attacks. The models under investigation include decision trees, multi-layer perceptron, random forests, support vector machines, ADA Boost, naive Bayes, and quadratic discriminant analysis. Our main objective is to gain insights into how these models make decisions when classifying SQL commands as either legitimate or potentially malicious. To achieve this, we employ a set of commonly used features from the literature to train and evaluate the models. By prioritizing explainability, our aim is to uncover the underlying factors and decision rules that drive the models’ predictions. Through this research, we seek to bridge the gap between model accuracy and human understanding, thereby facilitating the practical application of machine learning models in real-world security scenarios. The findings of this study contribute to the development of a case-based explanation system that provides valuable insights for cybersecurity practitioners and researchers. © 2023 CEUR-WS. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

MFANet: Mixed Feature Attention Network for Port Lane Detection 42

MFANet: Mixed Feature Attention Network for Port Lane Detect...

引用

42nd Chinese Control Conference, CCC 2023

作者： Zhang, Jinwei Su, Jinya Yi, Dewei Yang, Jun Ministry of Education The School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing210096 China University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

ISBN: (纸本)9789887581543

With the advancement of industrial automation and artificial intelligence technology, unmanned port autonomy has gained increasing attention. Port automatic driving technology is a critical component of unmanned autonomous systems, enabling rubber tire gantry cranes (RTGs) to autonomously navigate by detecting port lanes and implementing control commands. In this study, a deep learning-based method is proposed for detecting port lanes in complex port scenes. The method employs the Inception module and attention mechanism to enhance lane feature extraction, and a structural loss is introduced to explicitly constrain the detection results and incorporate the prior characteristics of port lanes. A novel Mixed Feature Attention Network (MFANet) is proposed to implement the method for port lane detection. Experimental results demonstrate that MFANet effectively improves the accuracy of port lane detection while maintaining high computational efficiency. Furthermore, the performance of MFANet is evaluated in a real-world application scenario. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Development of a Universal RNA Dual-Terminal Labeling Method for Sensing RNA-Ligand Interactions

引用

CCS Chemistry 2023年第1期5卷 221-233页

作者： Longhuai Cheng Dejun Ma Jie Zhang Xueying Kang Yang Wu Yi Zhao Long Yi Zhen Xi State Key Laboratory of Elemento-Organic Chemistry Department of Chemical BiologyCollege of ChemistryNational Pesticide Engineering Research CenterCollaborative Innovation Center of Chemical Science and EngineeringNankai UniversityTianjin 300071 State Key Laboratory of Organic-Inorganic Composites and Beijing Key Laboratory of Bioprocess Beijing University of Chemical Technology(BUCT)Beijing 100029 Key Laboratory of Intelligent Information Processing Research Center for Ubiquitous Computing SystemsInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190

Dual labeling of an RNA can provide Förster resonance energy transfer(FRET)sensors for studying RNA folding,miRNA maturation,and RNA-protein ***,we report the development of a highly efficient strategy for direct dual-terminal labeling of any RNA of *** explored new Michael cycloaddition for facile labeling of 5′-terminal RNA with improved *** chemical tetrazinylation of RNA at the 3′-terminus was achieved with the highly efficient and catalysis-free tetrazine-cycloalkyne *** single-terminal labeling methods were combined for dual-terminal labeling of an RNA including short hairpin RNA,pre-miRNA,riboswitch,and noncoding ***,these dual-labeled RNA-based FRET sensors were used to monitor RNA-ligand interactions in vitro and in live *** is anticipated that these universal RNA labeling strategies will be useful to study RNA structures and functions.

关键词： dual labeling Förster resonance energy transfer sensor Michael cycloaddition tetrazinecycloalkyne ligation RNA-ligand interaction

来源：评论

学校读者我要写书评

暂无评论

Classifying Textual Sentiment Using Bidirectional Encoder Representations from Transformers

Classifying Textual Sentiment Using Bidirectional Encoder Re...

引用

International Conference on Computer and Information Technology (ICCIT)

作者： Shawly Ahsan Fairooz Tasnia Nafisa Tabassum Avishek Das Mohammed Moshiul Hoque Nazmul Siddique Department of Computer Science & Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh School of Computing Engineering and Intelligent Systems Ulster University UK

Textual sentiment analysis (TSA) has gained significant attention recently for its wide-ranging applications across various research domains and industries. However, most existing research and sentiment analysis tools are primarily tailored for English texts. The unique linguistic complexities of the Bengali language, coupled with a paucity of comprehensive resources and tools, pose distinctive challenges for TSA in Bengali. This paper introduces an intelligent approach, leveraging transformer-based learning techniques by harnessing the potent capabilities of self-attention mechanisms for dealing with Bengali sentences containing ungrammatical structures or local dialects. To tackle the downstream TSA task in Bengali, this work explores a range of machine learning (ML), deep learning (DL), and transformer-based baselines. Experimental results reveal that the Bangla BERT model outperforms the other baselines, achieving the highest weighted f 1 -score of 0.69.

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：