检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Sundar, Koushik Bhavani, M. Jaeyalakshmi, M. Vijayakumar, R. Citibank NA Jersey CityNJ United States Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Computer Science and Design Tamil Nadu Chennai India

ISBN: (纸本)9798331522988

A new era of massive and varied data repositories has been brought about by the digitization of documents, necessitating the creation of reliable systems for interpreting and classifying scanned documents. Using deep learning capabilities, this study investigates state-of-the-art methods for document analysis and classification. Optical character recognition (OCR) systems have been revolutionized by deep learning models, especially CNN and transformer-based architectures. These algorithms are remarkably accurate at extracting text from scanned documents, independent of language, font size, or style. Transformer models perform well in comprehending textual material, whereas CNNs are skilled at extracting discriminative features from document images. Utilizing transfer learning approaches to maximize model performance while minimizing the requirement for large amounts of labelled data has been the subject of recent study. Deep learning has also resulted in notable advancements in Named Entity Recognition within scanned documents. Document organization and comprehension have been made easier by the remarkable accuracy with which names, dates, and locations can be extracted by bi-directional LSTMs, BERT-based models, and their variations. Improved document processing, organization, and accessibility are made possible by the approaches covered here, which have a wide range of applications in the financial, medical, and legal services sectors. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition in Real Time for Personalized Healthcare Using Digital Twin Approach 2

Emotion Recognition in Real Time for Personalized Healthcare...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Karthikeyani, B. Yuvaraj, D. Parimalam, T. Parthasarathi, P. Nandha Arts and Science College India CollegeGobi India Department of Computer Science and Design Kongu Engineering College Perundurai India Department of Computer Science Nandha Arts and Science College Perundurai India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India

ISBN: (纸本)9798350383867

Facial Emotional Recognition (FER) in healthcare can help to monitoring the patient by analyzing the emotional state of the patient through various emotional states. In medical industry it can help to trace the emotional state changes and diagnosis the pattern which are mapped respective to the patient's history. Digital twin technology is transforming healthcare systems and improving patient care, clinical operations, predictive analytics, and training and simulation by integrating virtual simulations and emerging analytic mechanism through ML and DL techniques. By allocating resources, monitoring workflow, and providing individualized patient care, these algorithms reduce healthcare operations and assist in determining an individual's risk. Since FER has lot of technical challenges like illumination, obstruction issues also high implementation cost. To solve these issues, the FER system will embed with the digital twin technology to provide a better result from real time sensing cameras also analyzing the result and guiding for a better treatment of an individual. We propose a system of end to end framework which produces best results in minimum amount of time with maximum accuracy. This real time implementation will help all the healthcare centers/industry to study an individual's health status as well as early prediction of diseases with effective treatment steps. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Diffuse Your Data Blues: Augmenting Low-Resource Datasets via User-Assisted Diffusion 25

Diffuse Your Data Blues: Augmenting Low-Resource Datasets vi...

引用

30th International Conference on Intelligent User Interfaces, IUI 2025

作者： Sinha, Yashaswi Shanmugam, Shravan Sahu, Yash Kumar Mukhopadhyay, Abhishek Biswas, Pradipta Department of Design and Manufacturing Indian Institute of Science Karnataka Bengaluru India Computer Science and Engineering Amity University West Bengal Kolkata India

ISBN: (纸本)9798400713064

Mixed reality applications in industrial contexts necessitate extensive and varied datasets for training object detection models, yet actual data gathering may be obstructed by logistical or cost issues. This study investigates the implementation of generative AI methods to work on this issue for mixed reality applications, with an emphasis on assembly and disassembly tasks. The novel objects found in industrial settings are difficult to describe using words, making text-based models less effective. In this study, a diffusion model is used to generate images by combining novel objects with various backgrounds. The backgrounds are selected where object detection in specific applications has been ineffective. This approach efficiently produces a diverse range of training samples. We compare three approaches: traditional augmentation methods, GAN-based augmentation, and Diffusion-based augmentation. Results show that the diffusion model significantly improved detection metrics. For instance, applying diffusion models to the dataset containing mechanical components of a pneumatic cylinder raised the F1 Score from 69.77 to 84.21 and the mAP@50 from 76.48 to 88.77, resulting in an increase in object detection performance, with a 67% less dataset size compared to the traditional augmented dataset. The proposed image composition diffusion model and user-friendly interface further simplify dataset enrichment, proving effective for augmenting data and improving the robustness of detection models. © 2025 Copyright held by the owner/author(s).

关键词： Synthetic Dataset

来源：评论

学校读者我要写书评

暂无评论

Multilingual Exploration of the Kambaramayana: Analyzing Tamil Translations in Telugu, Malayalam, and Kannada Using mBERT and DistilBERT 1

Multilingual Exploration of the Kambaramayana: Analyzing Tam...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Swathi, K. Kamalam, G.K. Hemalatha, S. Jothimani, K. Dharshini, N. Aadhishri, A. Kongu Engineering College Department of Computer Science and Design Tamil Nadu India Kongu Engineering College Department of Information Technology Tamil Nadu India Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356816

An essential and basic aspect of our existence are our emotions. Our behaviors and words reflect our feelings, even though they are not instantly obvious. This research looks at the multilingual features of the Kambaramayana, with a concentration on Tamil translates into Telugu, Malayalam, and Kannada. We study how linguistic and cultural subtleties show across translations using a varied dataset. We do a comparison study using sophisticated multilingual language models, specifically mBERT and DistilBERT, to identify semantic variances and similarities. We hope to uncover the subtle interplay among language and culture in literary text transmission by investigating vocabulary, grammar, and cultural allusions. Our findings not only improve the accuracy of cross-lingual text analysis, but also highlight the Ramayana's lasting relevance among South Indian language communities. The experiments clearly reveal that mBERT outperforms DistilBERT in emotion analysis tasks between languages. © 2024 IEEE.

关键词： Measurement Vocabulary Translation Accuracy Text analysis Semantics Robustness Multilingual Grammar Cultural differences

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach for Number Plate Detection 7

A Novel Deep Learning Approach for Number Plate Detection

引用

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Kavitha, M.N. Saranya, S.S. Santhiya, E. Swetha, D. Dharshika, R. Department of Computer Science and Engineering Kongu Engineering College TamilNadu Erode India Bachelor of Science - Computer Systems and Design Kongu Engineering College TamilNadu Erode India

ISBN: (纸本)9781665464086

The number of people in the world now is estimated to be 1.38 billion. As the population of India grows, there is a chance that there will be twice as many automobiles on the road. Numerous methods have been put out for finding and identifying the license plates of automobiles using various technologies and procedures. The license plate detection and identification accomplished in the paper is done by OpenCV and Tensor flow for the detection of the license plate. The second set makes use of CNN (Convolutional Neural Network). First, the input image has been taken and pre-processed. Next, the number plate has been detected and contours are extracted. Finally, the characters have been recognized and the model has been trained using CNN for predicting the characters in the number plate. Comparing to other TensorFlow projects, this system provides the highest accuracy. © 2023 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Real-Time Facial Recognition System for Secure College Bus Transport using Deep Learning Techniques 3

Real-Time Facial Recognition System for Secure College Bus T...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kavitha, M.N. Saranya, S.S. Pragatheeswari, E. Priya, N. Kaviya Ranjith, S.R. Vanchivel, N. Rahul Kongu Engineering College Department of Computer Science and Design Tamil Nadu India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu Erode India Kongu Engineering College Department of Csd Tamil Nadu India

ISBN: (纸本)9798331509675

The proposed system aims to enhance student transportation security through real-time face detection and recognition. Leveraging the MTCNN framework for accurate face detection and the FaceNet model for reliable face recognition, the system ensures only authorized students can board designated buses by comparing captured faces with a pre-registered database. In case of mismatches, alerts are triggered to notify drivers and authorities. Additionally, parallel implementation of Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers improves authentication accuracy. The system's deep learning-based architecture ensures robust performance under varying environmental conditions and supports continuous learning for long-term reliability. © 2025 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Beta Function Based Compression Method for Crop Image Using Singular Vector Sparse Reconstruction

引用

SN computer science 2025年第4期6卷 1-13页

作者： Mishra, Deepak Kumar, Anil Rathore, Vijaypal Singh Discipline of Electronics and Communication Engineering PDPM Indian Institute of Information Technology Design and Manufacturing Jabalpur 482005 India Discipline of Computer Science & Engineering PDPM Indian Institute of Information Technology Design and Manufacturing Jabalpur 482005 India

In this research, a new hybrid compression method is introduced, which is based on Beta function and singular vector sparse reconstruction (SVSR). The proposed technique incorporates wavelet filters whose coefficients are obtained from the beta function and its derivatives. These filters are employed to decompose the original crop image, and SVSR is used to enhance the compression efficiency. The efficacy of the suggested compression method is examined by testing it on different grayscale and color crop images and compared the results to other existing approaches. The assessment is based on fidelity parameters, including compression ratio (CR), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR). The Beta wavelet filters demonstrate superior compression ratios of 1.5% and 16.4% compared to Db4 and Bior4.4 wavelet filters, respectively. Additionally, they exhibit 47.8% and 80.13% higher compression ratios than SVSR and SVD, respectively, while maintaining approximately similar reconstruction quality. Experimental results show that the suggested compression technique achieves better performance than existing methods in terms of both image quality and compression efficiency. Therefore, it is concluded that this approach can be effectively utilized for grayscale and color crop image compression. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Beta wavelet Image compression Singular vector sparse reconstruction

来源：评论

学校读者我要写书评

暂无评论

Smart Health Monitoring: The Application of IoT and AI For Real-time monitoring and patient centric care

Smart Health Monitoring: The Application of IoT and AI For R...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Sharma, Mansi Sharma, Ankush Kumar, Praveen Department of Computer Science and Design Wardha India Administration and Research Ssgmce Department of Business Shegaon Shegaon India Department of Computer Science and Medical Engineering Wardha India

ISBN: (纸本)9798331508432

The combination of artificial intelligence (AI) and the internet of things (IoT) resulted in the era of smart health monitoring. This article explores the seamless integration of IoT and AI technologies to provide real-time monitoring and patient-centered treatment in an evolving healthcare environment. Various real-time health data focuses from Internet of Things (IoT) gadgets, such as medical-grade screens and wearable sensors, offer new points of view on a person's physiological parameters and behaviors. These gadgets serve as the essential information collectors, quickly sending information to centralized stages. These systems' AI calculations filter approaching information at a speed and exactness never before achievable, permitting for the early discovery of patterns and irregularities. IoT and AI work together to extend the adequacy of information preparing and empower proactive, individualized healthcare interventions. Machine learning has the potential to anticipate potential health issues and give custom-made interventions by utilizing different datasets for model training. This approach advances a move from responsive to preventive healthcare practices. This approach is especially supportive within the administration of constant ailments since it can essentially make strides understanding results on the off chance that intervene early. With smart health monitoring, there are execution issues related to information security, ethics, and interoperability. The paper addresses these issues and offers potential arrangements to ensure the suitable integration of IoT and AI innovation in healthcare settings. With a center on values changing over time, this article offers a comprehensive analysis of worldly designs utilizing scatter plots. To imagine these worldly elements, we utilize a dataset that contains verifiable records of esteem changes for diverse factors and districts. Through investigation, we reveal designs, patterns, and peculiarities within the info

关键词： Artificial Intelligence IoT Machine learning Smart Health Monitoring

来源：评论

学校读者我要写书评

暂无评论

Deep symbolic regression for numerical formulation of fundamental period in concentrically steel-braced RC frames

引用

Asian Journal of Civil engineering 2024年第6期25卷 4725-4744页

作者： Rahman, Taimur Sultana, Shamima Ahmed, Tanjir Momin, Md. Farhad Provasha, Afra Anam Department of Civil Engineering World University of Bangladesh Dhaka Bangladesh Department of Computer Science & amp Engineering University of Asia Pacific Dhaka Bangladesh Structural Design Engineer Doric Design and Architect Dhaka Bangladesh

This research explores the use of Deep Symbolic Regression (DSR) to develop a sophisticated predictive model for the fundamental period of vibration in concentrically steel-braced reinforced concrete (RC) frames. Traditional empirical models often overlook complex interactions within structural dynamics during seismic events, a gap this study addresses by deriving tailored equations for various bracing configurations such as Cross bracing, Diagonal bracing, and Chevron bracing. The model development incorporates an iterative refinement process utilizing DSR techniques to enhance accuracy and applicability in predicting seismic responses. Further refinement and optimization are achieved using the L-BFGS-B algorithm, ensuring robustness and adherence to safety standards. Validation against actual structural data reveals that our proposed equations achieve high predictive accuracy, with R-squared values up to 0.8247 and RMSE values as low as 0.2119, consistently presenting lower error metrics across various configurations compared to those found in established seismic design standards, such as ASCE, Eurocode, and Japan’s Building Standards. Comparative analyses and Bland–Altman plots confirm that the models not only match but often surpass the accuracy of traditional formulas, validating their potential as reliable tools in structural engineering for earthquake resilience planning. The findings demonstrate DSR’s potential to revolutionize traditional practices in formulating empirical equations, offering a scientifically rigorous, data-driven methodology for more accurately predicting the dynamic responses of structures under seismic loads. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Concentric bracing Deep symbolic regression (DSR) Fundamental period of vibration Machine learning (ML) Numerical formulation Steel-braced reinforced concrete frames

来源：评论

学校读者我要写书评

暂无评论

RAG-Enhanced Large Language Model for Intelligent Assistance from Web-Scraped Data 9

RAG-Enhanced Large Language Model for Intelligent Assistance...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Kanataria, Nikunj Patel, Kunj Pareshbhai Patel, Hetul Niteshbhai Goel, Parth Patel, Krishna Garg, Dweepna Devang Patel Institute of Advance Technology and Research Computer Science & Engineering Department Changa Anand India Computer Science & Design Department Vallabh vidyanagar Anand India

ISBN: (纸本)9798350377972

The explosion of online information necessitates efficient and accurate methods for retrieving and analyzing relevant data. This research proposes a novel framework that leverages Retrieval-Augmented Generation (RAG) techniques to address this challenge. The framework utilizes web scraping to extract information from various sources and employs advanced language models like Llama 3, Mistral, and Gemini to generate concise and informative summaries. Furthermore, the framework incorporates embedding models such as nomic-embed-text and Gemini embedding model text embedding 001 to create semantic representations of the retrieved data and utilize FAISS for efficient indexing and retrieval. The RAGAS framework was used to evaluate the performance of different LLMs, with Llama 3.1 demonstrating the highest accuracy at 86.67%. This framework has significant implications for various applications, including personalized education, where it can be used to provide students with tailored learning materials and personalized tutoring experiences. © 2024 IEEE.

关键词： Semantics

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：