检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems and computational Networks, ICISCN 2025

作者： Yuvaraj, S. Chenni Kumaran, J. Vinston Raja, R. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

The investigation aims to evaluate the performance of machine learning techniques, particularly the XGBoost regression method, for stock price prediction with the help of technical indicators. The research targets the adjusted closing price to reduce the autocorrelation problem in time series. The Five Days and Ten Days Exponential Moving Averages (EMA-5 and EMA-10) are involved in refining feature selection. The performance of the model was evaluated using different error metrics, namely, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2). The results indicate that the XGBoost model, combined with EMA-5 and EMA-10, achieves high predictive performance, obtaining an r2 value of 0.98. It implies that incorporating short-term EMAs into advanced machine learning techniques drastically improves stock price forecasting. © 2025 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

USR: Unrolled Super-Resolution with Deep Priors for Structured Illumination Microscopy

USR: Unrolled Super-Resolution with Deep Priors for Structur...

引用

3D Image Acquisition and Display: Technology, Perception and Applications, 3D, COSI, DH, FLatOptics, IS, pcAOP 2023 - Part of Imaging and Applied Optics Congress 2023

作者： Dajkhosh, S. Parisa Hossain, Mazharul Preza, Chrysanthe Computational Imaging Research Laboratory Electrical and Computer Engineering Department United States Computer Science Department The University of Memphis MemphisTN United States

We introduce a method for enhancing the resolution of Structured Illumination Microscopy images. It uses a deep prior network, unrolled with a model-based analytical process to improve performance, maintain structural... 详细信息

ISBN: (纸本)9781957171289

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Educational Digital Twin: Tackling Complexity in Educational Big Data

Educational Digital Twin: Tackling Complexity in Educational...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Huang, Luwen Willcox, Karen E. University of Texas Department of Computer Science Austin United States University of Texas Oden Institute for Computational Engineering & Sciences Austin United States

ISBN: (纸本)9798350362480

"Everything is bigger in Texas"and this includes the big data challenges of the state's educational system. But just as big is the opportunity for digital twin technologies to improve decision-making in education, with potential to improve student outcomes. This paper formulates an Educational Digital Twin, a novel approach to understanding, modeling, and analyzing educational data to address the complexities inherent in student pathways. By "student pathways", we refer to the joint facets of student behavior - evolving dynamically over time and encompassing not only course enrollments but also behavioral and academic factors. Unlike traditional approaches that rely on static analyses of historical data, the Educational Digital Twin applies the digital twin paradigm to model these pathways as a living construct that dynamically evolves alongside the physical world. At the heart of the Educational Digital Twin is a knowledge graph that organizes data into a semantic structure. By employing graph-theoretic methods, we manipulate this structure to derive multi-granular insights that inform decision-making. Our evaluation demonstrates how the Educational Digital Twin not only facilitates the dynamic integration of new data but also scales efficiently to handle complex datasets covering millions of students across hundreds of demographic and academic dimensions. © 2024 IEEE.

关键词： Complex networks Digital twin Educational big data Graph modeling Network visualization

来源：评论

学校读者我要写书评

暂无评论

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Few-shot Prompting for Pairwise Ranking: An Effective Non-Pa...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

ISBN: (纸本)9798891761681

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024 Association for computational Linguistics.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Synergistic Brain Tumor Detection: Anisotropic Diffusion, with SVM 3

Synergistic Brain Tumor Detection: Anisotropic Diffusion, wi...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Alphonsa, J. Kumari, V. Sheeja Roslin Dayana, K. Saveetha School of Engineering Simats University Department of Computational Intelligence Chennai600025 India R.M.D Engineering College Department of Computer Science Chennai601206 India

ISBN: (纸本)9798331518592

Accurate finding of the tumors in MRI images is crucial for effective prevention and cure. Here, an innovative approach integrating anisotropic diffusion filtering, U-net-based segmentation, CNN feature extraction, and SVM classification is proposed and optimized by Bayesian techniques. The method starts with anisotropic diffusion filtering to improve image quality by dropping noise while conserving significant basic particulars. The tumor regions are segmented using the U-Net architecture, which is known for its robust performance in segmenting medical images due to its encoder-decoder structure and skip connections. Feature extraction is performed using a Convolutional Neural Network (CNN) that finds some complex patterns, and features associated with tumors. An SVM classifier is then used to distinguish between tumor and non-tumor regions based on these features. To further refine the model, Bayesian optimization is used to fine-tune the hyperparameters of the SVM and other components of the pipeline. The proposed method shows significant improvements in detection accuracy and robustness compared to conventional techniques. Bayesian optimization plays an important part in cultivating classification performance by systematically exploring and optimizing the hyperparameters. This integrated approach provides a powerful and reliable solution for brain tumor detection with great potential for clinical healthcare applications where precision and early diagnosis are critical. The results not only advance the current state of tumor detection but also provide a solid foundation for future research to optimize diagnostic methods. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Irregular luggage classification experiments using data from Tromso airport

Irregular luggage classification experiments using data from...

引用

2023 International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Jansson, Andreas Dyroy Bremdal, Bernt Arild Remman, Espen UiT the Arctic University of Norway Department of Computer Science and Computational Engineering Narvik Norway Chronos As Oslo Norway

ISBN: (纸本)9798350322972

This paper examines the current state-of-the-art in object tracking and detection in the context of baggage handling systems using a variety of technologies, with special interest in image classification. Data collection at Tromso Airport using simple and inexpensive equipment in order to capture images of different types of luggage will be described. Furthermore, a selection of three relevant techniques for image classification will be investigated, and experiments will be conducted to detect irregular and potentially problematic bags in the collected dataset. Finally, recommendations for use cases and an interface to an intelligent baggage handling system will be proposed. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Digital Twin: Graph Formulations for Managing Complexity and Uncertainty 10

Digital Twin: Graph Formulations for Managing Complexity and...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Huang, Luwen Kapteyn, Michael Willcox, Karen E. University of Texas at Austin Department of Computer Science United States University of Texas at Austin Oden Institute for Computational Engineering and Sciences United States

ISBN: (纸本)9798331520861

This paper articulates the importance of graphical models and graph-based methods as fundamental enablers of Digital Twins. Graph-based representations are well known to be suited for describing complex systems where the connections between entities are as important as the entities themselves. The interconnections within and across data, models, and decisions are central to a Digital Twin's value. Not only does a graph emphasize the scalable representation of such interrelationships, it also provides a natural mathematical setting for addressing uncertainty and complexity - arguably the two biggest barriers to scalable deployment and adoption of Digital Twins. We discuss how recent advances in theory and algorithms for large-scale knowledge graphs and graphical models can be combined in a multi-layered formulation to provide a powerful foundation for achieving scalable Digital Twins for complex systems. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Driven Cardiovascular Disease Prediction Among Male Senior Adults

Machine Learning Driven Cardiovascular Disease Prediction Am...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Elango, Poongothai Kasthuri, A. Mariammal, G. Saravanan, T.R. Srm Institute Of Science And Technology Department Of Computational Intelligence Chennai India Arulmigu Subramania Swamy Arts And Science College Department Of Computer Science Thoothukudi Vilathikulam India Vel Tech Rangarajan Dr. Sagunthala R & D Institute Of Science And Technology Department Of Computer Science And Engineering Chennai Avadi India Srm Institute Of Science And Technology Department Of Computational Intelligence Chennai Kattankulathur603203 India

ISBN: (纸本)9798350364828

The heart is a critical organ at the heart of the circulatory system, acting as a powerful muscle pump that keeps life going by constantly pumping blood throughout the body. Heart illnesses, often known as cardiovascular diseases (CVDs), are a broad category of ailments that affect the heart and blood arteries. The severity of these illnesses ranges from minor to life-threatening. Heart disease prediction using machine learning is essential for improving patient care, reducing healthcare costs, and addressing a major public health challenge. It leverages advanced data analytics to enable early detection, personalized treatment, and more efficient allocation of resources, ultimately leading to better health outcomes and a positive impact on public health. Heart disease prediction involves the use of machine learning and data analysis techniques to assess an individual's risk of developing heart-related conditions. This process begins with collecting a wide range of medical data from kaggle for analysis, including demographics, medical history, and clinical measurements. In this analysis, Random forest is used as a feature estimate for the study of cardiovascular disease prediction for male senior adults in the age group of 37 to 70 years since we analyzed from the existing research that it performs better for heart disease. Recursive Feature Elimination with Cross-Validation (RFECV) is used to assess feature importance. It trains the model using logistic regression and achieves an accuracy of 82.4%. Predicting cardiovascular health among senior male adults is of utmost importance to proactively manage and mitigate the risks associated with these conditions. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Crop Yield Prediction Using Multimodal Meta-Transformer and Temporal Graph Neural Networks

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第2期2卷 545-553页

作者： Sarkar, Somrita Dey, Anamika Pradhan, Ritam Sarkar, Upendra Mohan Chatterjee, Chandranath Mondal, Arijit Mitra, Pabitra Indian Institute of Technology Kharagpur Centre for Computational and Data Sciences Kharagpur721302 India Indian Institute of Technology Kharagpur Department of Industrial and Systems Engineering Kharagpur721302 India Indian Institute of Technology Kharagpur Department of Agricultural and Food Engineering Kharagpur721302 India Indian Institute of Technology Patna Department of Computer Science and Engineering Patna801106 India Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur721302 India

Crop yield prediction is a crucial task in agricultural science, involving the classification of potential yield into various levels. This is vital for both farmers and policymakers. The features considered for this task are diverse, including weather, soil, and historical yield data. Recently, plant images captured in different modalities, such as red-green-blue, infrared, and multispectral bands, have also been utilized. Most of these data are inherently temporal. Integrating such multimodal and temporal data is advantageous for yield classification. In this work, a deep learning framework based on meta-transformers and temporal graph neural networks has been proposed to achieve this goal. Meta-Transformers allow the modeling of multimodal interactions, while temporayel graph neural networks enable the utilization of time sequences. Experimental results on the publicly available EPFL multimodal dataset demonstrate that the proposed framework achieves a high classification accuracy of nearly 97%, surpassing other state-of-the-art models, such as long short-term memory networks, 1-D convolutional neural networks, and Transformers. In addition, the proposed model excels in accuracy metrics, with a precision of approximately 98%, an F1-Score of 91%, and a recall of 94% in crop yield prediction. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

A Detailed Structured Monitoting System for ICU Patient Mortality rate by using AI Algorithm 5

A Detailed Structured Monitoting System for ICU Patient Mort...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Joshi, Shivani Kumar, Rajiv Rai, Vipin Dwivedi, Avinash Tripathi, Vikash Chandra G L Bajaj Institute of Technology and Management Department of Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Nvidia Ai and Learning & Research Center Department of Applied Computational Science and Engineering Greater Noida India Galgotias University Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350383522

The complexity and seriousness of diseases in ICU patients, though, make it difficult for medical practitioners to identify high-risk patients who may face irreversible harm. With ANN (Artificial Neural Network), this study will provide an ICU admission prediction model to help identify high-risk patients at an earlier stage. After collecting and analyzing extensive data from various perspectives including demographics, medical history, vital signs, test results and treatment modalities, exploratory data analysis has been conducted. These are used as markers on how statistical techniques and machine learning algorithms can be used to predict mortality among critically ill patients. Consequently, the parameters are designed within the ANN model to create a predictive model that will be able to effectively classify those at higher risk. Advanced machine learning algorithms together with modern tools such as deep learning techniques will aid in the prompt analysis of complex information for accurate forecasts by this predictive model. The ANN model's training set will include a large dataset of ICU patients so that it can become reliable and valid. This makes the predictive model developed capable of accurately identifying high risk cases expeditiously © 2024 IEEE.

关键词： accuracy Artificial Neural Networks (ANN) exploratory data analysis high-risk patients ICU patient admission medical technology mortality outcomes periodic updates prediction model

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：