检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Nakahara, Yuta Saito, Shota Ichijo, Naoki Kazama, Koki Matsushima, Toshiyasu Center for Data Science Waseda University Tokyo Japan Faculty of Informatics Gunma University Gunma Japan Dept. of Pure and Applied Math. Waseda University Tokyo Japan

In the field of decision trees, most previous studies have difficulty ensuring the statistical optimality of a prediction of new data and suffer from overfitting because trees are usually used only to represent prediction functions to be constructed from given data. In contrast, some studies, including this paper, used the trees to represent stochastic data observation processes behind given data. Moreover, they derived the statistically optimal prediction, which is robust against overfitting, based on the Bayesian decision theory by assuming a prior distribution for the trees. However, these studies still have a problem in computing this Bayes optimal prediction because it involves an infeasible summation for all division patterns of a feature space, which is represented by the trees and some parameters. In particular, an open problem is a summation with respect to combinations of division axes, i.e., the assignment of features to inner nodes of the tree. We solve this by a Markov chain Monte Carlo method, whose step size is adaptively tuned according to a posterior distribution for the trees. Copyright © 2023, The Authors. 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

Comparison of 2D SURE and 3D CT imaging of cortical vessels in a rat kidney

Comparison of 2D SURE and 3D CT imaging of cortical vessels ...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Lauge Naur Hansen Hans Martin Kjer Mostafa Amin-Naji Nathalie Sarup Panduro Charlotte Mehlin Sørensen Carsten Gundlach Anders Bjorholm Dahl Jørgen Arendt Jensen Dept. of Health Technology Technical University of Denmark Kgs. Lyngby Denmark Dept. of Applied Mathematics and Computer Science Technical University of Denmark Kgs. Lyngby Denmark Dept. of Biomedical Sciences University of Copenhagen Copenhagen Denmark Dept. of Physics Technical University of Denmark Kgs. Lyngby Denmark

SUper-Resolution ultrasound imaging using the Erythrocytes (SURE) can visualize blood vessels at about 25 to 50 µm resolution, but validation is required to assess how accurately the vasculature and its morphology are represented. Previous work compared ultrasound imaging to maximum intensity projections (MIP) of micro-CT volumes at an insufficient voxel size of 22.6 µm. Here, a 5 µm voxel size micro-CT volume of a cortical region in an excised rat kidney was acquired to test the hypothesis that blood vessels down to 50 µm in diameter are detected with SURE imaging. For the micro-CT volume, the blood vessels were segmented by an intensity threshold, and local thickness estimates were computed using expanding spheres within the segmentation mask. An affine registration between the SURE image and the micro-CT volume was manually defined, and a MIP of the micro-CT volume across 2 mm from the ultrasound imaging plane was computed for vessels with diameter estimates greater than 50 µm. The SURE image depicts 12 cortical radial vessels with high intensities and 9 dimmer cortical radial vessels. Notably, the 12 high intensity vessels are also depicted in the micro-CT projection, but 5 cortical radial vessels and 2 arcuate blood vessels are only visible in the SURE image. Of the faintly depicted cortical radial vessels, 5 vessels are not readily matched to vessels in the micro-CT projection. On the other hand, the micro-CT projection contains 6 cortical radial vessel segments and 2 arcuate blood vessels not depicted in the SURE image. These discrepancies in the comparison may arise from the challenging registration of the ultrasound focus beam and the micro-CT volume that is complicated further by the different states of the imaged tissue. Despite these challenges, SURE depicts most vessels at least down to 50 µm and even resolves parallel vessels not visible in the micro-CT projection, thus highlighting its clinical potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AIM-HKR: AI-Driven Molecular Retrosynthesis Using Heterogeneous Knowledge Representations

AIM-HKR: AI-Driven Molecular Retrosynthesis Using Heterogene...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Alain Bertrand Bomgni Ribot Fleury Téné Ceskoutsé Kevin Jordan Njike Njingang Thomas Bouetou Bouetou Venkataramana Gadhamshetty Etienne Gnimpieba Z. Math Science and Technology Oglala Lakota College Kyle SD USA Ecole Nationale Supérieure Polytechnique University of Yaounde 1 Yaounde Cameroon Dept. of Computer Science University of Dschang Dschang Cameroon Dept. of Civil and Environmental Engineering South Dakota School of Mines and Technology Rapid City SD USA Dept. of Biomedical Engineering University of South Dakota Vermillion SD USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The synthesis of small molecules is a crucial task across multiple scientific domains, including drug discovery, materials science, and sustainable chemistry. As AI and Machine Learning (ML) continue to advance, these technologies offer transformative potential in molecular synthesis, enhancing efficiency and expanding synthetic possibilities. In particular, small molecule synthesis has profound implications for creating novel therapeutic agents, high-performance materials, and greener chemical processes, but a major challenge remains in designing efficient synthetic routes for target molecules. Retrosynthesis, the process of mapping out synthetic pathways by working backwards from a target molecule, represents a vital step; however, traditional retrosynthesis methods often struggle to predict complex or novel transformations. To address this limitation, we introduce AIM-HKR: AI-Driven Molecular Retrosynthesis Using Heterogeneous Knowledge Representations, a model that leverages graph neural network techniques to enhance retrosynthetic predictions. AIM-HKR integrates information from heterogeneous knowledge graphs, capturing the intricate relationships and analogical reasoning required for retrosynthesis. This model generates type-specific embeddings that reflect both network topology and semantic connections across different entity types, such as molecules, reactions, and functional groups. AIM-HKR’s unique capacity to leverage heterogeneous graphs allows it to propose synthetic pathways that extend beyond established precedents, enabling predictions of chemically feasible but previously uncharted transformations. We believe AIM-HKR has the potential to significantly advance molecular synthesis through AI-driven retrosynthesis, establishing a new paradigm in AI-assisted chemistry.

关键词： Technological innovation Chemistry Accuracy Scalability Semantics Machine learning Predictive models Reliability engineering Drug discovery Chemicals

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a scoring system for computer image recognition technology

Design and implementation of a scoring system for computer i...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Cheng Chang Yong-Yi Fanjiang Chi-Huang Hung Li-Feng Wang Ya-Jou Chang Wen-Hsuan Chang Graduate Institute of Applied Science and Engineering Fu Jen Catholic University New Taipei City Taiwan Dept. of Computer Science and Information Engineering Graduate Institute of Applied Science and Engineering Fu Jen Catholic University New Taipei City Taiwan Dept. of Information Technology Graduate Institute of Applied Science and Engineering Fu Jen Catholic University Lee-Ming Institute of Technology New Taipei City Taiwan Graduate Institute of Design Science Tatung University Lee Ming Institute of Technology New Taipei City Taiwan Dept. of Applied Cosmetology Lee-Ming Institute of Technology New Taipei City Taiwan

This paper presents a scoring system for evaluating makeup paper pictures using computer vision feature recognition. In traditional makeup scoring systems, the assessment is conducted by human reviewers, leading to potential subjective biases and raising concerns about scoring fairness. To address this issue, the paper proposes a solution that utilizes computer vision feature recognition technology for scoring. By leveraging various computer vision techniques such as structural feature matching and image recognition retrieval, it develops a method for predicting makeup styles and scores based on an image learning model. An experimental platform is designed, utilizing paper drawings created by students and scores provided by multiple evaluators as makeup image data, to automatically generate grading results. This research demonstrates the potential of computer vision feature recognition technology to enhance scoring accuracy and objectivity in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Campus Exploration with GikiLenS: A Deep Learning-Powered Object Detection App

Revolutionizing Campus Exploration with GikiLenS: A Deep Lea...

引用

International Conference on Emerging Technologies, ICET

作者： Iqra Mueed Usama Arshad Raja Hashim Ali Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany

For newcomers and tourists, navigating university campuses can be difficult, resulting in aggravation and lost time. We respond by introducing “GikiLenS”, an object identification application driven by deep learning that revolutionizes campus exploration by accurately identifying buildings and landmarks while enhancing user experience. GikiLenS is a comprehensive and user-friendly smartphone application that precisely caters to the demands of newcomers and visitors, unlike previous studies in campus navigation. Our study intends to close this gap and develop a reliable method for identifying campus buildings, optimizing navigation, and enhancing user experience. Through rigorous testing, GikiLenS has proven to have remarkable real-time building detection accuracy, highlighting its potential as an important tool for campus exploration. The app's outcomes and conclusions demonstrate how well it works to give users specific building information, promoting a more knowledgeable and enjoyable campus experience. The importance of our findings lies in the development of a unique, user-centered app that offers a cutting-edge method of campus mobility. Our contribution consists of a game-changing method for building detection that improves campus exploration and user pleasure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Biological age estimation from ECG using Artificial Intelligence approaches

Biological age estimation from ECG using Artificial Intellig...

引用

Biomedical Engineering Conference (JIBEC), Jordanian International

作者： Jana Sleiman Mohamad Daher Mohamad Khalil Ahmad Diab Abdallah Kassem Computer and Communications Engineering Lebanese University Tripoli Lebanon Dep. of Computer Science/Dep. of Computer Science & Information Technology Faculty of Science/Faculty of Applied Sciences & Technology Tripoli Lebanon Electrical Engineering Lebanese University Tripoli Lebanon Biomedical Engineering Lebanese International University Beirut Lebanon ECCE Dept. Faculty Of Engineering Notre Dame University Zouk Mosbeh Lebanon

ISBN: (数字)9798331539542

ISBN: (纸本)9798331539559

This paper explores the application of Artificial Intelligence (AI) techniques in healthcare, specifically focusing on electrocardiogram (ECG) data analysis and biological age estimation. The study begins with an overview of ECG as a diagnostic tool and discusses the integration of Deep Learning (DL) models, particularly Convolutional Neural Networks (CNNs), in healthcare for various applications. Previous studies reviewed in this context consistently identify CNNs as the superior model for ECG analysis and prediction tasks. The primary research investigates the use of Machine Learning (ML) algorithms to estimate biological age from ECG data, employing metrics such as Mean Absolute Error (MAE) and variance to evaluate model performance. Subsequently, DL models are implemented and compared, demonstrating superior accuracy in estimating the biological age of new patients. While both ML and DL approaches were initially explored, this paper primarily focuses on deep learning methodologies due to their demonstrated superiority in healthcare applications. The findings highlight the efficacy of deep learning over traditional ML methods, underscoring its potential for enhancing diagnostic accuracy and personalized patient care. For instance, the most accurate deep learning model, the Convolutional Neural Network (CNN), achieved a Mean Absolute Error (MAE) of 1.49 and an R 2 score of 0.53, whereas the best-performing traditional ML model, Random Forest, achieved an MAE of 1.54 and an R 2 score of 0.55. These results clearly indicate the advantage of deep learning models in capturing complex patterns in ECG data, leading to more precise and reliable estimations of biological age.

关键词： Deep learning Maximum likelihood estimation Accuracy Data analysis Biological system modeling Medical services Electrocardiography Data models Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Infection Detection in X-Ray Images Using Enhanced Image Segmentation and Machine Learning Models 25

COVID-19 Infection Detection in X-Ray Images Using Enhanced ...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Nahar, Khalid M.O. Ebrahim Megdad, Mohammad Al Mamlook, Rabia Emhamed Aljaidi, Mohammad Nahar, Besan K.M. Nahar, Mohammad K. M. Anbarkhan, Samar Hussni Khafajeh, Hayel Amer, Waleed Arab Open University Faculty of Computer Studies P.O. Box 84901 Riyadh11681 Saudi Arabia Yarmouk University Computer Science Department Irbid21163 Jordan University of Zawia Dept. of Mechanical and Industrial Engineering Zawia Libya Zarqa University Faculty of Information Technology Department of Computer Science Zarqa13110 Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Yarmouk University Faculty of Medicine Irbid Jordan Jordan University of Science and Technology Faculty of Applied Medical Science Irbid21163 Jordan Northern Border University Information Systems Department Rafha76322 Saudi Arabia Zarqa University Faculty of Information Technology Department of Artificial Intelligence Zarqa13110 Jordan Zarqa University Faculty of Information Technology Department of Cybersecurity Zarqa13110 Jordan

ISBN: (纸本)9798331540012

The COVID-19 pandemic has shown a significant challenge to healthcare associations worldwide demanding the progress of reliable diagnostic techniques. Chest X-ray imaging is an easily available and cost-effective tool for evaluating lung defects combined with COVID-19. This study aims to introduce a novel COVID-19 infection detection and recognition method in X-ray images through image segmentation. By employing machine learning (ML) methods, particularly CNN-based U-Net architectures, the lung sections are accurately segmented, and infection sections are classified based on specific radiological features. The model was trained on a large dataset of annotated X-ray images assisting it to distinguish between healthy lungs, COVID-19-affected lungs, and other lung pathologies. The proposed method apprehended a segmentation accuracy of 96.6% with a Dice coefficient of 94.36% offering a potential solution for mechanical detection and 98.4% with KNN analysis of COVID-19 infection in chest X-rays in that way assisting radiologists in making faster and more accurate diagnoses. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

ClimateCast: ML-Powered Temperature Forecasting for North 24 Parganas

ClimateCast: ML-Powered Temperature Forecasting for North 24...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Abhirup Paria Anindya Ghatak Biswajit Jana Arpan Adhikary Priyanka Sen Ruma Das Dept. of Computer Sc. & Engg. (Artificial Intelligence & Machine Learning) Haldia Institute of Technology Haldia India School of Computer Sc. Engg. & Tech. Bennett University Greater Noida Uttar Pradesh Dept. of Computer Sc. & Engg. Haldia Institute of Technology Haldia India School of Applied Science & Humanities Haldia Institute of Technology Haldia India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

Global warming is increasing at a rapid rate. Several efforts are made to understand its influence worldwide and in particular regions as well. Therefore, temperature prediction has become one of the most important and influential research topics because of its application in agricultural, ecological, industrial, and environmental sectors. This study reviews dif-ferent machine learning algorithms for temperature prediction and observes their superiorities. The area of study was done in North 24 Parganas, West Bengal, India. Parameters used in the dataset of the North 24 Parganas include wind speed, different types of UV radiance, cloud amount, soil moisture, precipitation rate, surface pressure, and specific and relative humidity. The relevant features are chosen from all the parameters using feature selection. The feature selection technique used is SelectKBest, using Mutual Info Regression. The different ML models used are KNN Regression, Linear Regression (LR), Decision Tree Regression, Support Vector Regression, Random Forest Regression, LightGBM Regression, XGBoost Regression, AdaBoost Regression and Ridge Regression. The experimental results were evaluated using Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and R Squared (coefficient of determination). The result of this experiment revealed that XGBoost Regression has MAE, MSE, RMSE, and R Squared respectively 0.361, 0.273, 0.523, 0.989 followed by LightGBM Regression with MAE, MSE, RMSE and R squared followed by 0.366, 0.276, 0.526 and 0.988. These results show that XGBoost Regression possesses a high capability for temperature prediction

关键词： Support vector machines Temperature distribution Machine learning algorithms Accuracy Wind speed Soft sensors Soil moisture Feature extraction Vectors Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

Custom Hidden Markov Models for Effective Part-of-Speech Tagging

Custom Hidden Markov Models for Effective Part-of-Speech Tag...

引用

International Conference on Emerging Technologies, ICET

作者： Hassan Bin Khalid Abu Bakar Siddique Raja Hashim Ali Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany

Hidden Markov Models have proved to be a very significant tool for various time-series related problems, especially where context is important. One such problem is Part-of-speech tagging. The work uses a customized HMM to propose an effective and advanced solution to POS tagging. With a precision rate of 0.9657, recall of 0.9656, and F1-score of 0.9655, this proposed HMM-based model achieves an exceptional level of accuracy, exhibiting its accurate identification of the POS of words in a sentence. The statistical model employed by the HMM-based method predicts the most likely POS tags while taking into account the probabilities of transition between various POS tags. The model's dependability and resilience were demonstrated when it was tested on a different dataset after being trained on a extensive collection of text data. The study's findings demonstrate that the HMM-based strategy outperforms current POS tagging techniques, making it a significant contribution to the field of natural language processing. In addition, this research has significant implications for a number of NLP applications, including sentiment analysis, machine translation, and text categorization, paving the way for additional innovation and exploration in this domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Unlabeled Data in Self-Supervised Training Improves Automatic Vertebral Body Fracture Assessment

Using Unlabeled Data in Self-Supervised Training Improves Au...

引用

IEEE International Symposium on Biomedical Imaging

作者： Julian Lukas Laue Christian Adolph Eren Bora Yilmaz Carsten Meyer Department of Computer Science Ostfalia University of Applied Sciences Wolfenbüttel Germany L3S Research Center Leibniz University Hannover Hannover Germany Deptartment of Computer Science Faculty of Engineering Kiel University Germany Dept. of Radiology and Neuroradiology Section Biomedical Imaging UKSH Kiel Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Vertebral body (VB) fractures can have severe implications for the patient’s well-being, but often remain undetected. Automatic vertebral fracture assessment is challenging due to severe class imbalance in fracture grades, scarcity of annotated data, and often subtle visual differences between the grades. In this paper, we show that leveraging unlabeled data, collected from eight diverse, publicly available datasets in a self-supervised way via the BYOL framework, can noticeably improve performance. Our pre-trained models outperformed the non-pre-trained baselines in 17 out of 18 comparisons, 11 of which were statistically significant, when evaluated on the widely-used VerSe dataset, our in-house dataset, and combinations thereof. Furthermore, our models reached an average AUROC value of 99.6% on the VerSe test corpus, the highest recorded in the literature so far.

关键词： Training Visualization Sensitivity Biological system modeling Context modeling Biomedical imaging

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：