检索结果-内蒙古大学图书馆

International Conference on data engineering

作者： Damien A. Dablain Colin Bellinger Bartosz Krawczyk Nitesh V. Chawla Dept. Computer Science and Engineering Lucy Family Institute for Data & Society University of Notre Dame Notre Dame IN USA National Research Council of Canada Ottawa Canada Dept. Computer Science Virginia Commonwealth University Richmond VA USA

Deep learning models may not effectively generalize across under-represented or minority classes. We empirically study a convolutional neural network’s (CNN) internal representation of imbalanced image data and measure the generalization gap between a model’s feature embeddings in the training and test sets, showing that the gap is wider for minority classes. This insight enables us to design an efficient three-phase CNN training framework for imbalanced data. The framework involves training the network end-to-end on imbalanced data to learn feature embeddings, performing data augmentation in the learned embedding space to balance the training data distribution, and fine-tuning the classifier head on the embedded balanced training data. We develop Expansive Over-Sampling (EOS) as a data augmentation technique to utilize in the training framework. EOS forms synthetic training instances as convex combinations between the minority class samples and their nearest adversaries in the embedding space to reduce the generalization gap. The proposed framework improves the accuracy over leading cost-sensitive and resampling methods commonly used in imbalanced learning. Moreover, it is more computationally efficient than standard data pre-processing methods, such as SMOTE and GAN-based over-sampling, as it requires fewer parameters and less training time. The source code for the proposed framework is available at: https://***/dd1github/EOS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration of a multi-rate electron density profile observer in the plasma control system of TCV 49

Integration of a multi-rate electron density profile observe...

引用

49th EPS Conference on Plasma Physics, EPS 2023

作者： Pastore, F. Felici, F. Sauter, O. Bosman, T.O.S.J. Galperti, C. Vincent, B. Pau, A. Poels, Y. Ravensbergen, T. Vu, N.M.T. Lausanne Switzerland DIFFER - Dutch Institute for Fundamental Energy Research Energy Systems and Control Group Eindhoven Netherlands Eindhoven University of Technology Dept. of Mechanical Engineering Control Systems Technology Group Eindhoven Netherlands Eindhoven University of Technology Dept. of Mathematics and Computer Science Data Mining Group Eindhoven Netherlands ITER Organization Route de Vinon-sur-Verdon St. Paul Lez Durance13067 Cedex France

来源：评论

学校读者我要写书评

暂无评论

Trade-off between payoff and model rewards in shapley-fair collaborative machine learning 22

Trade-off between payoff and model rewards in shapley-fair c...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Quoc Phong Nguyen Bryan Kian Hsiang Low Patrick Jaillet Institute of Data Science National University of Singapore Republic of Singapore Dept. of Electrical Engineering and Computer Science MIT Dept. of Computer Science National University of Singapore Republic of Singapore

ISBN: (纸本)9781713871088

This paper investigates the problem of fairly trading off between payoff and model rewards in collaborative machine learning (ML) where parties aggregate their datasets together to obtain improved ML models over that of each party. Supposing parties can afford the optimal model trained on the aggregated dataset, we propose an allocation scheme that distributes the payoff fairly. Notably, the same scheme can be derived from two different approaches based on (a) desirable properties of the parties' payoffs or (b) that of the underlying payoff flows from one party to another. While the former is conceptually simpler, the latter can be used to handle the practical constraint on the budgets of parties. In particular, we propose desirable properties for achieving a fair adjustment of the payoff flows that can trade off between the model reward's performance and the payoff reward. We empirically demonstrate that our proposed scheme is a sensible solution in several scenarios of collaborative ML with different budget constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANFIS Model for Cost Analysis in a Dual Source Multi-Destination System 4

ANFIS Model for Cost Analysis in a Dual Source Multi-Destina...

引用

4th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2022

作者： Okwu, M.O. Tartibu, L.K. Ojo, E.O. Adume, S. Gidiagba, J.O. Fadeyi, J. Department of Mechanical Industrial Engineering Tech. University of Johannesburg South Africa Department of Mechanical Engineering Federal University of Petroleum Resources Effurun Nigeria Mathematics and Data Science Dept. Computing Science and Mathematics Division Faculty of Natural Science University of Stirling United Kingdom Faculty of Engineering and Applied Sc. Memorial University Newfoundland Canada Department of Industrial and Systems Engineering University of Buffalo United States

Managers face uncertainties while making allocation decisions, especially in dual or multi-source multi-destination inventory systems. Regrettably, many studies focus on classical methods as a technique for product distribution, which has never guaranteed a satisfactory solution. Real-life problems are non-deterministic polynomial-time hard (NP-hard), and solving such problems is relatively challenging. Such complicated problems need an efficient and robust computational hybrid algorithm. This study emphasises the need for a hybrid intelligent technique for effective product distribution. Soft computing hybrid algorithm, ANFIS was applied to product distribution in a double source multi-destination system. Rules were developed from available input datasets. Distributing products from dual manufacturing plants to fifteen available depots using the creative algorithm resulted in an overall 13.5% decrease in cost compared to the existing method adopted by the company. The result showed that the proposed method is relatively satisfactory and adequate for cost modelling. In addition, it is easy to use and outperforms the classical approach. © 2022 The Authors. Published by ELSEVIER B.V.

关键词： Soft computing

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Wearable Piezoelectric Integrated Shoe Energy Harvester

Implementation of a Wearable Piezoelectric Integrated Shoe E...

引用

IEEE International Conference on Biomedical engineering, Computer and Information Technology for Health

作者： Akib Jayed Islam Sultanus Salehin S. U. Alam Shreya Paul Prithwi Chowdhury Nirzar Barua Nafis Fuad Wasi Computational Colour and Spectral Imaging Norwegian University of Science and Technology Gjøvik Norway Dept. of ECE The University of Alabama Tuscaloosa USA Electrical & Electronics Engineering National Institute of Technology Trichy Tamil Nadu India Electrical & Electronics Engineering Ahsanullah Uni. of Science & Technology Dhaka Bangladesh Electronics & Telecommunication Engineering Chittagong Uni. of Engineering & Technology Chittagong Bangladesh Dept. of EEE NSTU Noakhali Bangladesh

ISBN: (数字)9798331534356

ISBN: (纸本)9798331534363

This research explores the viability of utilizing human locomotion as a renewable energy source through piezoelectric energy harvesting. By embedding piezoelectric transducers within footwear, mechanical energy generated during movement can be effectively converted into electrical energy. A comprehensive power management circuit, including a battery, rectifier, and DC-DC converter, is proposed to optimize energy capture and storage. Experimental results demonstrate significant improvements in energy harvesting efficiency through strategic placement and sizing of the piezoelectric transducer within the shoe soles. These findings underscore the potential of this method for powering wearable electronics, advancing the development of sustainable, self-powered devices. Moreover, this approach extends the application of piezoelectric energy harvesting beyond traditional power sources, facilitating the creation of self-sustaining wearable sensors and devices, with potential applications in fields such as rehabilitation and sports science.

关键词： Electric potential Power system management Piezoelectric transducers Rectifiers Footwear Medical services Energy harvesting Piezoelectric devices Wearable devices Sports

来源：评论

学校读者我要写书评

暂无评论

De Novo Drug Property Prediction using Graph Convolutional Neural Networks 9

De Novo Drug Property Prediction using Graph Convolutional N...

引用

9th Edition of IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2021

作者： Shishir, Fairuz Shadmani Hasib, Khan Md. Sakib, Shadman Maitra, Shithi Shah, Faisal Muhammad BJIT Group SD-06 | Dept. of AI Sylhet Dhaka Bangladesh Dept. of Computer Science and Engineering Sylhet Dhaka Bangladesh Ahsanullah University of Science and Technology Leading University Sylhet Dhaka Bangladesh Data and BI Engineering SureCash Sylhet Dhaka Bangladesh

ISBN: (纸本)9781665432405

Drug property prediction poses a complex task in the healthcare domain, because the drug-like molecules greatly vary in chemical structures. Inhibitory concentration (IC50) prediction is essential to reduce the cost and labor of a drug's preclinical and clinical trials, because a lot of drug evaluations (cellular, animal, and clinical) can be spared due to the predicted IC50. In the era of Artificial Intelligence, Drug Discovery processes can benefit from deep learning, which has been widely used in computational chemistry and bioinformatics with state-of-the-art performance. In this paper, we propose a novel (in other words, de novo) graph convolutional network approach, cross-validated by traditional methods like Lipinski's rule of five and PaDEL-described one-hot encoding. The experiment has been carried out on the ChEMBL bioactivity dataset of Acetylcholinesterase protein, achieving an R2 score of 0.52. © 2021 IEEE.

关键词： Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Easy Variational Inference for Categorical Models via an Independent Binary Approximation

arXiv

引用

arXiv 2022年

作者： Wojnowicz, Michael T. Aeron, Shuchin Miller, Eric L. Hughes, Michael C. Tufts University MedfordMA United States Data Intensive Studies Center Dept. of Electrical and Computer Engineering Dept. of Computer Science

We pursue tractable Bayesian analysis of generalized linear models (GLMs) for categorical data. Thus far, GLMs are difficult to scale to more than a few dozen categories due to non-conjugacy or strong posterior dependencies when using conjugate auxiliary variable methods. We define a new class of GLMs for categorical data called categorical-from-binary (CB) models. Each CB model has a likelihood that is bounded by the product of binary likelihoods, suggesting a natural posterior approximation. This approximation makes inference straightforward and fast;using well-known auxiliary variables for probit or logistic regression, the product of binary models admits conjugate closed-form variational inference that is embarrassingly parallel across categories and invariant to category ordering. Moreover, an independent binary model simultaneously approximates multiple CB models. Bayesian model averaging over these can improve the quality of the approximation for any given dataset. We show that our approach scales to thousands of categories, outperforming posterior estimation competitors like Automatic Differentiation Variational Inference (ADVI) and No U-Turn Sampling (NUTS) in the time required to achieve fixed prediction quality. © 2022, CC BY.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Interpretable Analysis of Oral Mucosal Lesions Using U-Net and Quantum Approaches

Interpretable Analysis of Oral Mucosal Lesions Using U-Net a...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Aparna M Anna Liza Sibi Prachi Kumari Golla Ram Senthil Kumar T. Somasundaram K. Vindhya Savithri Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Dept. of Artificial Intelligence and Data Science School of AI Amrita Vishwa Vidyapeetham Coimbatore India Department of Mathematics Amrita School of Physical Sciences Amrita Vishwa Vidyapeetham Coimbatore India Dept. of Oral & Maxillofacial Pathology and Microbiology Amrita School of Dentistry AIMS Ponekkara PO Kochi India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Oral mucosal lesions are abnormal changes found in the tissue of the mouth. They can be painful and may include abnormal cell growths, as well as rare tongue and hard- palate disorders. They may result from infections, inflamma- tory processes, trauma, autoimmune conditions, or precancerous changes. A recent study found a 59.6% prevalence of oral mucosal lesions among elderly individuals, highlighting a signif- icant association with factors such as age over 65, male gender, tobacco habits, and denture usage. Thus, lesions can significantly impact a patient's quality of life, necessitating accurate diagnosis and timely intervention. In this study, we use a combination of two advanced technologies-U-Net, a deep learning model, and quantum computing-to analyze medical images of oral health. We use a publicly available dataset containing labeled images classified as ‘Lesion’ and ‘Oral Cavity,’ focusing only on lesion detection. Our results show that while the U-Net model achieves 95.02% segmentation accuracy, the quantum approach using QCNN achieves 74.5% accuracy. Although the quantum model does not outperform U-Net in segmentation, it demonstrates potential for future research in quantum-enhanced medical imaging. To measure how well our method works, we use different evaluation techniques, including Dice Coefficient, Intersection over Union (IoU), accuracy, precision, recall, and F1-score. Our results indicate that while quantum computing has shown high accuracy in previous research for classification tasks, its application to segmentation-particularly in oral lesion detection-faces challenges such as lower accuracy, quantum noise, and hardware constraints. This research highlights the potential of integrating AI and quantum approaches for medical diagnosis while acknowledging the need for further improvements in quantum seamcntation models.

关键词： Deep learning Image segmentation Quantum computing Accuracy computational modeling Hardware computational efficiency Lesions Artificial intelligence Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Particle swarm optimization with local search for height-map surface reconstruction from point clouds in reverse engineering

引用

Neural Computing and Applications 2024年 1-20页

作者： Gálvez, Akemi Fister, Iztok Deb, Suash Fister, Iztok Iglesias, Andrés Dept. of Applied Mathematics and Computational Sciences E.T.S.I. Caminos Canales y Puertos University of Cantabria Avda. de los Castros s/n Santander39005 Spain Faculty of Pharmaceutical Sciences Toho University 2-2-1 Miyama Funabashi274-8510 Japan Faculty of Electrical Engineering and Computer Science University of Maribor Koroska cesta 34 Maribor2000 Slovenia IT & Educational Consultant Ranchi India Distinguished Professorial Associate Decision Sciences and Modeling Program Victoria University Melbourne Australia

Surface reconstruction is a classical process in industrial engineering and manufacturing, particularly in reverse engineering, where the goal is to obtain a digital model from a physical object. For that purpose, the real object is typically scanned or digitized and the resulting point cloud is then fitted to mathematical surfaces through numerical optimization. The choice of the approximating functions is crucial for the accuracy of the process. Real-world objects such as manufactured workpieces often require complex nonlinear approximating functions, which are not well suited for standard numerical methods. In a previous paper presented at the ISMSI 2023 conference, we addressed this issue by using manually selected approximation functions via optimization through the cuckoo search algorithm with Lévy flights. Building upon that work, this paper presents an enhanced and extended method for surface reconstruction by using height-map surfaces obtained through a combination of exponential, polynomial and logarithmic functions. A feasible approach for this goal is to consider continuous bivariate distribution functions, which ensures consistent models along with good mathematical properties for the output shapes, such as smoothness and integrability. However, this approach leads to a difficult multivariate, constrained, multimodal continuous nonlinear optimization problem. To tackle this issue, we apply particle swarm optimization, a popular swarm intelligence technique for continuous optimization. The method is hybridized with a local search procedure for further improvement of the solutions and applied to a benchmark of 15 illustrative examples of point clouds fitted to different surface models. The performance of the method is analyzed through several computational experiments. The numerical and graphical results show that the method is able to recover the shape of the point clouds accurately and automatically. Furthermore, our approach outperforms other alternati

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

A Bayesian analysis of the time through the order penalty in baseball

arXiv

引用

arXiv 2022年

作者： Brill, Ryan S. Deshpande, Sameer K. Wyner, Abraham J. Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania United States Dept. of Statistics University of Wisconsin-Madison United States Dept. of Statistics and Data Science The Wharton School University of Pennsylvania United States

As a baseball game progresses, batters appear to perform better the more times they face a particular pitcher. The apparent drop-off in pitcher performance from one time through the order to the next, known as the Time Through the Order Penalty (TTOP), is often attributed to within-game batter learning. Although the TTOP has largely been accepted within baseball and influences many managers' in-game decision making, we argue that existing approaches of estimating the size of the TTOP cannot disentangle continuous evolution in pitcher performance over the course of the game from discontinuities between successive times through the order. Using a Bayesian multinomial regression model, we find that, after adjusting for confounders like batter and pitcher quality, handedness, and home field advantage, there is little evidence of strong discontinuity in pitcher performance between times through the order. Our analysis suggests that the start of the third time through the order should not be viewed as a special cutoff point in deciding whether to pull a starting pitcher. Copyright © 2022, The Authors. All rights reserved.

关键词： Baseball

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：