检索结果-内蒙古大学图书馆

Contrastive Continual learning with Importance Sampling and Prototype-Instance Relation Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiyong Azizov, Dilshod Li, Yang Liang, Shangsong School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates AI Thrust Information Hub The Hong Kong University of Science and Technology Guangzhou China Department of CSE The Hong Kong University of Science and Technology China

Recently, because of the high-quality representations of contrastive learning methods, rehearsal-based contrastive continual learning has been proposed to explore how to continually learn transferable representation embeddings to avoid the catastrophic forgetting issue in traditional continual settings. Based on this framework, we propose Contrastive Continual learning via Importance Sampling (CCLIS) to preserve knowledge by recovering previous data distributions with a new strategy for Replay Buffer Selection (RBS), which minimize estimated variance to save hard negative samples for representation learning with high quality. Furthermore, we present the Prototype-instance Relation Distillation (PRD) loss, a technique designed to maintain the relationship between prototypes and sample representations using a self-distillation process. Experiments on standard continual learning benchmarks reveal that our method notably outperforms existing baselines in terms of knowledge preservation and thereby effectively counteracts catastrophic forgetting in online contexts. The code is available at https://***/lijy373/CCLIS. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

PAM: A Propagation-Based Model for Segmenting Any 3D Objects across Multi-Modal Medical Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Zifan Nan, Xinyu Li, Jiazheng Zhao, Jie Li, Haifeng Lin, Ziling Li, Haoshen Chen, Heyun Liu, Yiting Tang, Lei Zhang, Li Dong, Bin Center for Data Science Peking University Beijing China Department of Radiology Key Laboratory of Carcinogenesis and Translational Research Ministry of Education Peking University Cancer Hospital and Institute Beijing China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China Peking University Beijing China Center for Machine Learning Research Peking University Beijing China National Biomedical Imaging Center Peking University Beijing China

Background: Volumetric segmentation is crucial for medical imaging applications but faces significant challenges. Current approaches often require extensive manual annotations and scenario-specific model training, limiting their transferability across different tasks or modalities. While general segmentation models offer some versatility in natural image processing, they struggle with the unique characteristics of medical images. There is an urgent need in clinical practice for a new segmentation approach that can effectively handle medical imagery features while maintaining adaptability across various three-dimensional objects and imaging modalities. Methods: We introduce PAM (Propagating Anything Model), a propagation-based segmentation approach that operates on 3D medical image volumes using a 2D prompt (bounding box or sketch mask). PAM extrapolates this initial input to generate a complete 3D segmentation by modeling inter-slice structural relationships, establishing a continuous information flow within 3D medical structures. This approach enhances segmentation effectiveness across various imaging modalities by focusing on structural and semantic continuities rather than isolating specific objects. The model combines a CNN-based UNet architecture for intra-slice information processing with a Transformer-based attention module to facilitate inter-slice propagation. This innovative framework results in a method with unique generalizability, capable of segmenting diverse 3D objects across different medical imaging modalities. Results: PAM demonstrated superior performance on 44 diverse medical datasets, notably improving the dice similarity coefficient (DSC) for hundreds of segmentation object types and various medical imaging modalities. Compared to modern models like MedSAM and SegVol, PAM achieved an average DSC improvement of over 18.1%, while maintaining stable predictions despite prompt deviation (one-way ANOVA test, P ≥ 0.5985) and varying propagation confi

关键词： Semantic Segmentation

Natural Convection Optimizer: A Novel Physics-Based Metaheuristic Optimization Algorithm

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liang, Kang Yipeng, Wang Jiayi, Chen Krakhmalev, Oleg Engineering Training and Innovation Education Center Shanghai Polytechnic University Shanghai201209 China School of Foreign Languages and CulturalCommunication Shanghai Polytechnic University Shanghai201209 China School of Economics and Management Shanghai Polytechnic University Shanghai201209 China Department of Data Analysis and Machine Learning Financial University under the Government of the Rus-sian Federation 4‐th Veshnyakovsky Passage 4 Moscow109456 Russia

In this paper, Natural Convection Optimizer Algorithm (NCvO) is proposed as a novel physical-inspired metaheuristic optimization algorithm. It is a novel physics-inspired metaheuristic optimization algorithm based on natural convection phenomena in fluid dynamics. By simulating the heat transfer process in fluids, NCvO achieves a balanced exploration and exploitation of complex search spaces. We validate NCvO through three experiments: solving the CEC 2017 benchmark in 10 dimensions and comparing results with well-established metaheuristics using statistical analyses like Wilcoxon and Friedman tests. NCvO demonstrates superior performance in terms of average fitness values and objective function evaluations, establishing its potential as a robust optimization tool. © 2024, The Authors. All rights reserved.

关键词： Optimization

Predicting Response to Patients with Gastric Cancer Via a Dynamic-Aware Model with Longitudinal Liquid Biopsy data

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Chen, Zifan Zhao, Jie Li, Yanyan Li, Yilin Liu, Huimin Feng, Xujiao Nan, Xinyu Dong, Bin Shen, Lin Chen, Yang Zhang, Li Center for Data Science Peking University Beijing China Department of Gastrointestinal Oncology Key Laboratory of Carcinogenesis and Translational Research Ministry of Education Peking University Cancer Hospital and Institute Beijing China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China Guangzhou Medical University Guangzhou China Peking University Beijing China Center for Machine Learning Research Peking University Beijing China Peking University Changsha Institute for Computing and Digital Economy Changsha China

Gastric cancer (GC) presents challenges in predicting treatment responses due to its patient-specific heterogeneity. Recently, liquid biopsies have become recognized as a valuable data modality, offering essential cellular and molecular insights and enabling the capture of time-sensitive information. This study aimed to harness artificial intelligence (AI) technology to analyze longitudinal liquid biopsy data. We collected a dataset from longitudinal liquid biopsies of 91 patients at Peking Cancer Hospital, spanning from July 2019 to April 2022, which included 1,895 tumor-related cellular images and 1,698 tumor marker indices. Subsequently, we introduced the Dynamic-Aware Model (DAM) to predict GC treatment responses. DAM incorporates the dynamic data through AI-engineered components, enabling an in-depth longitudinal analysis. Utilizing three-fold cross-validation, DAM exhibited superior performance over traditional cell-counting-based methods, achieving an AUC of 0.807 in predicting GC treatment responses. In the test set, DAM maintained stable efficacy with an AUC of 0.802. Besides, DAM showed the capability to accurately predict treatment responses from early treatment data. Moreover, DAM's visual analysis of attention mechanisms identified six dynamic focus-area-related visual features and their strong association with treatment response. These findings represent a pioneering effort in applying AI technology for interpreting longitudinal liquid biopsy data and employ visual analytics in GC, offering a promising avenue toward precise response prediction and tailored treatment strategies for patients with ***: This work was supported by the National Natural Science Foundation of China (81801778 to Li Zhang., 82203881 to Yang Chen, U22A20327 to Lin Shen, 12090022 to Bin Dong), Beijing Natural Science Foundation (7222021 to Yang Chen), Beijing Hospitals Authority Youth Programme (QML20231115 to Yang Chen), Clinical Medicine Plus X-Young Scholars Project of P

关键词： Diseases

Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference machines

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Adam, Alexandre Perreault-Levasseur, Laurence Hezaveh, Yashar Welling, Max Department of Physics Université de Montréal Montréal Canada Mila - Quebec Artificial Intelligence Institute Montréal Canada Ciela - Montreal Institute for Astrophysical Data Analysis and Machine Learning Montréal Canada Center for Computational Astrophysics Flatiron Institute 162 5th Avenue New YorkNY10010 United States Microsoft Research AI4Science

Modeling strong gravitational lenses in order to quantify the distortions in the images of background sources and to reconstruct the mass density in the foreground lenses has been a difficult computational challenge. As the quality of gravitational lens images increases, the task of fully exploiting the information they contain becomes computationally and algorithmically more difficult. In this work, we use a neural network based on the Recurrent Inference machine (RIM) to simultaneously reconstruct an undistorted image of the background source and the lens mass density distribution as pixelated maps. The method iteratively reconstructs the model parameters (the image of the source and a pixelated density map) by learning the process of optimizing the likelihood given the data using the physical model (a ray-tracing simulation), regularized by a prior implicitly learned by the neural network through its training data. When compared to more traditional parametric models, the proposed method is significantly more expressive and can reconstruct complex mass distributions, which we demonstrate by using realistic lensing galaxies taken from the IllustrisTNG cosmological hydrodynamic simulation. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

Object Modeling in Kinematic Problems of Manipulation Robots

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Liang, Kang Krakhmalev, Oleg Blagoveshchensky, Ivan Krakhmalev, Nikita Beiresh, Andrew Engineering Training and Innovation Education Center Shanghai Polytechnic University Shanghai201209 China Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation Moscow Russia 4-th Veshnyakovsky Passage 4 Moscow109456 Russia Volokolamsk highway building 11 Moscow125080 Russia Department of Engineering Graphics Moscow State University of Technology "STANKIN" Vadkovsky Lane 3a Moscow127055 Russia

A method for compiling object diagrams has been developed to describe algorithms for calculating the kinematic parameters of manipulation robots. Examples of drawing up object diagrams for calculating the speeds and accelerations of points selected on the manipulation robot links are considered. Analysing the computational complexity of the obtained algorithms is carried out and a method is proposed to increase their computational efficiency. Raising the computational efficiency is achieved by reducing the addition and multiplication operations performed by the algorithm. A two-level parallel computational algorithm is developed, which makes it possible to additionally improve the computational efficiency when using multiprocessor computing systems. Information and computational graphs illustrating the developed algorithms are presented. The conducted research allows automating the process of modelling the manipulative robot movement. The object approach and the modelling methods carried out on its basis can also be implemented in the control systems for manipulation robots. © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

Overview of Modern Forecasting Methods and Models

学校读者我要写书评

暂无评论

Overview of Modern Forecasting Methods and Models

International Conference on Management of Large-Scale System Development (MLSD)

作者： Vera Ivanyuk Anatoliy Tsvirkun Anna Sunchalina Tatiana Goroshnikova Andrey Sunchalin Galina Zholobova Department of Data Analysis and Machine Learning Financial University Under the Government of the Russian Federation Moscow Russia Department of Higher Mathematics Bauman Moscow State Technical University Moscow Russia Laboratory of Management of the Development of Large-Scale Systems V.A.Trapeznikov Institute of Control Sciences of RAS Moscow Russia Faculty of International Economic Relations Financial University Under the Government of the Russian Federation Moscow Russia Department of Mathematics Financial University Under the Government of the Russian Federation Moscow Russia

The development of accurate forecasting models for financial time series is an essential area of research in finance and economics. The article describes modern models and forecasting methods.

关键词：

The Nearly Universal Disk Galaxy Rotation Curve

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Patel, Raj Arora, Nikhil Courteau, Stephane Stone, Connor Frosst, Matthew Widrow, Lawrence Department of Physics Engineering Physics & Astronomy Queen’s University KingstonONK7L 3N6 Canada Department of Physics Université de Montréal MontréalQC Canada Mila Québec Artificial Intelligence Institute MontréalQC Canada Ciela Montréal Institute for Astrophysical Data Analysis and Machine Learning MontréalQC Canada ICRAR M468 University of Western Australia CrawleyWA6009 Australia

The Universal Rotation Curve (URC) of disk galaxies was originally proposed to predict the shape and amplitude of any rotation curve (RC) based solely on photometric data. Here, the URC is investigated with an extensive set of spatially-resolved rotation curvesdrawn from the PROBES-I, PROBES-II, and MaNGA data bases with matching multi-band surface brightness profiles from the DESI-LIS and WISE surveys for 3,846 disk galaxies. Common URC formulations fail to achieve an adequate level of accuracy to qualify as truly universal over fully sampled RCs. We develop neural network (NN) equivalents for the proposed URCs which predict RCs with higher accuracy, showing that URC inaccuracies are not due to insufficient data but rather non-optimal formulations or sampling effects. This conclusion remains even if the total RC sample is pruned for symmetry. The latest URC prescriptions and their NN equivalents trained on our sub-sample of 579 disk galaxies with symmetric RCs perform similarly to the URC/NN trained on the complete data sample. We conclude that a URC with an acceptable level of accuracy (∆Vcirc 15 per cent) at all radii would require a detailed modelling of a galaxy’s central regions and outskirts (e.g., for baryonic effects leading to contraction or expansion of any dark-matter-only halo). © 2024, CC BY.

关键词： Galaxies

E-service quality from attributes to outcomes: The similarity and difference between digital and hybrid services

学校读者我要写书评

暂无评论

Journal of Open Innovation: Technology, Market, and Complexity 2020年第4期6卷 1-21页

作者： Vatolkina, Natalia Gorbashko, Elena Kamynina, Nadezhda Fedotkina, Olga Department of Management Bauman Moscow State Technical University (National Research University) Moscow 105005 Russian Federation Department of Project and Quality Management Saint Petersburg State University of Economics St. Petersburg 191023 Russian Federation Department of Land Law and State Registration of Real Estate Moscow State University of Geodesy and Cartography Moscow 105064 Russian Federation Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation Moscow 125167 Russian Federation

Our research goal is to offer an e-service quality model based on experience and multidimensional quality and compare its applicability for e-services to find differences and similarities in consumer perceptions and behavioral intentions. Additionally, we seek to compare attributes that compose quality dimensions for hybrid and digital e-services. The study was based on an online survey conducted in July–September 2019 among citizens and foreign residents in the Russian Federation. Respondents had to answer questions concerning a specific e-service brand to capture real consumer behavior. The data of 365 questionnaires were analyzed using the Spearman correlation to determine the relationship between the model components. Customer experience is a valid outcome variable in the e-service model that strongly influences customer satisfaction and repurchase intentions. The model proved to be equally valid for hybrid and digital e-services. The key differences between digital and hybrid e-services lie within the distribution of e-service attributes between quality dimensions. Ease of use and perceived usefulness are the most essential attributes that have a direct influence on customer satisfaction. The findings show the necessity of best practices diffused between different types of e-services and present an opportunity to widely spread research findings between different e-service sectors. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

关键词： Customer experience E-service E-service quality