检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Austin, George I. Pe’er, Itsik Korem, Tal Department of Biomedical Informatics Columbia University Irving Medical Center New YorkNY United States Program for Mathematical Genomics Department of Systems Biology Columbia University Irving Medical Center New YorkNY United States Department of Computer Science Columbia University New YorkNY United States Department of Obstetrics and Gynecology Columbia University Irving Medical Center New YorkNY United States

Cross-validation is a common method for estimating the predictive performance of machine learning models. In a data-scarce regime, where one typically wishes to maximize the number of instances used for training the model, an approach called ‘leave-one-out cross-validation’ is often used. In this design, a separate model is built for predicting each data instance after training on all other instances. Since this results in a single test data point available per model trained, predictions are aggregated across the entire dataset to calculate common rank-based performance metrics such as the area under the receiver operating characteristic or precision-recall curves. In this work, we demonstrate that this approach creates a negative correlation between the average label of each training fold and the label of its corresponding test instance, a phenomenon that we term distributional bias. As machine learning models tend to regress to the mean of their training data, this distributional bias tends to negatively impact performance evaluation and hyperparameter optimization. We show that this effect generalizes to leave-P-out cross-validation and persists across a wide range of modeling and evaluation approaches, and that it can lead to a bias against stronger regularization. To address this, we propose a generalizable rebalanced cross-validation approach that corrects for distributional bias. We demonstrate that our approach improves cross-validation performance evaluation in synthetic simulations and in several published leave-one-out analyses. © 2024, CC BY-SA.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

EXPLANATION BY PROGRESSIVE EXAGGERATION 8

EXPLANATION BY PROGRESSIVE EXAGGERATION

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Singla, Sumedha Pollack, Brian Chen, Junxiang Batmanghelich, Kayhan Department of Computer Science University of Pittsburgh United States Department of Biomedical Informatics University of Pittsburgh United States Intelligent Systems Program University of Pittsburgh United States

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess feature importance (e.g., saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually changes the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a "tuning knob" to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Empowering Biomedical Discovery with AI Agents

arXiv

引用

arXiv 2024年

作者： Gao, Shanghua Fang, Ada Huang, Yepeng Giunchiglia, Valentina Noori, Ayush Schwarz, Jonathan Richard Ektefaie, Yasha Kondic, Jovana Zitnik, Marinka Department of Biomedical Informatics Harvard Medical School BostonMA United States Department of Chemistry and Chemical Biology Harvard University CambridgeMA United States Program in Biological and Biomedical Sciences Harvard Medical School BostonMA United States Department of Brain Sciences Imperial College London London United Kingdom Harvard College CambridgeMA United States Program in Biomedical Informatics Harvard Medical School BostonMA United States Department of Electrical Engineering and Computer Science MIT CambridgeMA United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University MA United States Broad Institute of MIT and Harvard CambridgeMA United States Harvard Data Science Initiative CambridgeMA United States

We envision "AI scientists" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with experimental platforms. Rather than taking humans out of the discovery process, biomedical AI agents combine human creativity and expertise with AI’s ability to analyze large datasets, navigate hypothesis spaces, and execute repetitive tasks. AI agents are poised to be proficient in various tasks, planning discovery workflows and performing self-assessment to identify and mitigate gaps in their knowledge. These agents use large language models and generative models to feature structured memory for continual learning and use machine learning tools to incorporate scientific knowledge, biological principles, and theories. AI agents can impact areas ranging from virtual cell simulation, programmable control of phenotypes, and the design of cellular circuits to developing new therapies. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Parameter Optimization of Support Vector Regression Using Harris Hawks Optimization

引用

Procedia computer science 2021年 179卷 17-24页

作者： I Nyoman Setiawan Robert Kurniawan Budi Yuniarto Rezzy Eko Caraka Bens Pardamean Computational Statistics Department Polytechnic of Statistics - STIS Jakarta 13330 Indonesia Department of Information Management College of Informatics Chaoyang University of Technology Taiwan (ROC) Bioinformatics and Data Science Research Center Bina Nusantara University Indonesia 11530 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia. 11530.

Support Vector Regression (SVR) is often used in forecasting. Adjustment of parameters in the SVR affects the results of forecasting. This study aims to analyze the SVR method that is optimized using Harris Hawks Optimization (HHO), hereinafter referred to as HHO-SVR. The HHO-SVR was evaluated using five benchmark datasets to determine the performance of this method. The HHO process is also compared based on the type of kernel and other metaheuristic algorithms. The results showed that the HHO-SVR has almost the same performance as other methods but is less efficient in terms of time. In addition, the type of kernel also affects the process and results.

关键词： SVR harris hawks optimization parameter optimization kernel forecasting

来源：评论

学校读者我要写书评

暂无评论

ζ-QVAE: A Quantum Variational Autoencoder utilizing Regularized Mixed-state Latent Representations

arXiv

引用

arXiv 2024年

作者： Wang, Gaoyuan Warrell, Jonathan Emani, Prashant S. Gerstein, Mark Program in Computational Biology and Bioinformatics Yale University New HavenCT06520 United States Department of Molecular Biophysics and Biochemistry Yale University New HavenCT06520 United States Department of Computer Science Yale University New HavenCT06520 United States Department of Statistics & Data Science Yale University New HavenCT06520 United States Department of Biomedical Informatics & Data Science Yale University New HavenCT06520 United States NEC Laboratories America PrincetonNJ08540 United States

A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves compressing the original data to manageable dimensions while still representing essential information for downstream analysis. In classical machine learning, variational autoencoders (VAEs) facilitate efficient data compression, representation learning for subsequent tasks, and novel data generation. However, no model has been proposed that exactly captures all of these features for direct application to quantum data on quantum computers. Some existing quantum models for data compression lack regularization of latent representations, thus preventing direct use for generation and control of generalization. Others are hybrid models with only some internal quantum components, impeding direct training on quantum data. To bridge this gap, we present a fully quantum framework, ζ-QVAE, which encompasses all the capabilities of classical VAEs and can be directly applied for both classical and quantum data compression. Our model utilizes regularized mixed states to attain optimal latent representations. It accommodates various divergences for reconstruction and regularization. Furthermore, by accommodating mixed states at every stage, it can utilize the full-data density matrix and allow for a"global"training objective. Doing so, in turn, makes efficient optimization possible and has potential implications for private and federated learning. In addition to exploring the theoretical properties of ζ-QVAE, we demonstrate its performance on representative genomics and synthetic data. Our results consistently indicate that ζ-QVAE exhibits similar or better performance compared to matched classical models. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

arXiv

引用

arXiv 2023年

作者： Chiu, Ching-Yu Müller, Meinard Davies, Matthew E.P. Su, Alvin Wen-Yu Yang, Yi-Hsuan The Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan The International Audio Laboratories Erlangen Germany The Department of Informatics Engineering Centre for Informatics and Systems of the University of Coimbra University of Coimbra Portugal The Department of Computer Science and Information Engineering National Cheng Kung University Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use "post-processing trackers" (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called "predominant local pulses" (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2023, CC BY.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-cellular Representations of Single-Cell Transcriptomics Data Enables Characterization of Patient-Level Disease States 29th

Learning Multi-cellular Representations of Single-Cell Tran...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Liu, Tianyu De Brouwer, Edward Kuo, Tony Diamant, Nathaniel Missarova, Alsu Wang, Hanchen Hao, Minsheng Bravo, Hector Corrada Scalia, Gabriele Regev, Aviv Heimberg, Graham Research and Early Development Genentech South San FranciscoCA94080 United States Interdepartmental Program in Computational Biology and Bioinformatics Yale University New HavenCT06511 United States Roche Informatics F. Hoffmann-La Roche Ltd. Mississauga Canada Department of Computer Science Stanford University Palo AltoCA94035 United States

ISBN: (纸本)9783031902512

Single-cell RNA-seq (scRNA-seq) has become a prominent tool for studying human biology and disease. The availability of massive scRNA-seq datasets and advanced machine learning techniques has recently driven the development of single-cell foundation models that provide informative and versatile cell representations based on expression profiles. However, to understand disease states, we need to consider entire tissue ecosystems, simultaneously considering many different interacting cells. Here, we tackle this challenge by generating patient-level representations derived from multi-cellular expression context measured with scRNA-seq of tissues. We develop PaSCient, a novel model that employs a multi-level representation learning paradigm and provides importance scores at the individual cell and gene levels for fine-grained analysis across multiple cell types and gene programs characteristic of a given disease. We apply PaSCient to learn a disease model across a large-scale scRNA-seq atlas of 12.5 million cells from over 2,700 patients. Comprehensive and rigorous benchmarking demonstrates the superiority of PaSCient in disease classification and its multiple downstream applications, including dimensionality reduction, gene/cell type prioritization, and patient subgroup discovery. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Biomolecules

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm to Update Incremental Attributes in Morphological Trees

SSRN

引用

SSRN 2022年

作者： Gobber, Charles Ferreira Hashimoto, Ronaldo Fumio Alves, Wonder Alexandre Luz Informatics and Knowledge Management Graduate Program Universidade Nove de Julho São Paulo Brazil Department of Computer Science Institute of Mathematics and Statistics Universidade de São Paulo São Paulo Brazil

Attribute Filters are powerful image simplification operators that have very good contour-preservation properties. They can be efficiently computed using morphological trees. The most common strategy to compute attribute filters using morphological trees is based on three steps: (i) tree construction: the tree is built along with its attributes;(ii) filtering: we simplify the tree by removing some of its nodes based on some attribute and a filtering rule defined on a threshold value;and (iii) image reconstruction: this is the final phase where the tree is converted back to an image leading to an attribute filter. However, after filtering a few attributes in tree may change and they must be updated, since some attribute filters are computed by filtering the simplified tree again, but with a different threshold. In this paper it is presented an efficient algorithm to update incremental attributes in morphological trees with low memory consumption and fast computation. © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Digital Technology in Health Education Trend Mapping through Bibliometrics Analysis

Digital Technology in Health Education Trend Mapping through...

引用

International Conference on informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Fairuz Iqbal Maulana Dian Lestari Vandha Pradwiyasma Widartha Nirwana Haidar Wahyu Dirgantara Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Faculty of Medicine Airlangga University Surabaya Indonesia Information System of Industrial Engineering Faculty Telkom University Bandung Indonesia Informatics Engineering Study Program University of Madura Pamekasan Indonesia Department of Electrical Engineering University of Merdeka Malang Malang Indonesia

ISBN: (纸本)9781665473286

This study examines the mapping of research data on digital technology in the field of health education using bibliometric analysis method. Data was collected by identifying keywords in the Scopus database and sorting them out to sort the studies from the last 10 years (2012–2021). Through this step, a total of 1482 documents were obtained (articles, journals, proceedings, books, and others). The data is then processed using the VOSViewer instrument to obtain a visualization of the mapping analysis. This study also analyzes the network types of authors and co-authors through the VOSViewer instrument. The result of this study indicates that the most document types published within ten years are Articles (66.5%), Review (22.9 % ), Conference Paper (4.2 % ), and others. The most studied subjects are Medicine (55.7%), Nursing (9.0%), Health Professions (8.2%), Social sciences (7.8%), Engineering (3.9%), computer science (2.6 % ), Environmental science (2.6 % ), Biochemistry-Genetics and Molecular Biology (2.2%), Psychology (1.6%), and Dentistry (1.3%). This study offers a written communication process and the nature and direction of developing descriptive means of counting and analyzing the various phases of communication as well as recognizing the authorship and direction of its symptoms in documents on the subject of digital technology in the health sector.

关键词： Training Pediatrics Instruments Education Bibliometrics Transportation Psychology

来源：评论

学校读者我要写书评

暂无评论

Lab: An R Package for Generating Analysis-Ready Data from Laboratory Records

SSRN

引用

SSRN 2022年

作者： Tseng, Yi-Ju Chen, Chun Ju Chang, Chia-Wei Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Computational Health Informatics Program Boston Children’s Hospital BostonMA United States Department of Information Management National Taiwan University Taipei Taiwan

Electronic health records (EHRs) enable physicians to understand disease progression, identify appropriate treatment, and participate in data-driven health-care decision-making. Laboratory test results, which are included in EHRs, are commonly used to predict disease progression. In addition, analyzing the temporal information in EHRs can improve outcomes, prognoses, and diagnosis monitoring and prediction. However, laboratory records contain both data on the tests ordered and test results. Furthermore, the irregular frequency of the data in these records necessitates data preprocessing when time-series analyses are performed, which increases the burden of these analyses. Therefore, we developed an open-source R package that enables analysts to easily retrieve detailed information from laboratory records by mapping local laboratory codes onto the international standard, annotating abnormal results, slicing the data into time-series windows, summarizing the data through descriptive statistics, imputing missing values, and generating analysis-ready data. The proposed lab package simplifies and speeds up the workflow of laboratory report extraction and may assist clinical data analysts in generating simple and clean script that can easily be shared and reproduced. © 2022, The Authors. All rights reserved.

关键词： Laboratories

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：