检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Pan, Xiaokang Li, Xingyu Liu, Jin Sun, Tao Sun, Kai Chen, Lixing Qu, Zhe Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China Department of Computer Science Tulane University New Orleans United States College of Computer National University of Defense Technology Changsha China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China Institute of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai China

STOchastic Recursive Momentum (STORM)based algorithms have been widely developed to solve one to K-level (K ≥ 3) stochastic optimization problems. Specifically, they use estimators to mitigate the biased gradient issue and achieve near-optimal convergence results. However, there is relatively little work on understanding their generalization performance, particularly evident during the transition from one to K-level optimization contexts. This paper provides a comprehensive generalization analysis of three representative STORM-based algorithms: STORM, COVER, and SVMR, for one, two, and K-level stochastic optimizations under both convex and strongly convex settings based on algorithmic stability. Firstly, we define stability for K-level optimizations and link it to generalization. Then, we detail the stability results for three prominent STORM-based algorithms. Finally, we derive their excess risk bounds by balancing stability results with optimization errors. Our theoretical results provide strong evidence to complete STORM-based algorithms: (1) Each estimator may decrease their stability due to variance with its estimation target. (2) Every additional level might escalate the generalization error, influenced by the stability and the variance between its cumulative stochastic gradient and the true gradient. (3) Increasing the batch size for the initial computation of estimators presents a favorable trade-off, enhancing the generalization performance. Copyright 2024 by the author(s)

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fetal ECG Extraction: Novel UNET Architecture using Continuous Wavelet Transforms performing dimentionality reduction

Enhancing Fetal ECG Extraction: Novel UNET Architecture usin...

引用

2024 International Conference on Integrated Circuits, Communication, and Computing Systems, ICIC3S 2024

作者： Shah, Tanish Pujari, Pratik Raotole, Atharv Joshi, Diya Sheladia, Om Shah, Devam Sardar Patel Institute of Technology Department of Information Technology Mumbai India Sardar Patel Institute of Technology Department of Computer Science Mumbai India DY Patil University Department of Bioinformatics Navi Mumbai India Veermata Jijabai Technological Institute Department of Electronics Engineering Mumbai India MPSTME Department of Mechatronics Engineering Mumbai India

ISBN: (纸本)9798350364088

Pregnancy-related fetal heart monitoring is essential for the earliest identification of any possible cardiac abnormalities and the implementation of appropriate treatments to ensure a safe delivery. Extracting fetal electrocardiograms (ECGs) from maternal belly ECGs is a widely studied method for fetal cardiac surveillance. However, it is challenging because fetal signals can be overshadowed by maternal ECG signals and noise. We present a novel approach for efficient separation of an one-channel maternal abdomen ECG into maternal and fetal segments. This addresses the complexities of the extraction process. We implemented a U-NET architecture combined with continuous wavelet transform, resulting in a reduction in training parameters and enhancing the efficiency of the baseline model. We evaluate our suggested architecture's foetal ECG detection performance against that of other cutting-edge deep learning models. Notably, our model incorporates the detection of P waves, a feature missing in existing methods. Our findings show that the suggested model performs better than any other proposed architecture with respect to F1 scores, recall, and accuracy. This suggests that our approach is effective in extracting fetal ECGs from single-channel maternal abdominal ECGs. This advancement in fetal cardiac monitoring can contribute significantly to the early identification of potential issues, allowing for timely preventive measures and ensuring healthier births. © 2024 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Evolution Of SARS-CoV-2 In The Presence Of Vaccines.

Evolution Of SARS-CoV-2 In The Presence Of Vaccines.

引用

2022 IEEE International Conference on bioinformatics and Biomedicine, BIBM 2022

作者： Marathe, Vishwajeet Yan, Changhui North Dakota State University Department of Computer Scienceline FargoND United States North Dakota State University Department of Computer Science Genomics Phenomics and Bioinformatics Graduate Program FargoND United States

ISBN: (纸本)9781665468190

The COVID pandemic has caused tremendous loss worldwide. Now vaccines are the primary weapon to combat the pandemic. Understanding how SARS-CoV-2, the virus that causes the COVID, may mutate in the presence of the vaccines is critical for designing drugs and vaccines for future variants of the virus. In this study, we investigated the numbers of mutations that SARS-CoV-2 accumulated on each protein over time. We found that different proteins of the virus accumulated different levels of mutations and their mutation rates changed over time following different patterns. We also presented evidence that the mutation of the Spike protein might have been suppressed by the vaccines. This is the first time that such a relation was reported based on real world data. Although the discovery was not meant to be conclusive, this study sheds light onto how the virus may response to the vaccines. If confirmed by further studies, the discovery will have significant impacts on many fields, including drug and vaccine designs. © 2022 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Identify Non-mutational p53 Functional Deficiency in Human Cancers

引用

genomics, Proteomics & bioinformatics 2024年第5期22卷 85-98页

作者： Qianpeng Li Yang Zhang Sicheng Luo Zhang Zhang Ann L.Oberg David E.Kozono Hua Lu Jann N.Sarkaria Lina Ma Liguo Wang National Genomics Data Center China National Center for BioinformationBeijing 100101China Beijing Institute of Genomics Chinese Academy of SciencesBeijing 100101China University of Chinese Academy of Sciences Beijing 100049China Division of Computational Biology Mayo Clinic College of Medicine and ScienceRochesterMN 55905USA Department of Radiation Oncology Dana-Farber Cancer Institute and Brigham and Women's HospitalBostonMA 02215USA Department of Biochemistry&Molecular Biology and Tulane Cancer Center Tulane University School of MedicineNew OrleansLA 70112USA Department of Radiation Oncology Mayo Clinic College of Medicine and ScienceRochesterMN 55905USA Department of Biochemistry and Molecular Biology Mayo Clinic College of Medicine and ScienceRochesterMN 55905USA Bioinformatics and Computational Biology Graduate Program University of Minnesota RochesterRochesterMN 55904USA

An accurate assessment of p53's functional statuses is critical for cancer genomic ***,there is a significant challenge in identifying tumors with non-mutational p53 inactivation which is not detectable through DNA *** undetected cases are often misclassified as p53-normal,leading to inaccurate prognosis and downstream association *** address this issue,we built the support vector machine(SVM)models to systematically reassess p53's functional statuses in TP53 wild-type(TP53^(WT))tumors from multiple The Cancer Genome Atlas(TCGA)***-validation demonstrated the good performance of the SVM models with a mean area under the receiver operating characteristic curve(AUROC)of 0.9822,precision of 0.9747,and recall of *** study revealed that a significant proportion(87%-99%)of TP53^(WT) tumors actually had compromised p53 *** analyses uncovered that these genetically intact but functionally impaired(termed as predictively reduced function of p53 or TP53^(WT)-pRF)tumors exhibited genomic and pathophysiologic features akin to TP53-mutant tumors:heightened genomic instability and elevated levels of ***,patients with TP53^(WT)-pRF tumors experienced significantly shortened overall survival or progression-free survival compared to those with predictively normal function of p53(TP53^(WT)-pN)tumors,and these patients also displayed increased sensitivity to platinum-based chemotherapy and radiation therapy.

关键词： Cancer Composite expression DNA mutation Machine learning p53 deficiency

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Breast Cancer Detection 11

Machine Learning-Based Breast Cancer Detection

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Asharma, Sourabh Shinde, Siddhesh Choudhary, Aditya Raj, Utkarsh Srivastava, Prashant Niit University Department of Biotechnology and Bioinformatics Rajasthan Neemrana India Niit University Department of Computer Science and Engineering Rajasthan Neemrana India Amity Institute of Information Technology Amity University Uttar Pradesh Uttar Pradesh Noida India

ISBN: (纸本)9798350350357

Breast cancer is the most frequent and prevalent malignancy among Indian women. In general, if a patient's breast symptoms or the findings of an imaging test (such as a mammography) indicate that the patient might have breast cancer, the patient is advised to undergo a breast biopsy. This paper focusses on one of the most common breast biopsies which is Fine Needle Aspiration here. In Fine Needle Aspiration biopsy, a little amount of breast tissue or fluid is taken from a suspicious location with a thin, hollow needle and examined for cancer cells. The problem statement is to use Breast Cancer Wisconsin Dataset which contains the numerical values of features of each cell nucleus calculated after Fine Needle Aspiration biopsy, implement various machine learning classifiers on the dataset and estimate the type of breast cancer being, benign or malignant. The experimental results show that the accuracy of the predictions made by each classifier increases either by hyper- tuning the parameters of each classifier or optimizing the classifiers so that a higher accuracy of the predictions can be achieved, and maximum lives can be saved by the predictions made. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

BAYESIAN ORACLE FOR BOUNDING INFORMATION GAIN IN NEURAL ENCODING MODELS 11

BAYESIAN ORACLE FOR BOUNDING INFORMATION GAIN IN NEURAL ENCO...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Lurz, Konstantin-Klemens Bashiri, Mohammad Walker, Edgar Y. Sinz, Fabian H. Institute for Bioinformatics and Medical Informatics University of Tübingen Germany Department of Physiology Computational Neuroscience Center University of Washington United States Department of Computer Science University Göttingen Germany

In recent years, deep learning models have set new standards in predicting neural population responses. Most of these models currently focus on predicting the mean response of each neuron for a given input. However, neural variability around this mean is not just noise and plays a central role in several theories on neural computation. To capture this variability, we need models that predict full response distributions for a given stimulus. However, to measure the quality of such models, commonly used correlation-based metrics are not sufficient as they mainly care about the mean of the response distribution. An interpretable alternative evaluation metric for likelihood-based models is Normalized Information Gain (NInGa) which evaluates the likelihood of a model relative to a lower and upper bound. However, while a lower bound is usually easy to obtain, constructing an upper bound turns out to be challenging for neural recordings with relatively low numbers of repeated trials, high (shared) variability, and sparse responses. In this work, we generalize the jack-knife oracle estimator for the mean-commonly used for correlation metrics-to a flexible Bayesian oracle estimator for NInGa based on posterior predictive distributions. We describe and address the challenges that arise when estimating the lower and upper bounds from small datasets. We then show that our upper bound estimate is data-efficient and robust even in the case of sparse responses and low signal-to-noise ratio. We further provide the derivation of the upper bound estimator for a variety of common distributions including the state-of-the-art zero-inflated mixture models, and relate NInGa to common mean-based metrics. Finally, we use our approach to evaluate such a mixture model resulting in 90% NInGa performance. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Minimal Area Detection of Weed Patches in UAV Imagery 3

Deep Learning Model for Minimal Area Detection of Weed Patch...

引用

3rd IEEE India Geoscience and Remote Sensing Symposium, InGARSS 2023

作者： Singh, Vyomika Luthra, Raghav Khangarot, Laxman Singh Singh, Dharmendra Indian Institute of Technology Roorkee Department of Electronics and Communication Engineering Roorkee India Jaypee University of Information Technology Department of Biotechnology and Bioinformatics Waknaghat India Indian Institute of Technology Roorkee Department of Computer Science and Engineering Roorkee India

ISBN: (纸本)9798350325591

Deep learning convolutional networks exhibit promising target localization and classification potential. Specifically designed for image processing and computer vision tasks, CNN based models can help detect camouflage targets merged with background. In this paper, we explore a deep learning model on UAV acquired camouflage dataset and attempt to localize, detect and classify early and multiple weed patches in a sugarcane field © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

VirusT5: Harnessing Large Language Models to Predicting SARS-CoV-2 Evolution

arXiv

引用

arXiv 2024年

作者： Marathe, Vishwajeet Bajracharya, Deewan Yan, Changhui The Department of Computer Science Department of North Dakota State University FargoND58102 United States The Genomics Phenomics and Bioinformatics Program of North Dakota State University FargoND58102 United States The Department of Computer Science and the Genomics Phenomics and Bioinformatics Program of North Dakota State University FargoND58102 United States

During a virus's evolution, various regions of the genome are subjected to distinct levels of functional constraints. Combined with factors like codon bias and DNA repair efficiency, these constraints contribute to unique mutation patterns within the genome or a specific gene. In this project, we harnessed the power of Large Language Models (LLMs) to predict the evolution of SARS-CoV-2. By treating the mutation process from one generation to the next as a translation task, we trained a transformer model, called VirusT5, to capture the mutation patterns underlying SARS-CoV-2's evolution. We evaluated the VirusT5's ability to detect these mutation patterns including its ability to identify mutation hotspots and explored the potential of using VirusT5 to predict future virus strains. Our findings demonstrate the feasibility of using a large language model to model viral evolution as a translation process. This study establishes the groundbreaking concept of "mutation-as-translation," paving the way for new methodologies and tools in combating viral threats. © 2024, CC BY.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Beyond Normal: On the Evaluation of Mutual Information Estimators 37

Beyond Normal: On the Evaluation of Mutual Information Estim...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Czyż, Pawel Grabowski, Frederic Vogt, Julia E. Beerenwinkel, Niko Marx, Alexander Department of Biosystems Science and Engineering ETH Zurich Switzerland ETH AI Center ETH Zurich Switzerland Institute of Fundamental Technological Research Polish Academy of Sciences Poland Department of Computer Science ETH Zurich Switzerland SIB Swiss Institute of Bioinformatics Switzerland

ISBN: (纸本)9781713899921

Mutual information is a general statistical dependency measure which has found applications in representation learning, causality, domain generalization and computational biology. However, mutual information estimators are typically evaluated on simple families of probability distributions, namely multivariate normal distribution and selected distributions with one-dimensional random variables. In this paper, we show how to construct a diverse family of distributions with known ground-truth mutual information and propose a language-independent benchmarking platform for mutual information estimators. We discuss the general applicability and limitations of classical and neural estimators in settings involving high dimensions, sparse interactions, long-tailed distributions, and high mutual information. Finally, we provide guidelines for practitioners on how to select appropriate estimator adapted to the difficulty of problem considered and issues one needs to consider when applying an estimator to a new data set. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of K-Nearest Neighbor and Support Vector Regression for Predicting Oil Palm Yield 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Pardamean, Bens Suparyanto, Teddy Sinaga, Gokma Sahat Tua Elwirehardja, Gregorius Natanael Firmansyah, Erick Ginting, Candra Mawandha, Hangger Gahara Putra, Dian Pratama Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program—Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Faculty of Agriculture Institute of Agriculture STIPER Yogyakarta55282 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

With the high demand for oil palm production, implementations of Machine Learning (ML) technologies to provide accurate predictions and recommendations to assist oil palm plantation management tasks have become beneficial, such as in predicting annual oil palm. However, different geographical and meteorological conditions may result in different scales of influence for each variable. In this research, K-Nearest Neighbors (KNN) and Support Vector Regression (SVR) were used in predicting oil palm yield based on data collected in Riau, Indonesia. Pearson’s correlation coefficient was also calculated in selecting the input features for the models, whereas normalization and standardization were used in scaling the data. By setting the minimum absolute correlation threshold to 0.1 and using standardization, both models managed to obtain more than 0.81 R2, with SVR obtaining the overall best performance with 0.8709 R2, 1.372 MAE, and 1.8025 RMSE without hyperparameter fine-tuning. It was also discovered that the oil palm yield in the previous year is the variable with the most influence in estimating oil palm yield in the current year, followed by the number of plants and soil types. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Machine learning

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：