检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Clum, Charles Mixon, Dustin G. Villar, Soledad Xie, Kaiying Department of Mathematics The Ohio State University ColumbusOH United States Translational Data Analytics Institute The Ohio State University ColumbusOH United States Department of Applied Mathematics & Statistics Johns Hopkins University BaltimoreMD United States Mathematical Institute for Data Science Johns Hopkins University BaltimoreMD United States Department of Electrical and Computer Engineering The Ohio State University ColumbusOH United States

We introduce a sketch-and-solve approach to speed up the Peng-Wei semidefinite relaxation of k-means clustering. When the data is appropriately separated we identify the k-means optimal clustering. Otherwise, our approach provides a high-confidence lower bound on the optimal k-means value. This lower bound is data-driven;it does not make any assumption on the data nor how it is generated. We provide code and an extensive set of numerical experiments where we use this approach to certify approximate optimality of clustering solutions obtained by k-means++. © 2022, CC BY.

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

Glacier: Glass-Box Transformer for Interpretable Dynamic Neuroimaging

Glacier: Glass-Box Transformer for Interpretable Dynamic Neu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Usman Mahmood Zening Fu Vince Calhoun Sergey Plis Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Georgia Institute of Technology Emory University Atlanta GA USA Department of Computer Science Georgia State University Atlanta GA USA Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA

Deep learning models can perform as well or better than humans in many tasks, especially vision related. Almost exclusively, these models are used to perform classification or prediction. However, deep learning models are usually of black-box nature, and it is often difficult to interpret the model or the features. The lack of interpretability causes a restrain from applying deep learning to fields such as neuroimaging, where the results must be transparent, and interpretable. Therefore, we present a ’glass-box’ deep learning model and apply it to the field of neuroimaging. Our model mixes spatial and temporal dimensions in succession to estimate dynamic connectivity between the brain’s intrinsic networks. The interpretable connectivity matrices produced by our model result in beating state-of-the-art models on many tasks using multiple functional MRI datasets. More importantly, our model estimates task-based flexible connectivity matrices, unlike static methods such as Pearson’s correlation coefficients.

关键词： Neuroimaging Deep learning Magnetic resonance imaging Signal processing Predictive models Brain modeling Transformers

来源：评论

学校读者我要写书评

暂无评论

Optimizing Ethanol Production in Escherichia Coli Using a Hybrid of Particle Swarm Optimization and Artificial Bee Colony 6

Optimizing Ethanol Production in Escherichia Coli Using a Hy...

引用

6th International Conference on Advances in Artificial Intelligence, ICAAI 2022

作者： Dzulkalnine, Mohamad Faiz Mohamad, Mohd Saberi Choon, Yee Wen Remli, Muhammad Akmal Alashwal, Hany Artificial Intelligence and Bioinformatics Research Group Faculty of Computing Universiti Teknologi Malaysia Johor81310 Malaysia Health Data Science Lab Department of Genetics and Genomics College of Medical and Health Sciences United Arab Emirates University P.O. Box 17666 Al Ain Abu Dhabi United Arab Emirates Big Data Analytics Center United Arab Emirates University Al Ain Abu Dhabi United Arab Emirates Institute for Artificial Intelligence and Big Data Universiti Malaysia Kelantan Kelantan Kota Bharu16100 Malaysia Department of Data Science Universiti Malaysia Kelantan Kelantan Kota Bharu16100 Malaysia Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al-Ain United Arab Emirates

ISBN: (纸本)9781450396943

Metabolic engineering for biomass production using microorganisms' cell has received considerable attention in recent years. This is due to the biomass products being extensively used in the field of food additives, supplements, pharmaceuticals, and polymer materials. In this paper, ethanol production in Escherichia coli (E. coli) is the desired product. Sugarcane and corn are often used to produce ethanol. However, one of the problems to produce adequate amounts of ethanol is that large areas are needed to plant sugarcane and corn. Furthermore, the amount of time for the process of dry milling and wet milling is high, which are 40 to 50 hours and 24 to 48 hours, respectively. The wet laboratory is also having limitation on the production of ethanol in microorganisms because the amount of the ethanol produced is not satisfying. Hence, a lot of metabolic engineering techniques is introduced to enhance the production of ethanol in E. coli, such as gene knockout strategy, but the production is yet to meet the demand. Therefore, this paper proposes a hybrid algorithm of Particle Swarm Optimization with the Artificial Bee Colony algorithm (PSOABC) to identify the optimal set of gene knockout strategy to improve the ethanol production in E. coli. A list of genes to knockout, production of the desired product, and growth rate are presented in this paper. PSOABC has shown better performance in terms of production, growth rate and accuracy. © 2022 Association for Computing Machinery.

关键词： Ethanol

来源：评论

学校读者我要写书评

暂无评论

Advanced machine learning in neuroimaging studies via federated learning

Advanced machine learning in neuroimaging studies via federa...

引用

IEEE International Conference on Big data

作者： Sunitha Basodi Javier Romero Sandeep Panta Dylan Martin Sergey Plis Anand D. Sarwate Vince D. Calhoun Tri-Institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology Emory University Atlanta GA USA Department of Electrical & Computer Engineering Rutgers University NJ USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Federated analysis can help perform large-scale analyses using neuroimaging datasets across various research groups overcoming the limitations of institutional data-sharing policies, privacy or regulatory concerns as it requires no data sharing. In this work, we employ a federated neuromark algorithm to generate independent component analysis (ICA) time courses data from functional magnetic resonance imaging (fMRI) data and feed it to a federated deep neural network (DNN) model to perform classification of schizophrenia patients versus controls.

关键词： Neuroimaging data privacy Machine learning algorithms Federated learning Artificial neural networks Independent component analysis Functional magnetic resonance imaging Schizophrenia data models Feeds

来源：评论

学校读者我要写书评

暂无评论

Protecting Deep Neural Networks in Cloud-Based Environments Towards Backdoor Assaults

Protecting Deep Neural Networks in Cloud-Based Environments ...

引用

Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), International Conference on

作者： Manjunatha R Naresh Kaushik Yaduvir Singh Department of Data analytics and Mathematical Sciences School of Sciences JAIN (Deemed to be University) Bangalore Karnataka India Department of uGDX ATLAS SkillTech University Mumbai Maharashtra India Department of Computer Science and Engineering (AI) Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India

ISBN: (数字)9798350355338

ISBN: (纸本)9798350355345

When it comes to training deep neural networks, especially those with complicated architectures, the accompanying financial and temporal costs often force resource-constrained customers to outsource their learning process via cloud service providers. But there's a risk that dishonest cloud providers may include backdoors and jeopardise the security of the overall model. Users may examine the model closely and utilise state-of-the-art defence techniques to reduce this danger. The goal of this research is to create a robust backdoor attack technique called RobNet that can circumvent current defences from the perspective of malevolent cloud providers. Furthermore, multi-trigger backdoor assaults are introduced, which enlarge the attack area by misclassifying inputs with different triggers into target labels that are either identical or dissimilar. RobNet is tested against four popular defence techniques (Pruning, NeuralCleanse, Strip, and ABS) using datasets from MNIST, GTSRB, and CIFAR-10. RobNet has a higher attack success rate and more robustness against possible defensive measures when compared to two state-of-the-art baselines: Hidden Backdoors and BadNets.

关键词： Training Technological innovation Strips Neurons Artificial neural networks Robustness Service-oriented architecture Security Biological neural networks Resilience

来源：评论

学校读者我要写书评

暂无评论

Evaluating Trade-Offs in IVA of Multimodal Neuroimaging using Cross-Platform Multidataset Independent Subspace Analysis

Evaluating Trade-Offs in IVA of Multimodal Neuroimaging usin...

引用

IEEE International Symposium on Biomedical Imaging

作者： Xinhui Li Daniel Khosravinezhad Vince D. Calhoun Rogers F. Silva Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Georgia Institute of Technology and Emory University Atlanta GA USA Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA

Multidataset independent subspace analysis (MISA) unifies multiple linear blind source separation methods to analyze joint and unique information across multiple datasets. MISA can jointly analyze large multimodal neuroimaging datasets to advance our understanding of the brain from multiple perspectives. However, a systematic evaluation of the trade-offs between problem scale and sample size is still absent in the literature. Aiming to support flexibility and replicability of deep latent variable modeling, and equip practitioners with crucial tools and usage guidelines, we developed a MISA PyTorch module incorporating the linked multi-network architecture and loss function of the original MISA MATLAB. We then investigated critical performance trade-offs between latent space and sample sizes in independent vector analysis (IVA) problems. Both platforms were highly similar in hundreds of simulation settings, demonstrating successful replication of the original framework and flexibility to evaluate multiple configurations. We observed that a larger sample size, fewer datasets and fewer sources can lead to better IVA model performance. We then performed an IVA experiment on a large multimodal neuroimaging dataset and observed high cross-modal correlation linkage among the identified sources in both platforms, supporting MISA’s effectiveness for replicable multimodal linkage detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient data Collection using Whale Optimization Algorithm (WOA) in Wireless Sensor Network

An Efficient Data Collection using Whale Optimization Algori...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Udhayakumar Pasupathi A. Gopi Saminathan A. Manikandan M. Subhashini C. Gowrishankar T. S. Poornappriya Department of Computer Science Srimad Andavan Arts and Science College (Autonomous) (Affiliated to Bharathidasan University Tiruchirappalli) Tamilnadu India NPR College of Engineering and Technology Dindigul ECE SRM Institute of Science and Technology Chennai Department of Computer Science Srimad Andavan Arts and Science College (Autonomous) Trichy-5 Department of Electrical and Electronics Engineering Kongunadu College of Engineering and Technology Tiruchirappalli Module Lead Data and Analytics Aspire Systems Pvt Ltd Karnataka

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Wireless sensor networks (WSNs) are an innovative technology that can be used in critical situations such as battlefields as well as commercial applications including buildings, traffic monitoring, smart homes, habitat monitoring, and more. A wireless sensor network (WSN) comprises small nodes capable of wireless sensing, processing, and communication. One of the most pressing concerns plaguing WSNs today is security. This paper suggests and investigates an energy-efficient cluster head (CH) selection approach using the Whale Optimization Algorithm (WOA) (called WOA-Clustering (WOA-C)) and the Geographic and Energy Aware Routing Algorithm (GEAR). As a result, the suggested method simplifies the decision-making process of energy-aware CHs by utilizing the fitness function that assesses node residual energy and the total energy of neighbouring nodes. Compared to the GWO-C, GABEEC, and PSOMSB protocols, the proposed WOA-GEAR protocol consumes 28%, 22%, and 7.5% less power. The suggested algorithm's network lifetime, power efficiency, buffer occupancy, throughput, and end-to-end latency were evaluated.

关键词： Wireless communication Wireless sensor networks Gears Query processing Clustering algorithms Energy efficiency Whale optimization algorithms Routing protocols Security Monitoring

来源：评论

学校读者我要写书评

暂无评论

Efficient and Scalable Parametric High-Order Portfolios Design via the Skew-t Distribution

arXiv

引用

arXiv 2022年

作者： Wang, Xiwen Zhou, Rui Ying, Jiaxi Palomar, Daniel P. The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong The Shenzhen Research Institute of Big Data Shenzhen China The Department of Mathematics Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong The Department of Electronic and Computer Engineering Department of Industrial Engineering and Decision Analytics Hong Kong University of Science and Technology Kowloon Hong Kong

Since Markowitz’s mean-variance framework, optimizing a portfolio that strikes a trade-off between maximizing profit and minimizing risk has been ubiquitous in the financial industry. Initially, profit and risk were measured by the first two moments of the portfolio’s return, a.k.a. the mean and variance, which are sufficient to characterize a Gaussian distribution. However, it is broadly believed that the first two moments are not enough to capture the characteristics of the returns’ behavior, which have been recognized to be asymmetric and heavy-tailed. Although portfolio designs involving the third and fourth moments, i.e., skewness and kurtosis, have been demonstrated to outperform the conventional mean-variance framework, they present non-trivial challenges. Specifically, in the classical framework, the memory and computational cost of computing the skewness and kurtosis grow sharply with the number of assets. To alleviate the difficulty in high-dimensional problems, we consider an alternative expression for high-order moments based on parametric representations via a generalized hyperbolic skew-t distribution. Then, we reformulate the high-order portfolio optimization problem as a fixed-point problem and propose a robust fixed-point acceleration algorithm that solves the problem in an efficient and scalable manner. Empirical experiments also attest to the efficiency of our proposed high-order portfolio optimization framework, which presents low complexity and significantly outperforms the state-of-the-art methods by 2 ∼ 4 orders of magnitude. Copyright © 2022, The Authors. All rights reserved.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Large-scale benchmarking of circRNA detection tools reveals large differences in sensitivity but not in precision

引用

Nature methods 2025年第2期22卷 448页

作者： Marieke Vromman Jasper Anckaert Stefania Bortoluzzi Alessia Buratin Chia-Ying Chen Qinjie Chu Trees-Juen Chuang Roozbeh Dehghannasiri Christoph Dieterich Xin Dong Paul Flicek Enrico Gaffo Wanjun Gu Chunjiang He Steve Hoffmann Osagie Izuogu Michael S Jackson Tobias Jakobi Eric C Lai Justine Nuytens Julia Salzman Mauro Santibanez-Koref Peter Stadler Olivier Thas Eveline Vanden Eynde Kimberly Verniers Guoxia Wen Jakub Westholm Li Yang Chu-Yu Ye Nurten Yigit Guo-Hua Yuan Jinyang Zhang Fangqing Zhao Jo Vandesompele Pieter-Jan Volders OncoRNALab Cancer Research Institute Ghent (CRIG) Department of Biomolecular Medicine Ghent University Ghent Belgium. Department of Molecular Medicine University of Padova Padova Italy. Genomics Research Center Academia Sinica Taipei City Taiwan. Institute of Crop Science and Institute of Bioinformatics Zhejiang University Zhejiang China. Department of Biomedical Data Science and of Biochemistry Stanford University Stanford CA USA. Klaus Tschira Institute for Integrative Computational Cardiology Department of Internal Medicine III University Hospital Heidelberg German Center for Cardiovascular Research (DZHK) Heidelberg Germany. School of Basic Medical Science Department of Medical Genetics Wuhan University Wuhan China. EMBL-EBI Hinxton UK. Collaborative Innovation Center of Jiangsu Province of Cancer Prevention and Treatment of Chinese Medicine School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China. Computational Biology Group Leibniz Institute on Aging - Fritz Lipmann Institute (FLI) Jena Germany. Biosciences Institute Faculty of Medical Sciences Newcastle University Newcastle UK. Translational Cardiovascular Research Center University of Arizona - College of Medicine Phoenix Phoenix AZ USA. Sloan Kettering Institute New York NY USA. Bioinformatics Group Department of Computer Science and Interdisciplinary Center for Bioinformatics Universität Leipzig Leipzig Germany. Data Science Institute I-Biostat Hasselt University Hasselt Belgium. State Key Laboratory of Bioelectronics School of Biological Sciences and Medical Engineering Southeast University Nanjing China. Department of Biochemistry and Biophysics National Bioinformatics Infrastructure Sweden Science for Life Laboratory Stockholm University Stockholm Sweden. Center for Molecular Medicine Children's Hospital Fudan University and Shanghai Key Laboratory of Medical Epigenetics International Laboratory of Medical Epigenetics and Metab

来源：评论

学校读者我要写书评

暂无评论

T-Cell Receptor Optimization with Reinforcement Learning and Mutation Polices for Precision Immunotherapy 27th

T-Cell Receptor Optimization with Reinforcement Learning an...

引用

27th International Conference on Research in Computational Molecular Biology, RECOMB 2023

作者： Chen, Ziqi Min, Martin Renqiang Guo, Hongyu Cheng, Chao Clancy, Trevor Ning, Xia Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Machine Learning Department NEC Labs PrincetonNJ08540 United States Digital Technologies Research Centre National Research Council Canada Ontario Canada Department of Medicine Baylor College of Medicine HoustonTX77030 United States NEC Oncolmmunity AS Oslo Cancer Cluster Innovation Park Ullernchausséen 64 Oslo0379 Norway Biomedical Informatics The Ohio State University ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States

ISBN: (纸本)9783031291180

T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune response. Optimizing TCR sequences for TCR recognition represents a fundamental step towards the development of personalized treatments to trigger immune responses killing cancerous or virus-infected cells. In this paper, we formulated the search for these optimized TCRs as a reinforcement learning (Formula Presented) problem, and presented a framework (Formula Presented) with a mutation policy using proximal policy optimization. (Formula Presented) mutates TCRs into effective ones that can recognize given peptides. (Formula Presented) leverages a reward function that combines the likelihoods of mutated sequences being valid TCRs measured by a new scoring function based on deep autoencoders, with the probabilities of mutated sequences recognizing peptides from a peptide-TCR interaction predictor. We compared (Formula Presented) with multiple baseline methods and demonstrated that (Formula Presented) significantly outperforms all the baseline methods to generate positive binding and valid TCRs. These results demonstrate the potential of(Formula Presented) for both precision immunotherapy and peptide-recognizing TCR motif discovery. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Reinforcement 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：