检索结果-内蒙古大学图书馆

LIBRA:an adaptative integrative tool for paired single-cell multi-omics data

Quantitative Biology 2023年第3期11卷 246-259页

作者： Xabier Martinez-de-Morentin Sumeer AKhan Robert Lehmann Sisi Qu Alberto Maillo Narsis AKiani Felipe Prosper Jesper Tegner David Gomez-Cabrero Navarrabiomed Complejo Hospitalario de Navarra(CHN)Universidad Pública de Navarra(UPNA)IdiSNAPamplona 31001Spain Biological and Environmental Sciences and Engineering Division King Abdullah University of Science and TechnologyThuwal 23955Saudi Arabia Algorithmic Dynamic Lab Department of Oncology and PathologyCenter for Molecular MedicineKarolinska InstituteStockholm 17177Sweden Division of Hemato-Oncology Center for Applied Medical Research CIMACancer Center University of Navarra(CCUN)Navarra Institute for Health Research(IDISNA)CIBERONCPamplona 31008Spain Department of Hematology Clinica Universidad de NavarraCIBERONC Pamplona 31008Spain Computer Electrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and TechnologyThuwal 23955Saudi Arabia

Background:Single-cell multi-omics technologies allow a profound system-level biology understanding of cells and ***,an integrative and possibly systems-based analysis capturing the different modalities is *** response,bioinformatics and machine learning methodologies are being developed for multi-omics single-cell *** is unclear whether current tools can address the dual aspect of modality integration and prediction across modalities without requiring extensive parameter ***:We designed LIBRA,a neural network based framework,to learn translation between paired multi-omics profiles so that a shared latent space is ***,we implemented a variation,aLIBRA,that allows automatic fine-tuning by identifying parameter combinations that optimize both the integrative and predictive *** model parameters and evaluation metrics are made available to users with minimal user ***,aLIBRA allows experienced users to implement custom *** LIBRA toolbox is freely available as R and Python libraries at GitHub(TranslationalBioinformaticsUnit/LIBRA).Results:LIBRA was evaluated in eight multi-omic single-cell data-sets,including three combinations of *** observed that LIBRA is a state-of-the-art tool when evaluating the ability to increase cell-type(clustering)resolution in the integrated latent ***,when assessing the predictive power across data modalities,such as predictive chromatin accessibility from gene expression,LIBRA outperforms existing *** expected,adaptive parameter optimization(aLIBRA)significantly boosted the performance of learning predictive models from paired ***:LIBRA is a versatile tool that performs competitively in both“integration”and“prediction”tasks based on single-cell multi-omics *** is a data-driven robust platform that includes an adaptive learning scheme.

关键词： single-cell multi-omic Autoencoder auto-finetuning

来源：评论

学校读者我要写书评

暂无评论

Smart Diaper Embedded with Fully Printed Sensors for Wireless Healthcare and Monitoring

Smart Diaper Embedded with Fully Printed Sensors for Wireles...

引用

IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS)

作者： Shawkat Ali Arshad Khan Amine Bermak Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

In this research, a real-time healthcare and monitoring wireless system is developed to monitor vital signs of a wearer i.e., temperature, respiration rate, and wetting volume on a smartphone. The smart diaper consists of two main units, a detachable electronic module and a disposable printed biosensors patch deployed on a commercial diaper. Custom sensors array was designed and fabricated in a single patch through printed electronics technology by using biocompatible materials on a thermal transfer substrate. The sensors patch was designed in such a way to accurately collect the vital signs data by placing each sensor at appropriate site. Individual sensors were characterized for their electrical and mechanical properties. The overall system was tested, and data was wirelessly transmitted to a smartphone via Bluetooth. The main purpose of the proposed smart diaper is to minimize the effort of caregiver and avoid infection, rashes, and discomfort. We believe this work will open a new window for the printed electronics systems for special needs, elderly, and infant healthcare.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Beamforming Codebook Design for RIS-aided mmWave Systems

Deep Reinforcement Learning Based Beamforming Codebook Desig...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Asmaa Abdallah Abdulkadir Celik Mohammad M. Mansour Ahmed M. Eltawil Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal KSA Department of Elect. and Computer Engineering American University of Beirut Beirut Lebanon

Reconfigurable intelligent surfaces (RISs) are envisioned to play a pivotal role in future wireless systems with the capability of enhancing propagation environments by intelligently reflecting the signals toward the target receivers. However, the optimal tuning of the phase shifters at the RIS is a challenging task due to the passive nature of reflective elements and the high complexity of acquiring channel state information (CSI). Conventionally, wireless systems rely on pre-defined reflection beamforming codebooks for both initial access and data transmission. However, these existing pre-defined codebooks are commonly not adaptive to the environments. Moreover, identifying the best beam is typically performed using an exhaustive search that leads to high beam training overhead. To address these issues, this paper develops a multi-agent deep reinforcement learning framework that learns how to jointly optimize the active beamforming from the BS and the RIS-reflection beam codebook relying only on the received power measurements. To accelerate learning convergence and reduce the search space, the proposed model divides the RIS into multiple partitions and associates beam patterns to the surrounding environments with low computational complexity. Simulation results show that the proposed learning framework can learn optimized active BS beamforming and RIS reflection codebook. For instance, the proposed MA-DRL approach with only 6 beams outperforms a 256-beam discrete Fourier transform (DFT) codebook with a 97% beam training overhead reduction.

关键词： Training Wireless communication Deep learning Array signal processing Simulation Discrete Fourier transforms Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Unbiased Parameter Estimation for Bayesian Inverse Problems

arXiv

引用

arXiv 2025年

作者： Chada, Neil K. Jasra, Ajay Maama, Mohamed Tempone, Raul Department of Mathematics City University of Hong Kong China School of Data Science The Chinese University of Hong Kong Shenzhen CN Shenzhen China Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

In this paper we consider the estimation of unknown parameters in Bayesian inverse problems. In most cases of practical interest, there are several barriers to performing such estimation, This includes a numerical approximation of a solution of a differential equation and, even if exact solutions are available, an analytical intractability of the marginal likelihood and its associated gradient, which is used for parameter estimation. The focus of this article is to deliver unbiased estimates of the unknown parameters, that is, stochastic estimators that, in expectation, are equal to the maximizer of the marginal likelihood, and possess no numerical approximation error. Based upon the ideas of [4] we develop a new approach for unbiased parameter estimation for Bayesian inverse problems. We prove unbiasedness and establish numerically that the associated estimation procedure is faster than the current state-of-the-art methodology for this problem. We demonstrate the performance of our methodology on a range of problems which include a PDE and ODE. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Deep-learning based design of cascade observers for discrete-time nonlinear systems with output delay

引用

IFAC-PapersOnLine 2023年第2期56卷 9869-9874页

作者： Yasmine Marani Ibrahima N'Doye Taous Meriem Laleg-Kirati Computer Electrical and Mathematical Science and Engineering Division (CEMSE) King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Taous Meriem Laleg-Kirati is affiliated with the National Institute for Research in Digital Science and Technology Paris-Saclay France

Looking for a proper Lyapunov-based stability analysis for nonlinear discrete-time delay systems is non-trivial, even for constant delay. This paper proposes a learning approach that relies on neural networks to compute the state transformation map involved in the design of Kazantzis-Kravaris-Luenberger (KKL) based observers. Based on this transformation, we propose a chain of observers in cascade with exponential stability guarantees through the inverse transformation mapping in the original coordinates. Finally, we provide a simulation example that includes a sensitivity analysis of the delay parameter to illustrate the performance and demonstrate the effectiveness of the proposed learning-based design of chain observers for discrete-time nonlinear systems with output measurement delay.

关键词： Discrete-time nonlinear systems delay systems chain observers deep-learning design state observers

来源：评论

学校读者我要写书评

暂无评论

How "Like-minded Peers" Enhanced Session-Based Social Recommendation

How "Like-minded Peers" Enhanced Session-Based Social Recomm...

引用

IEEE International Conference on Web Services (ICWS)

作者： Yunhan Li Chunyan An Qiang Yang Winston K.G. Seah Conghao Yang College of Computer Science Inner Mongolia University Hohhot China King Abdullah University of Science and Technology Thuwal Kingdom of Saudi Arabia School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Session-based Social Recommendation (SSR) harnesses social relationships within online social networks to improve Session-based Recommendation (SR) performance. However, existing SSR algorithms often face the challenge of "friend data sparsity". Additionally, significant discrepancies may exist between the purchase preferences of social network friends and those of the target user, thereby diminishing the influence of friends relative to the target user’s preferences. To tackle these challenges, this paper introduces the concept of "Like-minded Peers" (LMP), representing users whose preferences are aligned with the target user’s current session in their history sessions. To the best of our knowledge, this is the first work to use LMP as an enhancement for modeling the social influence in SSR. It not only alleviates the problem of friend data sparseness but also effectively incorporates users with similar preferences. Furthermore, we propose a novel model named Transformer Encoder with Graph Attention Aggregator Recommendation. Experimental results on four real-world datasets demonstrates the efficacy and superiority of our proposed model.

关键词： Social networking (online) Web services Neural networks Transformers History Faces

来源：评论

学校读者我要写书评

暂无评论

Non-Asymptotic Neural Network-based State and Disturbance Estimation for a Class of Nonlinear Systems using Modulating Functions

Non-Asymptotic Neural Network-based State and Disturbance Es...

引用

American Control Conference (ACC)

作者： Yasmine Marani Ibrahima N’Doye Taous Meriem Laleg Kirati Computer Electrical and Mathematical Science and Engineering Division (CEMSE) King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia National Institute for Research in Digital Science and Technology Paris-Saclay France

Model disturbances result from model uncertainties or external factors acting on the system. They usually affect the closed-loop performance in a control loop system. However, they are often unknown and cannot be then compensated. Therefore, it is crucial to develop estimation methods for the effective estimation of the disturbances which can be then considered appropriately in the control design. This paper proposes a hybrid method for the joint estimation of the state and the disturbance for a class of nonlinear systems in two steps. The approach consists in a neural network with time-varying weights used to approximate the disturbance term and a modulating function method for the finite-time estimation of the state and the weights. The modulating functions approach simplifies the estimation problem into solving an algebraic systems of equations. Both offline and online frameworks are presented and discussed. An example is presented to demonstrate the performance of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

engineering of dendritic dopant-free hole transport molecules:enabling ultrahigh fill factor in perovskite solar cells with optimized dendron construction

引用

science China Chemistry 2021年第1期64卷 41-51页

作者： Wei Chen Yang Wang Bin Liu Yajun Gao Ziang Wu Yongqiang Shi Yumin Tang Kun Yang Yujie Zhang Weipeng Sun Xiyuan Feng Frédéric Laquai Han Young Woo Aleksandra B.Djurisic Xugang Guo Zhubing He Department of Materials Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Department of Physics The University of Hong KongPokfulamHong KongChina King Abdullah University of Science and Technology KAUST Solar CenterPhysical Sciences and Engineering DivisionMaterial Science and Engineering ProgramThuwal 23955-6900Kingdom of Saudi Arabia Department of Chemistry Korea UniversitySeoul 02841South Korea

Developing dopant-free hole-transporting materials(HTMs)for high-performance perovskite solar cells(PVSCs)has been a very active research topic in recent years since HTMs play a critical role in optimizing interfacial charge carrier kinetics and in turn determining device ***,a novel dendritic engineering strategy is first utilized to design HTMs with a D-A type molecular framework,and diphenylamine and/or carbazole is selected as the building block for constructing *** HTMs show good thermal stability and excellent film morphology,and the key optoelectronic properties could be fine-tuned by varying the dendron *** them,MPA-Cz-BTI and MCz-Cz-BTI exhibit an improved interfacial contact with the perovskite active layer,and non-radiative recombination loss and charge transport loss can be effectively ***,high power conversion efficiencies(PCEs)of 20.8%and 21.35%are achieved for MPA-Cz-BTI and MCz-Cz-BTI based devices,respectively,accompanied by excellent long-term storage *** encouragingly,ultrahigh fill factors of 85.2%and 83.5%are recorded for both devices,which are among the highest values reported to *** work demonstrates the great potential of dendritic materials as a new type of dopant-free HTMs for high-performance PVSCs with excellent FF.

关键词： dendritic molecules hole-transporting materials dopant-free ultrahigh fill factor perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

Generalized linear models in non-interactive local differential privacy with public data

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 6027-6083页

作者： Di Wang Lijie Hu Huanyu Zhang Marco Gaboardi Jinhui Xu CEMSE King Abdullah University of Science and Technology Thuwal Saudi Arabia Meta New York NY Department of Computer Science Boston University Boston MA Department of Computer Science and Engineering University at Buffalo SUNY Buffalo NY

In this paper, we study the problem of estimating smooth Generalized Linear Models (GLMs) in the Non-interactive Local Differential Privacy (NLDP) model. Unlike its classical setting, our model allows the server to access additional public but unlabeled data. In the first part of the paper, we focus on GLMs. Specifically, we first consider the case where each data record is i.i.d. sampled from a zero-mean multivariate Gaussian distribution. Motivated by the Stein's lemma, we present an (ε, δ)-NLDP algorithm for GLMs. Moreover, the sample complexity of public and private data for the algorithm to achieve an ℓ2-norm estimation error of α (with high probability) is O(pα-2) and Õ(p3α-2ε-2) respectively, where p is the dimension of the feature vector. This is a significant improvement over the previously known exponential or quasi-polynomial in α-1, or exponential in p sample complexities of GLMs with no public data. Then we consider a more general setting where each data record is i.i.d. sampled from some sub-Gaussian distribution with bounded ℓ1-norm. Based on a variant of Stein's lemma, we propose an (ε, δ)-NLDP algorithm for GLMs whose sample complexity of public and private data to achieve an ℓ∞-norm estimation error of α is O(p2α-2) and Õ(p2α-2ε-2) respectively, under some mild assumptions and if α is not too small (i.e., α≥Ω(1/√p)). In the second part of the paper, we extend our idea to the problem of estimating non-linear regressions and show similar results as in GLMs for both multivariate Gaussian and sub-Gaussian cases. Finally, we demonstrate the effectiveness of our algorithms through experiments on both synthetic and real-world datasets. To our best knowledge, this is the first paper showing the existence of efficient and effective algorithms for GLMs and non-linear regressions in the NLDP model with unlabeled public data.

关键词： differential privacy generalized linear models local differential privacy

来源：评论

学校读者我要写书评

暂无评论

Understanding Forgetting in Continual Learning with Linear Regression: Overparameterized and Underparameterized Regimes

arXiv

引用

arXiv 2024年

作者： Ding, Meng Ji, Kaiyi Wang, Di Xu, Jinhui Department of Computer Science and Engineering State University of New York at Buffalo Buffalo United States Division of CEMSE King Abdullah University of Science and Technology Thuwal Saudi Arabia

Continual learning, focused on sequentially learning multiple tasks, has gained significant attention recently. Despite the tremendous progress made in the past, the theoretical understanding, especially factors contributing to catastrophic forgetting, remains relatively unexplored. In this paper, we provide a general theoretical analysis of forgetting in the linear regression model via Stochastic Gradient Descent (SGD) applicable to both under-parameterized and overparameterized regimes. Our theoretical framework reveals some interesting insights into the intricate relationship between task sequence and algorithmic parameters, an aspect not fully captured in previous studies due to their restrictive assumptions. Specifically, we demonstrate that, given a sufficiently large data size, the arrangement of tasks in a sequence-where tasks with larger eigenvalues in their population data covariance matrices are trained later-tends to result in increased forgetting. Additionally, our findings highlight that an appropriate choice of step size will help mitigate forgetting in both under-parameterized and overparameterized settings. To validate our theoretical analysis, we conducted simulation experiments on both linear regression models and Deep Neural Networks (DNNs). Results from these simulations substantiate our theoretical findings. © 2024, CC BY-NC-SA.

关键词： Deep neural networks

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：