检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qiu, Jingna Aubreville, Marc Wilm, Frauke Öttl, mathias Utz, Jonas Schlereth, Maja Breininger, Katharina Department Artificial Intelligence in Biomedical Engineering FAU Erlangen-Nürnberg Erlangen Germany Technische Hochschule Ingolstadt Ingolstadt Germany Flensburg University of Applied Sciences Flensburg Germany Pattern Recognition Lab Department of Computer Science FAU Erlangen-Nürnberg Erlangen Germany Center for AI and Data Science Universität Würzburg Würzburg Germany

Acquiring annotations for whole slide images (WSIs)-based deep learning tasks, such as creating tissue segmentation masks or detecting mitotic figures, is a laborious process due to the extensive image size and the significant manual work involved in the annotation. This paper focuses on identifying and annotating specific image regions that optimize model training, given a limited annotation budget. While random sampling helps capture data variance by collecting annotation regions throughout the WSI, insufficient data curation may result in an inadequate representation of minority classes. Recent studies proposed diversity sampling to select a set of regions that maximally represent unique characteristics of the WSIs. This is done by pretraining on unlabeled data through self-supervised learning and then clustering all regions in the latent space. However, establishing the optimal number of clusters can be difficult and not all clusters are task-relevant. This paper presents prototype sampling, a new method for annotation region selection. It discovers regions exhibiting typical characteristics of each task-specific class. The process entails recognizing class prototypes from extensive histopathology image-caption databases and detecting unlabeled image regions that resemble these prototypes. Our results show that prototype sampling is more effective than random and diversity sampling in identifying annotation regions with valuable training information, resulting in improved model performance in semantic segmentation and mitotic figure detection tasks. Code is available at https://***/DeepMicroscopy/Prototype-sampling. Copyright © 2024, The Authors. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Artificial Bee Colony Based Gabor Parameters Optimizer (ABC-GPO) for Modulation Classification

引用

Computational Intelligence and Neuroscience 2022年第0期2022卷 9464633页

作者： Aljubayrin, Saad Sarfraz, Mubashar Ghauri, Sajjad A. Amirzada, Muhammad Rizwan Mezgebo Kebedew, Teweldebrhan Department of Computer Science College of Computing and Information Technology Shaqra University Shaqra Saudi Arabia Faculty of Engineering and Computer Science National University of Modern Languages Islamabad Pakistan School of Engineering & Applied Sciences ISRA University Islamabad Pakistan Ethio Telecom Addis Ababa Ethiopia

Modulation classification is one of the essential requirements in the various cognitive radio applications where prior information about the incoming signal is unknown. The modulation classification using a pattern recognition approach can be achieved in 2 modules: first, parameters are extracted from the noisy signal, and then feature selection is carried out using a Gabor filter network (GFN). In the second module, features are exploited for classification purposes. The modulation formats considered for the purpose of classification are BPSK, QPSK, 8PSK, 16PSK, 64PSK, 4FSK, 8FSK, 16FSK, QAM, 8QAM, 16QAM, 32QAM, and 64QAM. The Gabor filter parameters and weights of the adaptive filter are attuned using the Delta rule and recursive least square (RLS) algorithm until the cost function is minimized. In the end, the artificial bee colony (ABC) algorithm is used to optimize the Gabor parameters as well as the classifier's performance. The simulation results show the supremacy of the proposed classifier structure. © 2022 Saad AlJubayrin et al.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

A Cross-Cultural Assessment of the Actual Application of Cloud-Based Computing in Higher Education Using Data Management Variables

A Cross-Cultural Assessment of the Actual Application of Clo...

引用

IEEE UP Section Conference on Electrical computer and Electronics (UPCON)

作者： K. Deepthi Mohit Tiwari Melanie Lourens Vijilius Helena Raj Y Manohar Reddy Atul Singla School of CS & AL SR University Warangal Telangana India Department of Computer Science and Engineering Bharati Vidyapeeth's College of Engineering Delhi Faculty of Management Sciences Durban University of Technology South Africa Department of Applied Sciences New Horizon College of Engineering Bangalore Institute of Aeronautical Engineering Hyderabad Lovely Professional University Phagwara

The relationship between data management and cloud-based computation is well-endorsed in the available research. Nevertheless, the contribution of cross-culture in this connection is poorly recognized. As a result, the objective of this research is to analyze the influence of cross-culture in the connection between data management and cloud computing adoption in higher education. This study included 349 Malaysian and 300 Turkish college students. Cross-cultural variations are studied using a multi-group modeling of structural equations technique. According to the findings, the association between perceived simplicity of use and applicability was favorable in both nations, although it was stronger in Malaysia. Malaysia also had a stronger link between perceived simplicity of use and intended action. In addition, for Turkey, perceived applicability strongly predicts intended actions, whereas, for Malaysia, the relationship was not strong. The findings revealed that data management influenced perceived applicability in Turkey, but not in Malaysia. Finally, the results demonstrated that cross-culture plays a significant part in the connection between data management and cloud computing in higher education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expressive probabilistic sampling in recurrent neural networks

arXiv

引用

arXiv 2023年

作者： Chen, Shirui Jiang, Linxing Preston Rao, Rajesh P.N. Shea-Brown, Eric Department of Applied Mathematics University of Washington Seattle United States Paul G. Allen School of Computer Science & Engineering University of Washington Seattle United States Center for Neurotechnology University of Washington Seattle United States Department of Applied Mathematics Computational Neuroscience Center University of Washington Seattle United States

In sampling-based Bayesian models of brain function, neural activities are assumed to be samples from probability distributions that the brain uses for probabilistic computation. However, a comprehensive understanding of how mechanistic models of neural dynamics can sample from arbitrary distributions is still lacking. We use tools from functional analysis and stochastic differential equations to explore the minimum architectural requirements for recurrent neural circuits to sample from complex distributions. We first consider the traditional sampling model consisting of a network of neurons whose outputs directly represent the samples (sampler-only network). We argue that synaptic current and firing-rate dynamics in the traditional model have limited capacity to sample from a complex probability distribution. We show that the firing rate dynamics of a recurrent neural circuit with a separate set of output units can sample from an arbitrary probability distribution. We call such circuits reservoir-sampler networks (RSNs). We propose an efficient training procedure based on denoising score matching that finds recurrent and output weights such that the RSN implements Langevin sampling. We empirically demonstrate our model's ability to sample from several complex data distributions using the proposed neural dynamics and discuss its applicability to developing the next generation of sampling-based Bayesian brain models. Copyright © 2023, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Antiferromagnetic FeTe2 1T−phase formation at the Sb2Te3/Ni80Fe20 interface

引用

Physical Review Materials 2023年第2期7卷 024406-024406页

作者： A. R. Will-Cole James L. Hart Matthew Matzelle Adrian Podpirka Nirjhar Bhattacharjee Shreya K. Patel Sarah H. Tolbert Arun Bansil Judy J. Cha Don Heiman Nian X. Sun Electrical and Computer Engineering Northeastern University Boston Massachusetts 02115 USA Materials Science and Engineering Cornell University Ithaca New York 14853 USA Department of Physics Northeastern University Boston Massachusetts 02115 USA Applied Physics Laboratory Johns Hopkins Laurel Maryland 20723 USA Department of Chemistry and Biochemistry University of California Los Angeles Los Angeles California 90095 USA Plasma Science and Fusion Center Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA

Bilayer topological insulator/ferromagnet (TI/FM) heterostructures are promising for spintronic applications due to their low switching energy and therefore power efficiency. Until recently, the reactivity of TIs with FM films was overlooked in the spin-orbit-torque literature, even though there are reports that it is energetically favorable for TIs to react with transition metals and form interfacial layers. In this study, we fabricated a TI/FM heterostructure comprised of molecular beam epitaxy grown Sb2Te3 and dc sputtered Ni80Fe20. Broadband ferromagnetic resonance revealed spin-pumping evident by the significant enhancement in Gilbert damping, which is likely a signature of the topological surface states or the presence of large spin-orbit coupling in the adjacent Sb2Te3. With low-temperature magnetometry, an exchange bias is observed that indicates an exchange interaction between an antiferromagnet (AFM) and an adjacent FM. Cross-section high-angle annular dark-field scanning transmission electron microscopy characterization of the Sb2Te3−Ni80Fe20 bilayer revealed a complex interface showing diffusion of Fe and Ni into the Sb2Te3 film yielding the formation of a FeTe2 1T−type structural phase. Furthermore, density functional theory calculations revealed that the FeTe2 1T−phase has an AFM ground state. Due to experimental limitations in the electron-energy-loss spectroscopy measurements, the precise chemistry of the interfacial phase could not be determined, therefore it is possible that the FeTe2 1T and/or an intermixed (Fe1–xNix)Te2 1T is the AFM interfacial phase contributing to exchange bias in the system. This work emphasizes the chemical complexity of TI/FM interfaces that host novel, metastable magnetic topological phases and require more in-depth studies of other similar interfaces.

关键词： Exchange bias Spintronics Topological insulators Antiferromagnets Solid-solid interfaces

来源：评论

学校读者我要写书评

暂无评论

Automated Modal Parameter Estimation for Coupled Rotor-Foundation Systems Using Seal Forces as Excitation Source

SSRN

引用

SSRN 2023年

作者： Paulsen, Thomas Thougaard Damsgaard, Sebastian Vikær Clemmensen, Line Katrine Harder Santos, Ilmar F. Department of Civil and Mechanical Engineering Technical University of Denmark Koppels Allé 404 Kgs. Lyngby2800 Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Richard Petersens Plads 324 Kgs. Lyngby2800 Denmark

Modal analysis techniques are widely used to characterize vibrations in structures, vehicles, machinery, etc. In previous studies, the modal parameters obtained through modal analysis were useful for structural health monitoring and condition monitoring. In these contexts, the common goal is to ensure the integrity of a mechanical system through monitoring of different operational conditions. Operational conditions described by spatial measurements can for instance be used to observe the vibration characteristics of the system (and herein its parts). A consistent and automatic way of obtaining the vibration characteristics is necessary for this feature to be included in the monitoring schemes. Therefore, this work proposes a method to automatically obtain modal parameters for a bed plate of a rotor-foundation system when the rotor is affected by active magnetic bearings and gas seals. The automatic modal parameter algorithm is built on the stabilization diagram obtained from the stochastic subspace identification. Intermediate results from the automatic modal parameter algorithm illustrate that some distance measures for modal parameters in a stabilization diagram are better suited than others when distinguishing between possible physical modal parameters and certainly spurious poles. Also, the assumed frequency band for the system is found to influence the number of identified possible physical modal parameters in the automatic algorithm. Results from 13 roving accelerometer measurements using the automatic modal parameter algorithm are combined to obtain vibration characteristics for the bed plate. For different operational conditions in the seal geometry, seven modal parameter sets are consistently identified as chosen physical modal parameters by the automatic modal parameter algorithm using a combination of a white noise disturbance pattern induced in the active magnetic bearings and the disturbance from the turbulent gas flow in the seals. The seven physical m

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

Assessment of the Impact of Fractal Dimension of the Fracture Surface of Cement Mortar on its Strength

Assessment of the Impact of Fractal Dimension of the Fractur...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Mykola Kotov Volodymyr Volchuk Oleksandr Konoplianyk Yevhen Plakhtii Olena Rabich Irina Meshcheriakova Department of Reinforced Concrete and Masonry Structures Prydniprovska State Academy of Civil Engineering and Architecture Dnipro Ukraine Department of Materials Science and Materials Processing Prydniprovska State Academy of Civil Engineering and Architecture Dnipro Ukraine Department of Computer Sciences Information Technologies and Applied Mathematics Prydniprovska State Academy of Civil Engineering and Architecture Dnipro Ukraine Department of Life Safety Prydniprovska State Academy of Civil Engineering and Architecture Dnipro Ukraine

The study of the relationship between the structure and properties of cement mortars that make up concrete is complicated by the complex geometric structure of structural elements. The fractal approach was used to assess adequately the fracture surface of cement mortar with a plasticizer. The fractal dimension of the identified elements of mortar macrostructure is calculated: dark areas with cement stone predominance, light areas with sand predominance and pores. Linear models of strength prediction based on the influence of dark areas of the structure (the pair correlation coefficient is 0.77), light areas $(R^{2}=0.76)$ and pores $(R^{2}=0.72)$ are obtained, which indicates the sensitivity of physical and mechanical properties to changes in the fractal dimension of structural elements. An increase in the strength indicators of the mortar was recorded from 8 to 27 MPa with an increase in the fractal dimension of cement stone from 1.787 to 1.959 (by 8.9 %). Strength indicators decrease with an increase in the fractal dimension of light sections of the structure from 1.534 to 1.891 (by 19.9 %) and the fractal dimension of pores from 1.632 to 1.807 (by 9.7 %). A multiparametric fractal model of the influence of fractal dimensions of the identified structural components is constructed, which has a relatively high correlation coefficient of 0.89. The proposed approach can be used in industrial conditions as an additional method for operational forecasting of flexural strength indicators of cement mortar based on the fractal dimension of its macrostructure elements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision-making Support System for Predicting and Eliminating Malnutrition and Anemia

引用

Open Bioinformatics Journal 2023年 16卷

作者： Maasthi, Manasvi Jagadeesh Gururaj, Harinahalli Lokesh Ravi, Vinayakumar Basavesha, D. Almeshari, Meshari Alzamil, Yasser Department of Computer Science and Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Computer Science and Engineering Shridevi Institute of Engineering and Technology Karnataka Tumkur India Department of Diagnostic Radiology College of Applied Medical Sciences University of Ha'il Ha'il Saudi Arabia

Aims: This study investigates predicting and eliminating malnutrition and anemia using ML Algorithms and comparing all the methods with various malnutrition-based parameters. Background: The health of the nation is more important than the wealth of the nation. Malnutrition and anemia are serious health issues but the least importance is given to eradicate them. Objective: Proper nutrition is an essential component for the survival, growth, and development of infants, children, and women who in turn give birth to infants. Methods: In the proposed system, machine learning approaches are utilized to predict the malnutrition status of children under five years of age and anemia in men and women using old datasets and further providing a suitable diet recommendation to overcome the disease. Classification techniques are being used for malnutrition as well as anemia prediction. Results: Algorithms such as Naïve Bayes classifier (NBC), Decision Tree (DT) algorithm, Random Forest (RF) algorithm, and K-Nearest Neighbor (k-NN) algorithm are utilized for prediction. The results obtained by these algorithms are 94.47%, 85%, 95.49%, and 63.15%. When compared, Naïve Bayes and random forest algorithm provided efficient results for malnutrition and anemia, respectively. Conclusion: By testing and validating, preventive actions can be taken with the help of medical experts and dieticians to reduce malnutrition and anemia conditions among children and elders, respectively. © 2023 The Author(s).

关键词： Algorithm Dataset Deficiency Healthcare Naïve baye classifier Nutrition

来源：评论

学校读者我要写书评

暂无评论

Federated Multimedia Recommendation Systems with Privacy Protection

Federated Multimedia Recommendation Systems with Privacy Pro...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Shih Yu Chang Hsiao-Chun Wu Kun Yan Scott Chih-Hao Huang Yiyan Wu Department of Applied Data Science San Jose State University San Jose CA USA School of Electrical Engineering and Computer Science Louisiana State University Baton Rouge LA USA Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin Guangxi China Department of Information and Telecommunication Guilin University of Electronic Technology Guilin Guangxi China Department of Electrical Engineering National Tsinghua University Hsinchu Taiwan

ISBN: (数字)9798350364262

ISBN: (纸本)9798350364279

In this big data era, distributed machine learning and global data pooling have become quite critical in practical implementation of any multimedia data-science technique. The emerging federated multimedia recommendation systems (FeMRSs) offer a promising approach to address the need of personalized recommendations subject to both users’ privacy and data security. However, there exists no quantitative method for assessing the discrepancy between the large original rating matrix stored on the server and the dimensionality-reduced rating matrix produced on each client’s equipment. Meanwhile, there lacks a systematic means to evaluate the differential privacy (DP), which is a critical security measure in many distributed systems, particularly when sensitive data are processed. In this work, we first introduce a novel personalized dimensionalityreduction algorithm utilizing the matrix sketching technique. This new algorithm effectively control the difference between the original rating matrix on the server and the dimensionality-reduced rating matrix on each client’s equipment. Moreover, a randomized DP matrix factorization algorithm is designed to be executed at each client’s equipment. The theoretical proof is also carried out to show how much DP can be attained by use of the aforementioned randomized DP matrix factorization algorithm. Finally, extensive numerical studies are presented to evaluate the effectiveness of our proposed novel algorithms using both simulated and real datasets for building the FeMRSs.

关键词： Dimensionality reduction Digital multimedia broadcasting Privacy Systematics Distributed databases Filtering algorithms Servers

来源：评论

学校读者我要写书评

暂无评论

Data-centric framework for crystal structure identification in atomistic simulations using machine learning

引用

Physical Review Materials 2022年第4期6卷 043801-043801页

作者： Heejung W. Chung Rodrigo Freitas Gowoon Cheon Evan J. Reed Department of Computer Science Stanford University Stanford California 94305 USA Department of Materials Science and Engineering Stanford University Stanford California 94305 USA Cavendish Laboratory Department of Physics University of Cambridge J. J. Thomson Avenue Cambridge CB3 0HE United Kingdom Department of Materials Science and Engineering Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Applied Physics Stanford University Stanford California 94305 USA

Atomic-level modeling performed at large scales enables the investigation of mesoscale materials properties with atom-by-atom resolution. The spatial complexity of such cross-scale simulations renders them unsuitable for simple human visual inspection. Instead, specialized structure characterization techniques are required to aid interpretation. These have historically been challenging to construct, requiring significant intuition and effort. Here we propose an alternative framework for a fundamental structural characterization task: classifying atoms according to the crystal structure to which they belong. Our approach is data-centric and favors the employment of Machine Learning over heuristic rules of classification. A group of data-science tools and simple local descriptors of atomic structure are employed together with an efficient synthetic training set. We also introduce the first standard and publicly available benchmark data set for evaluation of algorithms for crystal-structure classification. It is demonstrated that our data-centric framework outperforms all of the most popular heuristic methods—especially at high temperatures when lattices are the most distorted—while introducing a systematic route for generalization to new crystal structures. Moreover, through the use of outlier detection algorithms our approach is capable of discerning between amorphous atomic motifs (i.e., noncrystalline phases) and unknown crystal structures, making it uniquely suited for exploratory materials synthesis simulations.

关键词： Classical statistical mechanics Crystal structures Machine learning Molecular dynamics

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：