检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ding, Lisang Jin, Kexin Ying, Bicheng Yuan, Kun Yin, Wotao Department of Mathematics University of California Los AngelesCA United States Department of Mathematics Princeton University PrincetonNJ United States Google Inc. Los AngelesCA United States Center for Machine Learning Research Peking University Beijing China AI for Science Institute Beijing China National Engineering Labratory for Big Data Analytics and Applications Beijing China Decision Intelligence Lab. Alibaba US BellevueWA United States

Decentralized Stochastic Gradient Descent (SGD) is an emerging neural network training approach that enables multiple agents to train a model collaboratively and simultaneously. Rather than using a central parameter server to collect gradients from all the agents, each agent keeps a copy of the model parameters and communicates with a small number of other agents to exchange model updates. Their communication, governed by the communication topology and gossip weight matrices, facilitates the exchange of model updates. The state-of-the-art approach uses the dynamic one-peer exponential-2 topology, achieving faster training times and improved scalability than the ring, grid, torus, and hypercube topologies. However, this approach requires a power-of-2 number of agents, which is impractical at scale. In this paper, we remove this restriction and propose Decentralized SGD with Communication-optimal Exact Consensus Algorithm (DSGD-CECA), which works for any number of agents while still achieving state-of-the-art properties. In particular, DSGD-CECA incurs a unit per-iteration communication overhead and an Õ(n3) transient iteration complexity. Our proof is based on newly discovered properties of gossip weight matrices and a novel approach to combine them with DSGD’s convergence analysis. Numerical experiments show the efficiency of DSGD-CECA. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Big data = Big Insights? Operationalising Brooks’ Law in a Massive GitHub data Set

arXiv

引用

arXiv 2022年

作者： Gote, Christoph Schweitzer, Frank Mavrodiev, Pavlin Scholtes, Ingo Department of Systems Design ETH Zurich Weinbergstrasse 56/58 Zurich8092 Switzerland Department of Computer Science XV - Machine Learning for Complex Networks Julius-Maximilians-Universität Würzburg Friedrich-Bergius-Ring 30 Würzburg97076 Germany Data Analytics Group University of Zurich Binzmühlestrasse 14 Zurich8050 Switzerland

Massive data from software repositories and collaboration tools are widely used to study social aspects in software development. One question that several recent works have addressed is how a software project’s size and structure influence team productivity, a question famously considered in Brooks’ law. Recent studies using massive repository data suggest that developers in larger teams tend to be less productive than smaller teams. Despite using similar methods and data, other studies argue for a positive linear or even super-linear relationship between team size and productivity, thus contesting the view of software economics that software projects are diseconomies of scale. In our work, we study challenges that can explain the disagreement between recent studies of developer productivity in massive repository data. We further provide, to the best of our knowledge, the largest, curated corpus of GitHub projects tailored to investigate the influence of team size and collaboration patterns on individual and collective productivity. Our work contributes to the ongoing discussion on the choice of productivity metrics in the operationalisation of hypotheses about determinants of successful software projects. It further highlights general pitfalls in big data analysis and shows that the use of bigger data sets does not automatically lead to more reliable insights. Copyright © 2022, The Authors. All rights reserved.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

An AI system for continuous knee osteoarthritis severity grading: An anomaly detection inspired approach with few labels

引用

Artificial Intelligence in Medicine 2025年 167卷 103138页

作者： Niamh Belton Aonghus Lawlor Kathleen M. Curran Science Foundation Ireland Centre for Research Training in Machine Learning Ireland School of Medicine University College Dublin Ireland School of Computer Science University College Dublin Ireland Insight Centre for Data Analytics University College Dublin Dublin Ireland

The diagnostic accuracy and subjectivity of existing Knee Osteoarthritis (OA) ordinal grading systems has been a subject of on-going debate and concern. Existing automated solutions are trained to emulate these imperfect systems, whilst also being reliant on large annotated databases for fully-supervised training. This work proposes a three stage approach for automated continuous grading of knee OA that is built upon the principles of Anomaly Detection (AD); learning a robust representation of healthy knee X-rays and grading disease severity based on its distance to the centre of normality. In the first stage, SS-FewSOME is proposed, a self-supervised AD technique that learns the ‘normal’ representation, requiring only examples of healthy subjects and < 3 % of the labels that existing methods require. In the second stage, this model is used to pseudo label a subset of unlabelled data as ‘normal’ or ‘anomalous’, followed by denoising of pseudo labels with CLIP. The final stage involves retraining on labelled and pseudo labelled data using the proposed Dual Centre Representation learning (DCRL) which learns the centres of two representation spaces; normal and anomalous. Disease severity is then graded based on the distance to the learned centres. The proposed methodology outperforms existing techniques by margins of up to 24% in terms of OA detection and the disease severity scores correlate with the Kellgren-Lawrence grading system at the same level as human expert performance. Code available at https://***/niamhbelton/SS-FewSOME_Disease_Severity_Knee_Osteoarthritis .

关键词： Few shot anomaly detection Knee osteoarthritis Self-supervision Self-supervised learning X-ray Contrastive learning Few labels CLIP Deep learning machine learning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Smart Electronic Wheelchair Design Using Artificial Intelligence and Intelligent Sensors Association

A Smart Electronic Wheelchair Design Using Artificial Intell...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： R Balamurugan D. Kanchana B. Anni Princy J Jaisudha P. Malathi E Glory Department of Artificial Intelligence and Machine Learning AJK College of Arts and Science Coimbatore Tamil Nadu India Department of Computer Applications SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Computer and Communication Engineering Panimalar Engineering College Chennai Tamil Nadu India Department of ECE Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Chennai Tamil Nadu India Department of Biosciences Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

Since the beginning of the seventeenth century, wheelchairs have been used to transport hospital patients and those with mobility impairments. The power of people is what spreads wheelchairs. Wheelchair users propel themselves forward using their upper bodies or, more commonly, require the assistance of another person to propel them. In this work, we examine how to build an autonomous electric wheelchair for the disabled at the lowest possible cost without sacrificing quality of design or control. This research presents the planning and development of an AI-enhanced electric wheelchair that can be controlled automatically to climb stairs, making it accessible to those with mobility impairments. The chair’s controls allow the user to move it in any direction and raise the landing and staircases to varying heights. The chair’s DC power source (battery used) may be recharged, allowing it to function for an extended period of time. In addition, a safety system was created that monitors and provides feedback on the user’s pulse rate, as well as the wheelchair’s functioning state (including acceleration, climate, and inclination position). This proposed AI based Wheelchair (AIWC) design is suitable for any aged people and the proposed model is cross-validated with the conventional wheelchair design using mobile based operations handling system called Mobile-Wheelchair (MWC) to test the efficiency of the proposed design in clear manner.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tracking one-in-a-million: Large-scale benchmark for microbial single-cell tracking with experiment-aware robustness metrics

arXiv

引用

arXiv 2024年

作者： Seiffarth, Johannes Blöbaum, Luisa Paul, Richard D. Friederich, Nils Yamachui Sitcheu, Angelo Jovin Mikut, Ralf Scharr, Hanno Grünberger, Alexander Nöh, Katharina Institute of Bio- and Geosciences IBG-1: Biotechnology Forschungszentrum Jülich GmbH Jülich Germany RWTH Aachen University Aachen Germany Multiscale Bioengineering Bielefeld University Bielefeld Germany Institute for Advanced Simulation IAS-8: Data Analytics and Machine Learning Forschungszentrum Jülich GmbH Jülich Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany Institute of Biological and Chemical Systems Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany Microsystems in Bioprocess Engineering Karlsruhe Institute of Technology Karlsruhe Germany

Tracking the development of living cells in live-cell time-lapses reveals crucial insights into single-cell behavior and presents tremendous potential for biomedical and biotechnological applications. In microbial live-cell imaging (MLCI), a few to thousands of cells have to be detected and tracked within dozens of growing cell colonies. The challenge of tracking cells is heavily influenced by the experiment parameters, namely the imaging interval and maximal cell number. For now, tracking benchmarks are not widely available in MLCI and the effect of these parameters on the tracking performance are not yet known. Therefore, we present the largest publicly available and annotated dataset for MLCI, containing more than 1.4 million cell instances, 29k cell tracks, and 14k cell divisions. With this dataset at hand, we generalize existing tracking metrics to incorporate relevant imaging and experiment parameters into experiment-aware metrics. These metrics reveal that current cell tracking methods crucially depend on the choice of the experiment parameters, where their performance deteriorates at high imaging intervals and large cell colonies. Thus, our new benchmark quantifies the influence of experiment parameters on the tracking quality, and gives the opportunity to develop new data-driven methods that generalize across imaging and experiment parameters. The benchmark dataset is publicly available at https://***/doi/10.5281/zenodo.7260136. © 2024, CC BY.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

A case-control study of reaction time deficits in a 3D virtual reality in patients with Post-COVID syndrome

引用

Scientific Reports 2024年第1期14卷 1-12页

作者： Güttes, Moritz Lucio, Marianna Skornia, Adam Rühl, Eva Steußloff, Fritz Zott, Julia Mardin, Christian Mehringer, Wolfgang Ganslmayer, Marion Michelson, Georg Hohberger, Bettina Department of Ophthalmology Universitätsklinikum Erlangen Friedrich-Alexander-Universität Erlangen- Nürnberg Erlangen Germany Research Unit Analytical BioGeoChemistry Helmholtz Zentrum München Neuherberg Germany Department Artificial Intelligence in Biomedical Engineering (AIBE) Machine Learning and Data Analytics Lab (MaD Lab) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany Department of Internal Medicine 1 Universitätsklinikum Erlangen Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

Following the Coronavirus disease 2019 (COVID-19) pandemic, a large number of people continue to report Post-COVID symptoms (PCS). A wide variety of symptoms are described, including fatigue, post-exertional malaise and cognitive impairment. However, adequate objective diagnostic tests for PCS are not yet available. Since the neurotropism of SARS-CoV-2 could be a possible factor for cognitive impairment, the aim of this study was to clarify whether visual reaction time (RT) in a stereoscopic setting can be a marker in PCS diagnostics. The Virtual-Reality-Oculomotor-Test-System (VR-OTS) was used testing binocular vision in 9 gaze directions via stereoscopic stimuli displayed in a virtual reality (VR)-environment (disparity: 275″, 550″, 1100″) in 179 individuals: 130 patients with PCS and 49 healthy controls. The results from the generalized linear models indicated that both group membership (PCS vs. control) and covariates (age and sex) yielded statistically significant different RT across the models. Accounting for the effect of covariates a statistically significant difference of RT was observed between patients with PCS and controls (disparity 275″ p-value = 0.001;550″ p-value = 0.001;1100″ p-value = 0.003). Patients with PCS performed worse in RT in all gaze directions, respectively. Adjusting for the influence of covariates, correct responses (CR) differed significantly between patients with PCS and controls (disparity 275″ p-value < 0.001;550″ p-value = 0.003;1100″ p-value = 0.019). Statistically significant effects of covariates on RT were observed for sex (disparity 275″ p-value = 0.047;550″ p-value = 0.012;1100″ p-value = 0.005) and age (disparity 275″ p-value < 0.001;550″ p-value < 0.001;1100″ p-value < 0.001). However, regarding covariates, no significant effects were found for CR, except for age at disparity 275″ (p-value = 0.035). The present data suggested that the mentioned variables uniquely contributed to explain the variation of the response variabl

关键词：

来源：评论

学校读者我要写书评

暂无评论

Latent space conditioning on generative adversarial networks

arXiv

引用

arXiv 2020年

作者： Lopez, Ricard Durall Ho, Kalun Pfreundt, Franz-Josef Keuper, Janis Fraunhofer ITWM Germany IWR University of Heidelberg Germany Fraunhofer Center Machine Learning Germany Data and Web Science Group University of Mannheim Germany Institute for Machine Learning and Analytics Offenburg University Germany

Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data. These supervised methods allow a much finer-grained control of the output image, offering more flexibility and stability. Nevertheless, the main drawback of such models is the necessity of annotated data. In this work, we introduce an novel framework that benefits from two popular learning techniques, adversarial training and representation learning, and takes a step towards unsupervised conditional GANs. In particular, our approach exploits the structure of a latent space (learned by the representation learning) and employs it to condition the generative model. In this way, we break the traditional dependency between condition and label, substituting the latter by unsupervised features coming from the latent space. Finally, we show that this new technique is able to produce samples on demand keeping the quality of its supervised counterpart. © 2020, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Electrophysiological Insights in Exergaming—Electroencephalography data Recording and Movement Artifact Detection: Systematic Review

引用

JMIR Serious Games 2025年 13卷 e50992页

作者： Rico-Olarte, Carolina Lopez, Diego M. Eskofier, Bjoern M. Becker, Linda Telematics Department Universidad del Cauca Popayán Colombia Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department of Psychology Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

Background: Exergames are interactive solutions that require physical activity and are commonly used in learning or rehabilitation settings. For cognitive rehabilitation with exergames, the assessment of the intervention progress can be conducted by verifying the changes in brain activity. Electroencephalography (EEG) is a well-known method for this evaluation. However, motion artifacts due to large body movements can impede signal quality. No comprehensive guide on the artifact removal methods in the context of exergaming has been found. Objective: This paper aimed to identify studies that have assessed EEG signals while a user interacts with an exergame and the applied methods for data handling and analysis with a focus on dealing with movement artifacts. Methods: This review included studies on human participants while engaging in exergames, where the primary outcome was brain activity measured by EEG. A total of 5 databases were searched at 3 time points: March 2021, October 2022, and February 2024. The Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies assessed methodological quality, rating studies as “good,” “fair,” or “poor.” data were synthesized quantitatively to identify characteristics across studies, including sample demographics and intervention details, and basic statistics (mean [SD]) were calculated. Results: A total of 494 papers were screened, resulting in 17 studies having been included. All studies carried out EEG recordings during exergame interactions, primarily assessing attention and concentration, with the alpha wave being the most analyzed EEG band. Common motion artifact removal methods included visual inspection and independent component analysis. The review identified significant risks of bias, with 2 studies rated as “good,” 7 as “fair,” and 8 as “poor.” Due to the small number of studies and their heterogeneity, a meta-analysis was not feasible. Conclusions: The study successfully identifies the feasibility o

关键词： artifact removal brain activity EEG exergaming motion artifact

来源：评论

学校读者我要写书评

暂无评论

Accuracy-Aware Compression of Channel Impulse Responses using Deep learning

Accuracy-Aware Compression of Channel Impulse Responses usin...

引用

International Conference on Indoor Positioning and Indoor Navigation (IPIN)

作者： Thomas Altstidl Sebastian Kram Oskar Herrmann Maximilian Stahlke Tobias Feigl Christopher Mutschler Fraunhofer Institute for Integrated Circuits IIS Nürnberg Germany Machine Learning and Data Analytics Lab Friedrich-Alexander-University Erlangen-Nürnberg (FAU) Germany Institute of Information Technology Friedrich-Alexander-University Erlangen-Nürnberg (FAU) Germany

Ultra-wideband (UWB) systems based on Channel State Information (CSI) estimate the position of mobile nodes within an environment by using Channel Impulse Responses (CIRs) of multiple stationary nodes. These contain spatial information caused by environment interactions such as reflections and scattering. To estimate positions from CSI of stationary nodes, we must transmit them to a centralized node. This introduces considerable communication *** present a large-scale study to determine whether CSI can be compressed into a small set of underlying latent variables that describe the most valuable information. We evaluate multiple neural network architectures containing encoding (compressing) and decoding (reconstructing) components and compare them to the state-of-the-art compression techniques Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT). We show that fully connected autoencoders achieve the lowest error, outperforming both DCT and DWT. Further experiments prove that the reconstructed CSI can be used for positioning with only mild performance deterioration at a compression of >97% and even when trained on a different environment.

关键词： Training Neural networks Scattering Transforms Reflection Discrete wavelet transforms Decoding

来源：评论

学校读者我要写书评

暂无评论

Automatic clinical gait test detection from inertial sensor data

Automatic clinical gait test detection from inertial sensor ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Stefan Fischer Martin Ullrich Arne Küderle Heiko Gaßner Jochen Klucken Bjoern M. Eskofier Felix Kluge Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Germany University Hospital Erlangen Germany

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

The analysis of gait data is one approach to support clinicians with the diagnosis and therapy of diseases, for example Parkinson's disease (PD). Traditionally, gait data of standardized tests in the clinic is analyzed, ensuring a predefined setting. In recent years, long-term home-based gait analysis has been used to acquire a more representative picture of the patient's disease status. data is recorded in a less artificial setting and therefore allows a more realistic perception of the disease progression. However, fully unsupervised gait data without additional context information impedes interpretation. As an intermediate solution, performance of gait tests at home was introduced. Integration of instrumented gait test requires annotations of those tests for their identification and further processing. To overcome these limitations, we developed an algorithm for automatic detection of standardized gait tests from continuous sensor data with the goal of making manual annotations obsolete. The method is based on dynamic time warping, which compares an input signal with a predefined template and quantifies similarity between both. Different templates were compared and an optimized template was created. The classification scored a F1-measure of 86.7% for evaluation on a data set acquired in a clinical setting. We believe that this approach can be transferred to home-monitoring systems and will facilitate a more efficient and automated gait analysis.

关键词： Turning Diseases Instruments Legged locomotion Gyroscopes Hospitals Reliability

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：