检索结果-内蒙古大学图书馆

On Assignments Verification during the ICS databases Lifecycle 14

学校读者我要写书评

暂无评论

On Assignments Verification during the ICS Databases Lifecyc...

14th International Conference Management of Large-Scale System Development, MLSD 2021

作者： Budynkova, Elizaveta Baybulatov, Artur Joint Stock Company «aLFA-BANK» Business Process Automation Directorate Moscow Russia Ivery Prangishvili Laboratory 31 'Distributed Data-Analysis and Control Systems' V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

ISBN: (纸本)9781665412308

Today, Industrial Control System (ICS) databases are incredibly complicated with quite prolonged iterative lifecycle where every new iteration is driven by a new version of the database assignment. For the correct databases development, the assignments should be consistent and correspond to special requirements, but this is not always the case. Therefore, the checking, or verification, of the assignments is becoming especially important. However, the appropriate problem of databases assignments verification is not widely discussed, and available verification methods are not suitable enough for solving the problem. The article clarifies the place of the assignments verification in the ICS databases lifecycle and presents a novel algorithm for the assignments verification. The particular implementation of the algorithm is also considered. As an example, the results of the verification of the assignments for the NPP ICS databases are presented. © 2021 IEEE.

关键词： database systems

Deep Interpretable Ensembles

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kook, Lucas Götschi, Andrea Baumann, Philipp F. M. Hothorn, Torsten Sick, Beate Epidemiology Biostatistics & Prevention Institute University of Zurich CH-8001 Switzerland Institute for Data Analysis and Process Design Zurich University of Applied Sciences CH-8400 Switzerland KOF Swiss Economic Institute ETH Zurich CH-8092 Switzerland

Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently, partially interpretable semi-structured deep transformation models. However, interpretability of the ensemble members is generally lost upon aggregation. This is a crucial drawback of deep ensembles in high-stake decision fields, in which interpretable models are desired. We propose a novel transformation ensemble which aggregates probabilistic predictions with the guarantee to preserve interpretability and yield uniformly better predictions than the ensemble members on average. Transformation ensembles are tailored towards interpretable deep transformation models but are applicable to a wider range of probabilistic neural networks. In experiments on several publicly available data sets, we demonstrate that transformation ensembles perform on par with classical deep ensembles in terms of prediction performance, discrimination, and calibration. In addition, we demonstrate how transformation ensembles quantify both aleatoric and epistemic uncertainty, and produce minimax optimal predictions under certain conditions. © 2022, CC BY.

关键词： Uncertainty analysis

Deep transformation models for functional outcome prediction after acute ischemic stroke

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Herzog, Lisa Kook, Lucas Götschi, Andrea Petermann, Katrin Hänsel, Martin Hamann, Janne Dürr, Oliver Wegener, Susanne Sick, Beate Epidemiology Biostatistics & Prevention Institute University of Zurich Switzerland Institute for Data Analysis and Process Design Zurich University of Applied Sciences Switzerland Department of Neurology University Hospital Zurich Switzerland Insitute for Optical Systems Konstanz University of Applied Sciences Germany

In many medical applications, interpretable models with high prediction performance are sought. Often, those models are required to handle semi-structured data like tabular and image data. We show how to apply deep transformation models (DTMs) for distributional regression which fulfill these requirements. DTMs allow the data analyst to specify (deep) neural networks for different input modalities making them applicable to various research questions. Like statistical models, DTMs can provide interpretable effect estimates while achieving the state-of-the-art prediction performance of deep neural networks. In addition, the construction of ensembles of DTMs that retain model structure and interpretability allows quantifying epistemic and aleatoric uncertainty. In this study, we compare several DTMs, including baseline-adjusted models, trained on a semi-structured data set of 407 stroke patients with the aim to predict ordinal functional outcome three months after stroke. We follow statistical principles of model-building to achieve an adequate trade-off between interpretability and flexibility while assessing the relative importance of the involved data modalities. We evaluate the models for an ordinal and dichotomized version of the outcome as used in clinical practice. We show that both, tabular clinical and brain imaging data, are useful for functional outcome prediction, while models based on tabular data only outperform those based on imaging data only. There is no substantial evidence for improved prediction when combining both data modalities. Overall, we highlight that DTMs provide a powerful, interpretable approach to analyzing semi-structured data and that they have the potential to support clinical decision making. © 2022, CC BY.

关键词： Deep neural networks

UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Pengfei Li, Chang Zhang, Yongjun Qin, Rongjun Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province College of Urban and Environmental Science Central China Normal University Wuhan China School of Remote Sensing and Information Engineering Wuhan University China Department of Civil Environmental and Geodetic Engineering Department of Electrical and Computer Engineering Translational Data Analytics Institute The Ohio State University ColumbusOH United States

Remotely sensed imagery interpretation (RSII), including semantic segmentation and change detection, faces the three major problems: (1) objective representation of spatial distribution patterns with coexistence of spatial stationary and non-stationary;(2) edge uncertainty problem caused by downsampling encoder and intrinsic edge noises (e.g., mixed pixel and edge occlusion etc.);and (3) false detection problem caused by geometric registration error in change detection. To solve the aforementioned problems, uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed, whose superiorities are as follows: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially frequency-wise stationary and non-stationary features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP proposes high-frequency-wise stream to replace high-resolution-wise stream in HRFormer through the whole encoder-decoder process with parallel frequency-wise high-to-low streams, so it improves the edge extraction accuracy by continuously remaining high-frequency information;(2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM), which is a self-supervised learning strategy, is proposed to improve the edge accuracy of extraction and change detection by gradually removing the simulated spectrum noises based on geo-knowledge and the generated diffused spectrum noises;(3) a frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection. Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error. In semantic segmentation experiments, UDHF2-Net achieved the best mIoU values of 92.00%, 87.31% and 55.27% respecti

关键词： Semantic Segmentation

Road network disruptions during extreme flooding events and their impact on the access to emergency medical services: A spatiotemporal vulnerability analysis

学校读者我要写书评

暂无评论

Science of the Total Environment 2024年 956卷 177140页

作者： Papilloud, Tsolmongerel Steiner, Albert Zischg, Andreas Keiler, Margreth University of Bern Institute of Geography Hallerstrasse 12 BernCH-3012 Switzerland University of Bern Oeschger Centre for Climate Change Research Mobiliar Lab for Natural Risks Hochschulstrasse 4 BernCH-3012 Switzerland Zurich University of Applied Sciences ZHAW Institute of Data Analysis and Process Design Technikumstrasse 81 WinterthurCH-8401 Switzerland University of Innsbruck Department of Geography Innrain 52f Innsbruck6020 Austria Austrian Academy of Sciences Institute of Interdisciplinary Mountain Research Innrain 25 Innsbruck6020 Austria

The impact of extreme floods can be significant, affecting humans, the environment and any type of human-built infrastructure. A further consequence of flooding is restricted access to medical facilities, including constraints to access more dedicated emergency medical services (EMS). To date, there has been a lack of investigation into EMS accessibility dynamics during extreme floods. The objective of this study is to gain a deeper understanding of the spatiotemporal changes in accessibility-based vulnerability related to EMS during a representative extreme flood event, which was simulated over a period of six days. The study assesses the spatial accessibility of EMS centres to populations located within 15-, 30-, 45-, and 60-minute travel time thresholds in Canton Bern, Switzerland, and applies floating catchment area method. The dynamic aspects of EMS access vulnerability during extreme floods were assessed in two different ways. Firstly, the ratios between accessibility change and accessibility under normal conditions in 1 km grid cells were calculated at hourly moments, t. Subsequently, the resulting values were used to calculate the average vulnerability score. Secondly, percentage changes of affected populations were evaluated for different accessibility classes during the flood event and under all-time high static flood conditions. Varied spatial patterns of accessibility were generally observed with respect to the road network and population distributions in the hilly and mountainous landscape. Extending evaluations to consider temporal dynamics revealed a complex pattern of accessibility gains and losses in different regions of the study area, including those where no direct flood impacts occurred on the road network. The application of a static, all-time high flood condition resulted in an overestimation of accessibility limits to EMS centres. While this overestimation was not considered to be critical, the application of a spatiotemporal accessibility-ba

关键词： Travel time

Gradual (In)Compatibility of Fairness Criteria

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hertweck, Corinna Räz, Tim Institute for Data Analysis and Process Design Zurich University of Applied Sciences Winterthur Switzerland Department of Informatics University of Zurich Zurich Switzerland Institute of Philosophy University of Bern Bern Switzerland

Impossibility results show that important fairness measures (independence, separation, sufficiency) cannot be satisfied at the same time under reasonable assumptions. This paper explores whether we can satisfy and/or improve these fairness measures simultaneously to a certain degree. We introduce information-theoretic formulations of the fairness measures and define degrees of fairness based on these formulations. The information-theoretic formulations suggest unexplored theoretical relations between the three fairness measures. In the experimental part, we use the information-theoretic expressions as regularizers to obtain fairness-regularized predictors for three standard datasets. Our experiments show that a) fairness regularization directly increases fairness measures, in line with existing work, and b) some fairness regularizations indirectly increase other fairness measures, as suggested by our theoretical findings. This establishes that it is possible to increase the degree to which some fairness measures are satisfied at the same time-some fairness measures are gradually compatible. Copyright © 2021, The Authors. All rights reserved.

关键词： Information theory

A novel augmented reality-based simulator for enhancing orthopedic surgical training

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2025年 185卷 109536-109536页

作者： Wu, Luohong Seibold, Matthias Cavalcanti, Nicola A. Hein, Jonas Gerth, Tatiana Lekar, Roni Hoch, Armando Vlachopoulos, Lazaros Grabner, Helmut Zingg, Patrick Farshad, Mazda Fürnstahl, Philipp Research in Orthopedic Computer Science Balgrist University Hospital University of Zurich Lengghalde 5 Zurich8008 Switzerland Department of Orthopaedics Balgrist University Hospital University of Zurich Forchstrasse 340 Zurich8008 Switzerland Computer Vision and Geometry Group ETH Zurich Ramistrasse 101 Zurich8092 Switzerland Institute of Computer Science School of Engineering Zurich University of Applied Sciences Obere Kirchgasse 2 Winterthur8401 Switzerland Institute of Data Analysis and Process Design School of Engineering Zurich University of Applied Sciences Technikumstrasse 81 Winterthur8400 Switzerland

Background: Total Hip Arthroplasty (THA) is a well-established and common orthopedic surgery. Due to the complexity involved in THA, orthopedic surgeons require rigorous training. However, the current gold standard, the tutor-guided and -evaluated apprenticeship model is time-consuming, costly, and poses risks to patients. There is a pressing need for additional training resources to enhance the efficiency and safety of the training process. In this work, we present a novel Augmented Reality (AR)-based simulator designed for THA that helps enable a new self-paced training and learning paradigm without the need for instructors. Methods: The simulator reduces the need for instructors by integrating an AR guidance module and an automated performance evaluation module. Three types of AR guidance were developed: Overlay, Virtual Twin, and Sectional Views. A feasibility study was conducted with five resident surgeons and two senior surgeons to compare these guidance methods quantitatively and qualitatively. The automated performance evaluation module was assessed against manual performance evaluation using Bland-Altman analysis with limits of agreement (LoA) and Mann–Whitney U tests. Results: The quantitative feasibility results indicate the efficacy of the developed AR guidance, characterized by mean transitional and rotational deviation errors below 3 mm and 3 degrees. Based on the qualitative results, we provide recommendations for efficient AR guidance designs. The Bland-Altman analysis results (0.22±1.32mm with LoA −2.37 to 2.81 mm for distance deviation, 0.94±2.41 degrees with LoA −3.78 to 5.66 degrees for yaw deviation, −0.34±1.30 degrees with LoA −2.90 to 2.22 degrees for pitch deviation) and p-values of Mann–Whitney U tests (0.64 for distance deviation, 0.12 for yaw deviation, 0.11 for pitch deviation) indicate no statistically significant differences between the automated and manual performance evaluation at a significance level of 0.05. Conclusion: This work sh

关键词： Augmented reality

A cyber-attack detection based on time-delay mutual information analysis

学校读者我要写书评

暂无评论

process Safety and Environmental Protection 2025年 200卷

作者： Fangyuan Ma Cheng Ji Jingzhi Rao Chengyu Han Jingde Wang Wei Sun College of Chemical Engineering Beijing University of Chemical Technology Beijing 100029 China Center of Process Monitoring and Data Analysis Wuxi Research Institute of Applied Technologies Tsinghua University Wuxi 214072 China

In recent years, data-driven fault detection and diagnosis (FDD) have been widely studied and applied in academia and industry to ensure the safe operation of processes. However, traditional FDD is mainly developed to process spontaneous faults and ignores the detection of cyber-attack. With the widespread application of industrial control systems, a large number of control actuators and measurement sensors are connected using wireless or wired communications, which greatly increases the risk of sensor tampering. Meanwhile, faults caused by sensor tampering have similar effects as process faults, making the distinction much more difficult. If the fault is incorrectly recognized as a process fault, it will mislead human engineers, even cause catastrophic consequence. Therefore, it is important to identify cyber-attacks promptly and accurately. By comparing the two types of faults, the main difference lies in the root cause of the fault. In a cyber-attack, state variables such as temperature, pressure, level, etc. are the preferred targets to be tampered with, and feedback from industrial control systems is not able to control them to a preset value. Therefore, the root cause of these faults is reflected in state variables. In contrast, changes in the manipulated variables, such as feed flow, are frequently the root cause of process faults. Inspired by it, the two types of faults should be distinguished by the root cause. Time-delay mutual information analysis (TDMI) is a fault diagnosis method that has been successfully applied to actual industrial processes. By analyzing the changes in time-delay mutual information between variables, the fault propagation path and the root cause can be objectively identified. In this work, a cyber-attack detection based on TDMI is developed. When a fault occurs, TDMI is employed to analyze the root cause. If the root cause is a state variable, the fault should be caused by a cyber-attack in a big chance, instead of a process fault.

关键词：

Prediction of Activated Sludge Settling Characteristics from Microscopy Images with Deep Convolutional Neural Networks and Transfer Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Borzooei, Sina Scabini, Leonardo F.S. Miranda, Gisele Daneshgar, Saba Deblieck, Lukas De Langhe, Piet Bruno, Odemir De Baets, Bernard Nopens, Ingmar Torfs, Elena IVL Swedish Environmental Research Institute PO Box 210 60 StockholmSE-100 31 Sweden Department of Data Analysis and Mathematical Modelling Faculty of Bioscience Engineering Ghent University Coupure links 653 Gent9000 Belgium São Carlos Institute of Physics University of São Paulo SP São Carlos13560-970 Brazil KERMIT Department of Data Analysis and Mathematical Modelling Ghent University Coupure links 653 Gent9000 Belgium Division of Computational Science and Technology KTH Royal Institute of Technology Stockholm10044 Sweden CAPTURE Centre for Advanced Process Technology for Urban Resource Recovery Frieda Saeysstraat 1 Gent9000 Belgium Pantarein Water Egide Walschaertsstraat 22L Mechelen2800 Belgium Université Laval 1065 avenue de la Médecine QuébecQCG1V 0A6 Canada

Timely assessment and prediction of changes in microbial compositions leading to activated sludge settling problems, such as filamentous bulking (FB), can reduce water resource recovery facilities (WRRFs) upsets, operational challenges, and negative environmental impacts. This study presents a computer vision approach to assess activated sludge-settling characteristics based on Microscopy Images (MIs). We utilize MIs to train deep convolutional neural networks (CNN) using transfer learning to investigate the morphological properties of flocs and filaments. The methodology was tested on the offline MI dataset collected over two years at a full-scale industrial WRRF in Belgium. Various CNN architectures were tested, including Inception v3, ResNet18, ResNet152, ConvNeXt-nano, and ConvNeXt-S. The sludge volume index (SVI) was used as the final prediction variable, but the method can be easily adjusted to predict any other settling metric of choice. The best-performing CNN, ConvNeXt-nano, could predict SVI values with MAE (37.51 ± 4.02), MTD (11.65 ± 1.94), MAPE (0.18 ± 0.02), and R2 (0.75 ± 0.05). The model was tested in real-life FB events, where it identified early indicators of bulking by predictive surges in SVI values. We also use an explainable AI technique, Eigen-CAM, to discover key morphological indicators of sludge bulking transitions. The findings highlight the SVI multimodality issue, where SVI readings as a unidimensional metric could not capture delicate shifts from good to poor sludge settling, while the model detected these subtle changes. The key morphological attributes of threshold conditions leading to FB were identified, which can provide actionable insight for preemptive WRRF management. © 2024, The Authors. All rights reserved.

关键词： Forecasting