68,529 Hits in 5.4 sec

Sampling Strategies for Data-Driven Inference of Input-Output System Properties [article]

Anne Romer, Jan Maximilian Montenbruck, Frank Allgöwer
2019 arXiv   pre-print
Due to their relevance in controller design, we consider the problem of determining the L^2-gain, passivity properties and conic relations of an input-output system.  ...  These sampling strategies are based on gradient dynamical systems and saddle point flows to solve the reformulated optimization problems, where the gradients can be evaluated from only input-output data  ...  In this paper, we present these approaches as a more general idea of the following form: Sampling strategy for inference of system properties: 1) Formulate system property as optimization problem 2) Iteratively  ... 
arXiv:1910.08919v1 fatcat:sbl2vymqozbg5kdajy4o4262pi

Iterative data-driven inference of nonlinearity measures via successive graph approximation [article]

Tim Martin, Frank Allgöwer
2020 arXiv   pre-print
First, we compute a guaranteed upper bound of these measures by given input-output samples based on a data-based non-parametric set-membership representation of the ground-truth system and local inferences  ...  In this paper, we establish an iterative data-driven approach to derive guaranteed bounds on nonlinearity measures of unknown nonlinear systems.  ...  One data-driven approach is examined in [2] where controltheoretic system properties, as L 2 -gain and conic relations, are learned from given input-output samples.  ... 
arXiv:2004.11746v2 fatcat:i7bleeq2irgilctvlhptngmxwq

On Modelling of Data-Driven Monotone Zero-Order TSK Fuzzy Inference Systems using a System Identification Framework

Chin Ying Teh, Yi Wen Kerk, Kai Meng Tay, Chee Peng Lim
2018 IEEE transactions on fuzzy systems  
Index Terms-Degree of monotonicity, monotone data, monotone fuzzy rules, monotone fuzzy rules relabeling, monotonicity test, strong fuzzy partition, system identification, TSK fuzzy inference system.  ...  A system identification-based framework is used to develop monotone fuzzy If-Then rules for formulating monotone zero-order Takagi-Sugeno-Kang (TSK) Fuzzy Inference Systems (FISs) in this paper.  ...  Monotonicity Property in FIS Modeling A model that obeys the monotonicity property between the input and output variables, i.e., a monotone model, is useful in various applications, e.g., , we showed that  ... 
doi:10.1109/tfuzz.2018.2851258 fatcat:svpjnjjwbbdjrpnnounkqdymie

Machine learning for modeling, diagnostics, and control of non-equilibrium plasmas

Ali Mesbah, David B Graves
2019 Journal of Physics D: Applied Physics  
Machine learning (ML) is a set of computational tools that can analyze and utilize large amounts of data for many different purposes.  ...  in the field of non-equilibrium plasma (NEP) studies.  ...  between inputs and outputs of a system.  ... 
doi:10.1088/1361-6463/ab1f3f fatcat:zdmlxj2jn5b6dj23purms2r7xq

Dealing with observational data in control

Emma D. Wilson, Quentin Clairon, Robin Henderson, C. James Taylor
2018 Annual Reviews in Control  
This considers the following issues: (i) how to identify a system model from observational data subject to missing measurements, (ii) how to determine control inputs when output data includes missing measurements  ...  There is growing interest in the use of control theory for interdisciplinary applications, where data may be sparse or missing, be non-uniformly sampled, have greater uncertainty, and where there is no  ...  Therefore, when data are missing it is attractive to provide estimates of the outputs at a constant sampling rate, so as to have access to the systems theory for time driven systems (Heemels et al., 2008  ... 
doi:10.1016/j.arcontrol.2018.05.001 fatcat:nixli7cvg5drto7y2wwbqrwpku

Spiking Neural Network-Based Near-Sensor Computing for Damage Detection in Structural Health Monitoring

Francesco Barchi, Luca Zanatta, Emanuele Parisi, Alessio Burrello, Davide Brunelli, Andrea Bartolini, Andrea Acquaviva
2021 Future Internet  
In this work, we present an innovative approach for damage detection of infrastructures on-edge devices, exploiting a brain-inspired algorithm.  ...  We used a hardware-in-the-loop environment with virtual sensors generating data on an SPI interface connected to the physical microcontroller to evaluate the system with a data stream from a real viaduct  ...  (I) as it is a property of the spiking input encoding.  ... 
doi:10.3390/fi13080219 fatcat:2pmrqwysanebloasddvcyluf4q

Model-Based Deep Learning [article]

Nir Shlezinger, Jay Whang, Yonina C. Eldar, Alexandros G. Dimakis
2021 arXiv   pre-print
We divide hybrid model-based/data-driven systems into categories based on their inference mechanism.  ...  We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.  ...  to avoid overfitting and allow the resulting system to infer reliably with new data samples.  ... 
arXiv:2012.08405v2 fatcat:4ilqi3vv4rar5gsveqzo4loqpy


K. Asaithambi, A.N. Gani
2016 International Journal of Pure and Applied Mathematics  
An open source traffic data has been evaluate and compare the performance of these neurofuzzy systems.  ...  This paper evaluates two recent neurofuzzy algorithms that are capable of automatically determining the rule base and architecture in a purely data driven approach.  ...  For the system identification task, the SaFIN used three terms for fuzzy clustering of each input and output dimension as shown in fig 2.  ... 
doi:10.12732/ijpam.v107i4.20 fatcat:lixdttoerjbzledr7lgst5wxiu

Assigning Confidence to Molecular Property Prediction [article]

AkshatKumar Nigam, Robert Pollice, Matthew F. D. Hurley, Riley J. Hickman, Matteo Aldeghi, Naruki Yoshikawa, Seyone Chithrananda, Vincent A. Voelz, Alán Aspuru-Guzik
2021 arXiv   pre-print
First, our considerations for assessing confidence begin with dataset bias and size, data-driven property prediction and feature design.  ...  Accordingly, the explosive rise of data-driven techniques raises an important question: What confidence can be assigned to molecular property predictions and what techniques can be used for that purpose  ...  In doing so, we discuss uncertainties inherent in datasets, outputs of data-driven models, input features, and simulation of binding affinities.  ... 
arXiv:2102.11439v1 fatcat:vblssmndlvchbjmubsnjjjppcy

RDFProv: A relational RDF store for querying and managing scientific workflow provenance

Artem Chebotko, Shiyong Lu, Xubo Fei, Farshad Fotouhi
2010 Data & Knowledge Engineering  
Finally, our case study for provenance management in a real-life biological simulation workflow showed the production quality and capability of the RDFProv system.  ...  on-the-fly by using the type information of an instance available from the input provenance ontology and the statistics of the sizes of the tables in the database.  ...  In our sample model, a workflow consists of a set of workflow tasks, workflow inputs, workflow input parameters, workflow outputs, and data channels that connect them.  ... 
doi:10.1016/j.datak.2010.03.005 fatcat:hbwenralmjeephtly2bmcnx7qe

An artificial olfactory inference system based on memristive devices

Tong Wang, He‐Ming Huang, Xiao‐Xue Wang, Xin Guo
2021 InfoMat  
To address such an issue, an artificial olfactory system is promoted, emulating the function of the human nose by means of gas sensors and an inference system.  ...  Eventually, the olfactory inference system successfully identifies the gases with a high accuracy of 95%.  ...  data, then the outputs are used as the input of a neural network for the classification task; it is much easier to train a machine learning model by using the output of the RC system than using original  ... 
doi:10.1002/inf2.12196 fatcat:53txgaprbfbdvez2w6eagqdy24

Soft metrology based on machine learning: A review

Marcela Vallejo, Carolina de la Espriella, Juliana Andrea Gómez-Santamaría, Andres Felipe Ramirez Barrera, Edilson Delgado-Trejos
2019 Measurement science and technology  
For this purpose, the literature on indirect measurement techniques and systems has been reviewed, encompassing recent as well as a few older key documents to present a time line of development and map  ...  Soft metrology has been defined as a set of measurement techniques and models that allow the objective quantification of properties usually determined by human perception such as smell, sound or taste.  ...  Acknowledgments This work was supported by the Instituto Tecnologico Metropolitano ITM of Medellin (Grant No. P17202).  ... 
doi:10.1088/1361-6501/ab4b39 fatcat:dw6ahml7ofhrbcz43nx7643yaq

Automatically learning shape specifications

He Zhu, Gustavo Petri, Suresh Jagannathan
2016 SIGPLAN notices  
language using a lightweight data-driven learning procedure.  ...  This paper presents a novel automated procedure for discovering expressive shape specifications for sophisticated functional data structures.  ...  This work was supported in part by the Center for Science of Information (CSoI), an NSF Science and Technology Center, under grant agreement CCF-0939370.  ... 
doi:10.1145/2980983.2908125 fatcat:pkr2zib775burhalokplvgevke

Data-Driven Model Predictive Control for Wave Energy Converters Using Gaussian Process

Yanhua Liu, Shuo Shi, Zhenbin Zhang, Zhenfeng Di, Oluleke Babayomi
2022 Symmetry  
A cross-entropy solver for data-driven MPC is employed for rapid, high-performance results, which samples trajectories from Gaussian distributions based on the concept of the symmetry principle.  ...  This article overcomes this challenge by proposing a data-driven MPC scheme for wave energy converters.  ...  Conclusions This paper proposes a data-driven MPC strategy for PAWEC energy maximization that relies on a GP-based probabilistic model from black-box identification using input/output training datasets  ... 
doi:10.3390/sym14071284 fatcat:rkcw3hj6wnfhzc3o22ieqwtkem

Confidence Driven Unsupervised Semantic Parsing

Dan Goldwasser, Roi Reichart, James Clarke, Dan Roth
2011 Annual Meeting of the Association for Computational Linguistics  
Evaluated over Geoquery, a standard dataset for this task, our system achieved 66% accuracy, compared to 80% of its fully supervised counterpart, demonstrating the promise of unsupervised approaches for  ...  Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain.  ...  Acknowledgments We thank the anonymous reviewers for their helpful feedback.  ... 
dblp:conf/acl/GoldwasserRCR11 fatcat:7y7k3ejnnrgfvmrxeqcwme3n5u
« Previous Showing results 1 — 15 out of 68,529 results