Real Time Estimation of Population Receptive Fields Using Gradient Descent

Mapping Intimacies ◽

10.1101/194621 ◽

2017 ◽

Cited By ~ 1

Author(s):

Mario Senden

Keyword(s):

Real Time ◽

Gradient Descent ◽

Receptive Fields ◽

Simulated Data ◽

Time Estimation ◽

Ground Truth ◽

Good Correspondence ◽

Mapping Procedure ◽

Model Free ◽

Exact Shape

AbstractA real-time population receptive field mapping procedure based on gradient descent is proposed. Model-free receptive fields produced by the algorithm are evaluated in context of simulated data exhibiting different levels of temporally autocorrelated noise and spatial point spread. As with any model-free approach, the exact shape of receptive fields produced by the real-time algorithm depends on the stimulus. Nevertheless, estimated receptive fields show good correspondence with ground-truth receptive fields in terms of both position and size. Furthermore, fitting a parametric model to the previously obtained estimates approximates the exact shape of the true underlying receptive fields well.

Download Full-text

Ship As a Wave Buoy: Using Simulated Data to Train Neural Networks for Real Time Estimation of Relative Wave Direction

Volume 9: Rodney Eatock Taylor Honoring Symposium on Marine and Offshore Hydrodynamics; Takeshi Kinoshita Honoring Symposium on Offshore Technology ◽

10.1115/omae2019-96225 ◽

2019 ◽

Cited By ~ 1

Author(s):

Bart Mak ◽

Bülent Düz

Keyword(s):

Neural Networks ◽

Real Time ◽

General Model ◽

Simulated Data ◽

Time Estimation ◽

Measured Data ◽

Wave Direction ◽

Sea State ◽

Digital Twin ◽

Extended Training

Abstract Being able to give real time on-board advice, without depending on extensive sets of measured data, is the ultimate goal of the digital twin concept. Ideally, the models used in a digital twin only rely on current in-service data, although they have been built using simulated and possibly some measured data. Working with just the 6-DOF motions of a ship, can the local sea state reliably be estimated using the digital twin concept? Does a general model exist to do so, without the need to measure or simulate the particular ship? In this paper, we discuss how simulations of an advancing ship, subjected to various sea states, can be used to estimate the relative wave direction from in-service motion measurements of the corresponding ship. Various types of neural networks are used and evaluated with simulated data and measured data. In order to study the generalization power of the neural networks, a range of ships has been simulated, with varying lengths, drafts and geometries. Neural networks have been trained on selections of the ships in this extended training set and evaluated on the remaining ships. Results show that the developed neural networks give a remarkable performance in simulation data. Furthermore, generalization over geometry is very good, opening the door to train a general model for estimating sea state characteristics. Using the same model for in-service measurements does not perform well enough yet and further research is required. The paper will include discussion on possible causes for this performance gap and some promising ideas for future work.

Download Full-text

A Spatial-Temporal based Next Frame Prediction and Unsupervised Classification of Video Anomalies in Real Time Estimation

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.a3161.1011121 ◽

2021 ◽

Vol 11 (1) ◽

pp. 120-124

Author(s):

Swapna Kumari Sahu ◽

◽

Dr. M. Jayanthi Rao ◽

Keyword(s):

Anomaly Detection ◽

Real Time ◽

Prediction Models ◽

Temporal Dynamics ◽

Time Estimation ◽

Ground Truth ◽

Unsupervised Classification ◽

Reconstruction Error ◽

Method Performance ◽

Time Accuracy

Anomaly detection is an area of video analysis has a great importance in automated surveillance. Although it has been extensively studied, there has been little work started using CNN networks. Hence, in this thesis we presented a novel approach for learning motion features and modeling normal Spatio-temporal dynamics for anomaly detection. In our technique, we capture variations in scale of the patterns of motion in an image object by using optical flow dense estimation technique and train our auto encoder model using convolution long short term memories (ConvLSTM2D) as we are processing video frames and we predict the anomaly in real time using Euclidean distance between the generated and the ground truth frame and we achieved a real time accuracy of nearly 98% for the youtube videos which are not used for either testing or training. Error between the network’s output and the target output is used to classify a video volume as normal or abnormal. In addition to the use of reconstruction error, we also use prediction error for anomaly detection. The prediction models show comparable performance with state of the art methods. In comparison with the proposed method, performance is improved in one dataset. Moreover, running time is significantly faster.

Download Full-text

Extremely Fast pRF Mapping for Real-Time Applications

10.1101/2021.03.24.436795 ◽

2021 ◽

Author(s):

Salil Bhat ◽

Michael Lührs ◽

Rainer Goebel ◽

Mario Senden

Keyword(s):

Receptive Field ◽

Real Time ◽

Communication Systems ◽

Brain Activity ◽

Receptive Fields ◽

Cortical Activation ◽

Mapping Procedure ◽

The Road ◽

Real Time Applications ◽

Computational Resources

AbstractPopulation receptive field (pRF) mapping is a popular tool in computational neuroimaging that allows for the investigation of receptive field properties, their topography and interrelations in health and disease. Furthermore, the possibility to invert population receptive fields provides a decoding model for constructing stimuli from observed cortical activation patterns. This has been suggested to pave the road towards pRF-based brain-computer interface (BCI) communication systems, which would be able to directly decode internally visualized letters from topographically organized brain activity. A major stumbling block for such an application is, however, that the pRF mapping procedure is computationally heavy and time consuming. To address this, we propose a novel and fast pRF mapping procedure that is suitable for real-time applications. The method is build upon hashed-Gaussian encoding of the stimulus, which significantly reduces computational resources. After the stimulus is encoded, mapping can be performed using either ridge regression for fast offline analyses or gradient descent for real-time applications. We validate our model-agnostic approach in silico, as well as on empirical fMRI data obtained from 3T and 7T MRI scanners. Our approach is capable of estimating receptive fields and their parameters for millions of voxels in mere seconds. This method thus facilitates real-time applications of population receptive field mapping.

Download Full-text

Real-Time Roll Angle Estimation for Two-Wheeled Vehicles

Volume 1: Advanced Computational Mechanics; Advanced Simulation-Based Engineering Sciences; Virtual and Augmented Reality; Applied Solid Mechanics and Material Processing; Dynamical Systems and Control ◽

10.1115/esda2012-82182 ◽

2012 ◽

Cited By ~ 4

Author(s):

Roberto Lot ◽

Vittore Cossalter ◽

Matteo Massaro

Keyword(s):

Real Time ◽

Low Cost ◽

Simulated Data ◽

Time Estimation ◽

Real Data ◽

Original Method ◽

Roll Angle ◽

Collision Warning ◽

Multibody Model ◽

Wheeled Vehicles

An original method for the real-time estimation of the roll angle using low-cost sensors in two-wheeled vehicles is proposed. The roll angle greatly affects the dynamics of single-track vehicles and its estimation is essential in control systems such as ABS, Traction Control, as well as Curve and Collision Warning, or even active suspensions. The proposed method uses a non-linear Kalman filter, its performances are assessed by using both a set of simulated data from a multibody model and a set of real data collected on an instrumented test vehicle.

Download Full-text

A machine for real-time estimation of the tribological characteristics of materials

Industrial laboratory Diagnostics of materials ◽

10.26896/1028-6861-2020-86-4-61-65 ◽

2020 ◽

Vol 86 (4) ◽

pp. 61-65

Author(s):

M. V. Abramchuk ◽

R. V. Pechenko ◽

K. A. Nuzhdin ◽

V. M. Musalimov

Keyword(s):

Real Time ◽

Time Estimation ◽

Tribological Characteristics ◽

Continuous Processing ◽

Friction Machine ◽

Dynamic Friction Coefficient ◽

Displacement Sensors ◽

Frictional Interaction ◽

Real Time Estimation ◽

Automated Quality Control

A reciprocating friction machine Tribal-T intended for automated quality control of the rubbing surfaces of tribopairs is described. The distinctive feature of the machine consists in implementation of the forced relative motion due to the frictional interaction of the rubbing surfaces fixed on the drive and conjugate platforms. Continuous processing of the signals from displacement sensors is carried out under conditions of continuous recording of mutual displacements of loaded tribopairs using classical approaches of the theory of automatic control to identify the tribological characteristics. The machine provides consistent visual real time monitoring of the parameters. The MATLAB based computer technologies are actively used in data processing. The calculated tribological characteristics of materials, i.e., the dynamic friction coefficient, damping coefficient and measure of the surface roughness, are presented. The tests revealed that a Tribal-T reciprocating friction machine is effective for real-time study of the aforementioned tribological characteristics of materials and can be used for monitoring of the condition of tribo-nodes of machines and mechanisms.

Download Full-text

Onboard Real-time Estimation of Mean Orbital Elements with Atmospheric Drag

ACTA AUTOMATICA SINICA ◽

10.3724/sp.j.1004.2013.01722 ◽

2013 ◽

Vol 39 (10) ◽

pp. 1722

Author(s):

Zhao-Wei SUN ◽

Wei-Chao ZHONG ◽

Shi-Jie ZHANG ◽

Jian ZHANG

Keyword(s):

Real Time ◽

Time Estimation ◽

Atmospheric Drag ◽

Orbital Elements ◽

Real Time Estimation

Download Full-text

Anomaly Identification during Polymerase Chain Reaction for Detecting SARS-CoV-2 Using Artificial Intelligence Trained from Simulated Data

Molecules ◽

10.3390/molecules26010020 ◽

2020 ◽

Vol 26 (1) ◽

pp. 20

Author(s):

Reynaldo Villarreal-González ◽

Antonio J. Acosta-Hoyos ◽

Jaime A. Garzon-Ochoa ◽

Nataly J. Galán-Freyle ◽

Paola Amar-Sepúlveda ◽

...

Keyword(s):

Artificial Intelligence ◽

Big Data ◽

Real Time ◽

Binary Classification ◽

Simulated Data ◽

Classification Model ◽

Rt Pcr ◽

Simon Bolivar ◽

Polymerase Chain ◽

Available Information

Real-time reverse transcription (RT) PCR is the gold standard for detecting Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), owing to its sensitivity and specificity, thereby meeting the demand for the rising number of cases. The scarcity of trained molecular biologists for analyzing PCR results makes data verification a challenge. Artificial intelligence (AI) was designed to ease verification, by detecting atypical profiles in PCR curves caused by contamination or artifacts. Four classes of simulated real-time RT-PCR curves were generated, namely, positive, early, no, and abnormal amplifications. Machine learning (ML) models were generated and tested using small amounts of data from each class. The best model was used for classifying the big data obtained by the Virology Laboratory of Simon Bolivar University from real-time RT-PCR curves for SARS-CoV-2, and the model was retrained and implemented in a software that correlated patient data with test and AI diagnoses. The best strategy for AI included a binary classification model, which was generated from simulated data, where data analyzed by the first model were classified as either positive or negative and abnormal. To differentiate between negative and abnormal, the data were reevaluated using the second model. In the first model, the data required preanalysis through a combination of prepossessing. The early amplification class was eliminated from the models because the numbers of cases in big data was negligible. ML models can be created from simulated data using minimum available information. During analysis, changes or variations can be incorporated by generating simulated data, avoiding the incorporation of large amounts of experimental data encompassing all possible changes. For diagnosing SARS-CoV-2, this type of AI is critical for optimizing PCR tests because it enables rapid diagnosis and reduces false positives. Our method can also be used for other types of molecular analyses.

Download Full-text