Development of the nearest neighbour multivariate localized regression modelling technique for steady state engine calibration and comparison with neural networks and global regression

2008 ◽  
Vol 9 (4) ◽  
pp. 297-323 ◽  
Author(s):  
I Brahma ◽  
M C Sharp ◽  
I B Richter ◽  
T R Frazier
Keyword(s):  
Neural Networks ◽  
Steady State ◽  
Modelling Technique ◽  
Nearest Neighbour ◽  
Engine Calibration ◽  
Regression Modelling ◽  
Global Regression

Operational Determination of the Activated Sludge Process Using Neural Networks

1992 ◽  
Vol 26 (9-11) ◽  
pp. 2461-2464 ◽  
Author(s):  
R. D. Tyagi ◽  
Y. G. Du
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Activated Sludge ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Activated Sludge Process

A steady-statemathematical model of an activated sludgeprocess with a secondary settler was developed. With a limited number of training data samples obtained from the simulation at steady state, a feedforward neural network was established which exhibits an excellent capability for the operational prediction and determination.

Efficient engine calibration with local linear neural networks

MTZ worldwide ◽  
2003 ◽  
Vol 64 (5) ◽  
pp. 19-22 ◽  
Author(s):  
Eike Martini ◽  
Hartmut Voß ◽  
Susanne Töpfer ◽  
Rolf Isermann
Keyword(s):  
Neural Networks ◽  
Engine Calibration ◽  
Local Linear

scholarly journals Determination of Body Parts in Holstein Friesian Cows Comparing Neural Networks and k Nearest Neighbour Classification

Animals ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 50
Author(s):  
Jennifer Salau ◽  
Jan Henning Haas ◽  
Wolfgang Junge ◽  
Georg Thaller
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Body Parts ◽  
Nearest Neighbour ◽  
Data Set ◽  
3D Data ◽  
Holstein Friesian ◽  
Knn Classification ◽  
Friesian Cows

Machine learning methods have become increasingly important in animal science, and the success of an automated application using machine learning often depends on the right choice of method for the respective problem and data set. The recognition of objects in 3D data is still a widely studied topic and especially challenging when it comes to the partition of objects into predefined segments. In this study, two machine learning approaches were utilized for the recognition of body parts of dairy cows from 3D point clouds, i.e., sets of data points in space. The low cost off-the-shelf depth sensor Microsoft Kinect V1 has been used in various studies related to dairy cows. The 3D data were gathered from a multi-Kinect recording unit which was designed to record Holstein Friesian cows from both sides in free walking from three different camera positions. For the determination of the body parts head, rump, back, legs and udder, five properties of the pixels in the depth maps (row index, column index, depth value, variance, mean curvature) were used as features in the training data set. For each camera positions, a k nearest neighbour classifier and a neural network were trained and compared afterwards. Both methods showed small Hamming losses (between 0.007 and 0.027 for k nearest neighbour (kNN) classification and between 0.045 and 0.079 for neural networks) and could be considered successful regarding the classification of pixel to body parts. However, the kNN classifier was superior, reaching overall accuracies 0.888 to 0.976 varying with the camera position. Precision and recall values associated with individual body parts ranged from 0.84 to 1 and from 0.83 to 1, respectively. Once trained, kNN classification is at runtime prone to higher costs in terms of computational time and memory compared to the neural networks. The cost vs. accuracy ratio for each methodology needs to be taken into account in the decision of which method should be implemented in the application.

scholarly journals Segmented Linear Regression Modelling of Time-Series of Binary Variables in Healthcare

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Epaminondas Markos Valsamis ◽  
Henry Husband ◽  
Gareth Ka-Wai Chan
Keyword(s):  
Time Series ◽  
Hip Fracture ◽  
Maximum Likelihood ◽  
Mortality Rate ◽  
Linear Regression ◽  
Modelling Technique ◽  
Binary Variables ◽  
Regression Modelling ◽  
Before And After ◽  
Linear Sections

Introduction. In healthcare, change is usually detected by statistical techniques comparing outcomes before and after an intervention. A common problem faced by researchers is distinguishing change due to secular trends from change due to an intervention. Interrupted time-series analysis has been shown to be effective in describing trends in retrospective time-series and in detecting change, but methods are often biased towards the point of the intervention. Binary outcomes are typically modelled by logistic regression where the log-odds of the binary event is expressed as a function of covariates such as time, making model parameters difficult to interpret. The aim of this study was to present a technique that directly models the probability of binary events to describe change patterns using linear sections. Methods. We describe a modelling method that fits progressively more complex linear sections to the time-series of binary variables. Model fitting uses maximum likelihood optimisation and models are compared for goodness of fit using Akaike’s Information Criterion. The best model describes the most likely change scenario. We applied this modelling technique to evaluate hip fracture patient mortality rate for a total of 2777 patients over a 6-year period, before and after the introduction of a dedicated hip fracture unit (HFU) at a Level 1, Major Trauma Centre. Results. The proposed modelling technique revealed time-dependent trends that explained how the implementation of the HFU influenced mortality rate in patients sustaining proximal femoral fragility fractures. The technique allowed modelling of the entire time-series without bias to the point of intervention. Modelling the binary variable of interest directly, as opposed to a transformed variable, improved the interpretability of the results. Conclusion. The proposed segmented linear regression modelling technique using maximum likelihood estimation can be employed to effectively detect trends in time-series of binary variables in retrospective studies.

Identification of a Steady-State Flow in Porous Media Using Artificial Neural Networks

2012 ◽  
Author(s):  
Marek J. Lefik ◽  
Daniela P. Boso ◽  
Bernhard A. Schrefler
Keyword(s):  
Neural Networks ◽  
Porous Media ◽  
Artificial Neural Networks ◽  
Steady State ◽  
Concentration Field ◽  
Flow In Porous Media ◽  
Homogeneous Field ◽  
Steady State Flow ◽  
Convection Problem ◽  
Artificial Neural

For a steady state convection problem, assuming given concentration field values in a few measurement points and hydraulic head values in the same piezometers, the source of the concentration, and its intensity are deduced using Artificial Neural Networks (ANNs). ANNs are trained with data extracted from Finite Difference (FD) solution of a classical convection problem for small Peclet number. The numerical analysis is exemplified for vanishing, homogeneous and non-homogeneous field of velocity. It is shown that the diffusivity vector can also be identified. The complexity of the problem is discussed for each studied case.

An Estimation of 3-Way Catalyst Performance Using Artificial Neural Networks During Idle Speed

2004 ◽  
Author(s):  
P. N. Botsaris ◽  
D. Bechrakis ◽  
P. D. Sparis
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Steady State ◽  
Expert Knowledge ◽  
Operating Conditions ◽  
Experimental Results ◽  
Outlet Temperature ◽  
Practical Applications ◽  
Idle Speed ◽  
Artificial Neural

The intelligent control as fuzzy or artificial is based on either expert knowledge or experimental data and therefore it possesses intrinsic qualities like robustness and ease implementation. Lately, many researchers present studies aim to show that this kind of control can be used in practical applications such as the idle speed control problem in automotive industry. In this study, an estimation of an automobile three-way catalyst performance with artificial neural networks is presented. It may be an alternative approach for an on board diagnostic system (OBD) to predict the catalyst performance. This method was tested using data sets from two kind of catalysts, a brand new and an old one on a laboratory bench at idle speed. The catalyst operation during the “steady state” phase (the phase that the catalyst has reached its operating conditions and works normally) is examined. Further experiments are needed for different catalyst typed before the methods is proposed generally. It consists of 855 elements of catalyst inlet-outlet temperature difference (DT), hydrocarbons (HC), and carbon monoxide (CO) and carbon dioxide (CO2) emissions. The simulation: detects the values of HC, CO, CO2 using the DT as an input to our network forms a neural network. Results showed serious indications that artificial neural networks (or fuzzy logic control laws) could estimate the catalyst performance adequately depending their training process, if certain information about the catalyst system and the inputs and output of such system are known. In this study the “steady state” period experimental results are presented. In this paper the “steady state” period experimental results are presented.

Sign in / Sign up

Export Citation Format

Share Document