scholarly journals Utilization of multilayer perceptron for determining the inverse kinematics of an industrial robotic manipulator

2021 ◽  
Vol 18 (4) ◽  
pp. 172988142092528
Author(s):  
Sandi Baressi Šegota ◽  
Nikola Anđelić ◽  
Vedran Mrzljak ◽  
Ivan Lorencin ◽  
Ivan Kuric ◽  
...  
Keyword(s):  
Multilayer Perceptron ◽  
Inverse Kinematics ◽  
Absolute Error ◽  
Robotic Manipulator ◽  
Inverse Kinematic ◽  
Percentage Error ◽  
Joint Angles ◽  
Transformation Matrices ◽  
Error Metrics

Inverse kinematic equations allow the determination of the joint angles necessary for the robotic manipulator to place a tool into a predefined position. Determining this equation is vital but a complex work. In this article, an artificial neural network, more specifically, a feed-forward type, multilayer perceptron (MLP), is trained, so that it could be used to calculate the inverse kinematics for a robotic manipulator. First, direct kinematics of a robotic manipulator are determined using Denavit–Hartenberg method and a dataset of 15,000 points is generated using the calculated homogenous transformation matrices. Following that, multiple MLPs are trained with 10,240 different hyperparameter combinations to find the best. Each trained MLP is evaluated using the R 2 and mean absolute error metrics and the architectures of the MLPs that achieved the best results are presented. Results show a successful regression for the first five joints (percentage error being less than 0.1%) but a comparatively poor regression for the final joint due to the configuration of the robotic manipulator.

Posture Prediction Versus Inverse Kinematics

2001 ◽  
Author(s):  
Karim Abdel-Malek ◽  
Wei Yu ◽  
Zan Mi ◽  
E. Tanbour ◽  
M. Jaber
Keyword(s):  
Inverse Kinematics ◽  
Degrees Of Freedom ◽  
Human Performance ◽  
Inverse Kinematic ◽  
Cost Functions ◽  
Optimization Approach ◽  
Final Position ◽  
Serial Robot ◽  
Posture Prediction

Abstract Inverse kinematics is concerned with the determination of joint variables of a manipulator given its final position or final position and orientation. Posture prediction also refers to the same problem but is typically associated with models of the human limbs, in particular for postures assumed by the torso and upper extremities. There has been numerous works pertaining to the determination and enumeration of inverse kinematic solutions for serial robot manipulators. Part of these works have also been directly extended to the determination of postures for humans, but have rarely addressed the choice of solutions undertaken by humans, but have focused on purely kinematic solutions. In this paper, we present a theoretical framework that is based on cost functions as human performance measures, subsequently predicting postures based on optimizing one or more of such cost functions. This paper seeks to answer two questions: (1) Is a given point reachable (2) If the point is reachable, we shall predict a realistic posture. We believe that the human brain assumes different postures driven by the task to be executed and not only on geometry. Furthermore, because of our optimization approach to the inverse kinematics problem, models with large number of degrees of freedom are addressed. The method is illustrated using several examples.

Inverse Kinematics of Serial Redundant Manipulators With Locked Articulations

1995 ◽  
Author(s):  
Louis Perreault ◽  
Clément M. Gosselin
Keyword(s):  
Inverse Kinematics ◽  
General Procedure ◽  
Inverse Kinematic ◽  
Redundant Manipulators ◽  
Redundant Manipulator ◽  
Inverse Kinematic Problem

Abstract This paper presents an algorithm for the solution of the inverse kinematics of a serial redundant manipulator with one (or more) locked joint(s). To this end, a general procedure is developed for the determination of the equivalent Denavit-Hartenberg parameters of a serial manipulator with locked joints. This procedure can be applied to any serial architecture. The solution of the inverse kinematic problem for the three cases which can arise is then addressed. An example of the application of the method to a SARCOS 7-DOF manipulator is also given.

scholarly journals COVID-19 Infection Forecasting based on Deep Learning in Iran

2020 ◽  
Author(s):  
Mehdi Azarafza ◽  
Mohammad Azarafza ◽  
Jafar Tanha
Keyword(s):  
Short Term Memory ◽  
Mean Squared Error ◽  
Moving Average ◽  
National Level ◽  
Absolute Error ◽  
Percentage Error ◽  
Autoregressive Integrated Moving Average ◽  
Error Metrics ◽  
Squared Error ◽  
Better Than

Since December 2019 coronavirus disease (COVID-19) is outbreak from China and infected more than 4,666,000 people and caused thousands of deaths. Unfortunately, the infection numbers and deaths are still increasing rapidly which has put the world on the catastrophic abyss edge. Application of artificial intelligence and spatiotemporal distribution techniques can play a key role to infection forecasting in national and province levels in many countries. As methodology, the presented study employs long short-term memory-based deep for time series forecasting, the confirmed cases in both national and province levels, in Iran. The data were collected from February 19, to March 22, 2020 in provincial level and from February 19, to May 13, 2020 in national level by nationally recognised sources. For justification, we use the recurrent neural network, seasonal autoregressive integrated moving average, Holt winter's exponential smoothing, and moving averages approaches. Furthermore, the mean absolute error, mean squared error, and mean absolute percentage error metrics are used as evaluation factors with associate the trend analysis. The results of our experiments show that the LSTM model is performed better than the other methods on the collected COVID-19 dataset in Iran

scholarly journals The Analysis of the 2008 US Financial Crisis: An Intervention Approach

2018 ◽  
Vol 10 (1) ◽  
pp. 59
Author(s):  
Katleho Daniel Makatjane ◽  
Edward Kagiso Molefe ◽  
Roscoe Bertrum Van Wyk
Keyword(s):  
South Africa ◽  
Exchange Rate ◽  
Financial Crises ◽  
Moving Average ◽  
Absolute Error ◽  
Percentage Error ◽  
Intervention Model ◽  
Sarima Model ◽  
Error Metrics ◽  
The Impact

The current study investigates the impact of the 2008 US financial crises on the real exchange rate in South Africa. The data used in this empirical analysis is for the period from January 2000 to June 2017. The Seasonal autoregressive integrated moving average (SARIMA) intervention charter was used to carry out the analysis. Results revealed that the financial crises period in South Africa occurred in March 2008 and significantly affected the exchange rate. Hence, the impact pattern was abrupt. Using the SARIMA model as a benchmark, four error metrics; to be precise mean absolute error (MAE), mean absolute percentage error (MAPE), mean error (ME) and Mean percentage error (MPE) was used to assess the performance of the intervention model and SARIMA model. The results of the SARIMA intervention model produced better forecasts as compared to that one of SARIMA model. 

scholarly journals Robot Forward and Inverse Kinematics Research using Matlab

2019 ◽  
Vol 8 (2S3) ◽  
pp. 29-35
Keyword(s):  
Inverse Kinematics ◽  
Twist Angle ◽  
Inverse Kinematic ◽  
Forward Kinematics ◽  
Joint Angles ◽  
Link Length ◽  
Matlab Program ◽  
Kinematic Models ◽  
Position And Orientation ◽  
End Effectors

The joint arrangement of every robot can be described by the Denavit Hardenberg parameters. These parameters are enough to obtain a working of the robot described and Presented is a Matlab program which modelled Sorbet era 5u pluse given a set of corresponding DH parameters. The prim aim of this paper is to develop forward and inverse kinematic models of Sorbet era 5u plus using Matlab GUI in order to optimize the manipulative task execution. Forward kinematics analysis is done for the flexible twist angle, link lengths, and link offsets of each joints by varying joint angles to specify the position and orientation of the end effectors. Forward analysis can be used to provide the position of some point on the end effectors together with the orientation of the end effectors measured relative to a coordinate system fixed to ground for a specified set of joint variables. This simulation allows the user to get forward kinematics and inverse kinematics of Scorbot era 5u Plus of the modelled robot in various link length parameters and joint angles and corresponding end effectors position and orientation is going to validate with Rob cell software and compared with Lab view measured values.

scholarly journals Grid search of multilayer perceptron based on the walk-forward validation methodology

2021 ◽  
Vol 11 (2) ◽  
pp. 1742
Author(s):  
Tran Thanh Ngoc ◽  
Le Van Dai ◽  
Dang Thi Phuc
Keyword(s):  
Neural Network ◽  
Multilayer Perceptron ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Ho Chi Minh City ◽  
Percentage Error ◽  
Grid Search ◽  
Load Demand ◽  
The Us ◽  
Airline Passenger

Multilayer perceptron neural network is one of the widely used method for load forecasting. There are hyperparameters which can be used to determine the network structure and used to train the multilayer perceptron neural network model. This paper aims to propose a framework for grid search model based on the walk-forward validation methodology. The training process will specify the optimal models which satisfy requirement for minimum of accuracy scores of root mean square error, mean absolute percentage error and mean absolute error. The testing process will evaluate the optimal models along with the other ones. The results indicated that the optimal models have accuracy scores near the minimum values. The US airline passenger and Ho Chi Minh city load demand data were used to verify the accuracy and reliability of the grid search framework.

scholarly journals The Analysis of the 2008 US Financial Crisis: An Intervention Approach

2018 ◽  
Vol 10 (1(J)) ◽  
pp. 59-68
Author(s):  
Katleho Daniel Makatjane ◽  
Edward Kagiso Molefe ◽  
Roscoe Bertrum Van Wyk
Keyword(s):  
South Africa ◽  
Exchange Rate ◽  
Financial Crises ◽  
Moving Average ◽  
Absolute Error ◽  
Percentage Error ◽  
Intervention Model ◽  
Sarima Model ◽  
Error Metrics ◽  
The Impact

The current study investigates the impact of the 2008 US financial crises on the real exchange rate in South Africa. The data used in this empirical analysis is for the period from January 2000 to June 2017. The Seasonal autoregressive integrated moving average (SARIMA) intervention charter was used to carry out the analysis. Results revealed that the financial crises period in South Africa occurred in March 2008 and significantly affected the exchange rate. Hence, the impact pattern was abrupt. Using the SARIMA model as a benchmark, four error metrics; to be precise mean absolute error (MAE), mean absolute percentage error (MAPE), mean error (ME) and Mean percentage error (MPE) was used to assess the performance of the intervention model and SARIMA model. The results of the SARIMA intervention model produced better forecasts as compared to that one of SARIMA model. 

scholarly journals Freeing the Serial Mechanism Designer from Inverse Kinematic Solvability Constraints

2010 ◽  
Vol 7 (3) ◽  
pp. 209-216 ◽  
Author(s):  
Diana C. W. Friedman ◽  
Tim Kowalewski ◽  
Radivoje Jovanovic ◽  
Jacob Rosen ◽  
Blake Hannaford
Keyword(s):  
Patient Safety ◽  
Robotic Surgery ◽  
Closed Form ◽  
Inverse Kinematics ◽  
Inverse Kinematic ◽  
Forward Kinematics ◽  
Joint Angles ◽  
Computing Power ◽  
Six Degree Of Freedom ◽  
Serial Mechanism

This paper presents a fast numerical solution for the inverse kinematics of a serial manipulator. The method is implemented on the C-arm, a manipulator designed for use in robotic surgery. The inverse kinematics solution provides all possible solutions for any six degree-of-freedom serial manipulator, assuming that the forward kinematics are known and that it is possible to solve for the remaining joint angles if one joint angle’s value is known. With a fast numerical method and the current levels of computing power, designing a manipulator with closed-form inverse kinematics is no longer necessary. When designing the C-arm, we therefore chose to weigh other factors, such as actuator size and patient safety, more heavily than the ability to find a closed-form inverse kinematics solution.

A Sequential Ensemble Model for Communicable Disease Forecasting

2020 ◽  
Vol 15 (4) ◽  
pp. 309-317
Author(s):  
Nashreen Sultana ◽  
Nonita Sharma ◽  
Krishna Pal Sharma ◽  
Shobhit Verma
Keyword(s):  
Communicable Disease ◽  
Research Work ◽  
Foot And Mouth Disease ◽  
Absolute Error ◽  
Percentage Error ◽  
Support Vector ◽  
Ensemble Model ◽  
Prediction Errors ◽  
Classification Problems ◽  
Error Metrics

Background: Ensemble building is a popular method for improving model accuracy for classification problems as well as regression. Objective: In this research work, we propose a sequential ensemble model to predict the number of incidences for communicable diseases like influenza, hand foot and mouth disease (HFMD), and diarrhea and compare it with applied models for prediction. Methods: The weekly dataset of the three diseases, namely, influenza, HFMD, and diarrhea, are collected from the official government site of Hong Kong from the year 2010 to 2018. The data was preprocessed by taking log transformation and z-score transformation. The proposed sequential ensemble model is applied to the processed dataset to predict future occurrences. Results: The result of the proposed ensemble model is compared against standard support vector regression (SVR) using different error metrics such as root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). In the case of all the threedisease datasets, the proposed ensemble model gives better results in comparison to the standard SVR model. Conclusion: The main objective of this research work is to minimize the prediction error; the proposed sequential ensemble model has shown a significant result in terms of prediction errors.

EINE CHEMISCHE METHODE ZUR BESTIMMUNG VON 16-EPI-ÖSTRIOL IM URIN DES MENSCHEN

1963 ◽  
Vol 44 (1) ◽  
pp. 47-66 ◽  
Author(s):  
W. Nocke ◽  
H. Breuer
Keyword(s):  
Melting Point ◽  
Phosphoric Acid ◽  
Aqueous Alkali ◽  
Percentage Error ◽  
Organic Layer ◽  
Maximum Percentage ◽  
Chemical Determination ◽  
Routine Assay ◽  
Hydrolysis Of

ABSTRACT A method for the chemical determination of 16-epi-oestriol in the urine of nonpregnant women with a qualitative sensitivity of less than 0.5 μg/24 h is described. The separation of 16-epi-oestriol and oestriol is accomplished by converting 16-epi-oestriol into its acetonide, a reaction which is stereoselective for cis-glycols and therefore not undergone by oestriol as a trans-glycol. Following partition between chloroform and aqueous alkali, the acetonide of 16-epi-oestriol is completely separated with the organic layer whereas oestriol as a strong phenol remains in the alkaline phase. 16-epi-oestriol is chromatographed on alumina as the acetonide and determined as a Kober chromogen. This procedure can easily be incorporated into the method of Brown et al. (1957 b) thus making possible the simultaneous routine assay of oestradiol-17β, oestrone, oestriol and 16-epi-oestriol from one sample of urine. The specificity of the method was established by separation of 16-epi-oestriol from nonpregnancy urine as the acetonide, hydrolysis of the acetonide by phosphoric acid, isolation of the free compound by microsublimation and identification by micro melting point, colour reactions and chromatography. The accuracy of the method is given by a mean recovery of 64% for pure crystalline 16-epi-oestriol when added to hydrolysed urine in 5–10 μg amounts. The precision is given by s = 0.24 μg/24 h. For the duplicate determination of 16-epi-oestriol the qualitative sensitivity is 0.44 μg/24 h, the maximum percentage error being ± 100% The quantitative sensitivity (±25% error) is 1.7 μg/24 h.

Sign in / Sign up

Export Citation Format

Share Document