Help Of Artificial Neural Network Research Articles

Designing Half-Adder with CMOS Technology using Artificial Neural Network with Verilog Implementation

In this study we want to design a Half-Adder with the help of Artificial Neural Network and design will be made by Complementary metal oxide semiconductor(CMOS).When we design any COMS circuit always we keep in mind that should be in minimum at cost .In this study we have used multi layer ANN to design the circuit. In our study neurons are treated like transistors and weights are used to adjust the value; like negative value as an inverter. Keywords: Half Adder, Complementary Metal Oxide Semiconductor, Artificial Neural Network, Verilog HDL

Analysis of the Possibility of Making a Digital Twin for Devices Operating in Foundries

This work aims to conduct an analysis to find opportunities for the implementation of software incorporating the concept of digital twins for foundry work. Examples of implementations and their impact on the work of enterprises are presented, as is a definition and history of the concept of a digital twin. The outcome of this work is the implementation of software that involves a digital copy of the author’s device, created by the “Łukasiewicz” Research Network at the Krakow Institute of Technology. The research problem of this scientific work is to reduce the number of necessary physical tests on real objects in order to find a solution that saves time and energy when testing the thermal expansion of known and new metal alloys. This will be achieved by predicting the behavior of the sample in a digital environment and avoiding causing it to break in reality. Until now, after an interruption, the device often continued to operate and collect data even though no current was flowing through the material, which could be described as inefficient testing. The expected result will be based on the information and decisions obtained by predicting values with the help of a recurrent neural network. Ultimately, it is intended to predict the condition of the sample after a set period of time. Thanks to this, a decision will be made, based on which the twin will know whether it should automatically end its work, disconnect the power or call the operator for the necessary interaction with the device. The described software will help the operator of a real machine, for example, to operate a larger number of workstations at the same time, without devoting all their attention to a process that may last even for hours. Additionally, it will be possible to start work on selecting the chemical composition of the next material sample and plan its testing in advance. The machine learning handles model learning and value prediction with the help of artificial neural networks that were created in Python. The application uses historical test data, additionally retrieves current information, presents it to the user in a clear modern form and runs the provided scripts. Based on these, it decides on the further operation of the actual device.

MemeNet: Toward a Reliable Local Projection for Image Recognition via Semantic Featurization.

When we recognize images with the help of Artificial Neural Networks (ANNs), we often wonder how they make decisions. A widely accepted solution is to point out local features as decisive evidence. A question then arises: Can local features in the latent space of an ANN explain the model output to some extent? In this work, we propose a modularized framework named MemeNet that can construct a reliable surrogate from a Convolutional Neural Network (CNN) without changing its perception. Inspired by the idea of time series classification, this framework recognizes images in two steps. First, local representations named memes are extracted from the activation map of a CNN model. Then an image is transformed into a series of understandable features. Experimental results show that MemeNet can achieve accuracy comparable to most models' through a set of reliable features and a simple classifier. Thus, it is a promising interface to use the internal dynamics of CNN, which represents a novel approach to constructing reliable models.

Comparison of two different artificial neural network models for prediction of soil penetration resistance

A time-varying, nonlinear soil-plant system contains many unknown elements that can be quantified based on analytical methodologies. Artificial Neural Networks (ANNs) are a widely used mathematical computing, modelling, and predicting method that estimates unknown values of variables from known values of others. This paper aims to simulate relationship between soil moisture, bulk density, porosity ratio, depth, and penetration resistance and to estimate soil penetration resistance with the help of ANNs. For this aim, the Generalized Regression Neural network (GRNN) and Radial Basis Function (RBF) models were developed and compared for the estimation of soil penetration resistance values in MATLAB. A dataset of 153 samples was collected from experimental field. From the 153 data, 102 data (33%) were selected for training and the remaining 51 data (67%) were used for testing. The estimation process was implemented 10 replications using randomly selected testing and training data. Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) were used to evaluate estimation accuracy on the developed ANN methods. Based on MSE, RMSE, MAE and Standard Deviation (SD), statistical results showed that the GRNN modelling presented better results than the RBF model in predicting soil penetration resistance success.

Machine Learning Technique to Classify EMG Signal for Diabetes Person

Diabetes can cause a disease known as diabetic peripheral neuropathy (DPN), which affects the blood vessels and nerves in the legs and feet. This condition can result in plantar foot ulcers and muscular weakness. Detecting DPN early stage is crucial so patients can receive early treatment before their disease worsens. Most technology that detects this disease is usually expensive, like an Electromyography machine (EMG). But, with the increasing popularity of machine learning classification in the health sciences, DPN can be identified early by producing a low-cost equipment. This study aimed to develop a low-cost surface EMG (sEMG) system to detect electrical activity in the lower limb muscles and classify healthy and diabetic subjects during muscle fatigue using K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN) as two methods of machine learning technique. This study used Muscle Sensor V3 as sEMG to record the signal and extract using time domain feature extraction before classification. In KNN, 1–10 values (K) are used, while in ANN, 1–10 values of the number of hidden neurons are used to compare the classification performance. The result shows that ANN is suitable compared to KNN with the method used in this study. ANN algorithm performs better using four hidden neurons with an accuracy of 100% for the training and testing process. The study can conclude that this low-cost sEMG system, with the help of ANN, can effectively classify two subjects (healthy and diabetic) according to the EMG data obtained. This system can help to identify any diabetes neuropathy at an early stage and able to prevent lower limb complications related to the disease.

Review and Analysis of the Development of Artificial Neural Networks

Introduction. The creation of intelligent cyber-physical systems is impossible without knowledge of the analysis and process of development of scientific thought regarding artificial neural networks. The main task of this article is research and analysis of the concept of intelligent technologies based on artificial neural networks. Knowledge of the peculiarities of the creation, formation, and development of knowledge about artificial neural networks is of particular importance for scientists, developers, and design engineers. The article consists of the following parts: first, different approaches to the problem of building artificial functions of the brain are highlighted, the views of which are, in turn, divided into monotypic and genotypic models. The next part is the analysis of the development of artificial intelligence systems, some facts of the process of the development of the artificial intelligence system are also introduced and the peculiarities of scientific opinion on the issues of artificial neural networks are clarified. Various concepts and views are considered, with the help of which it is possible to reproduce the calculation process for a more detailed analysis and synthesis of algorithms of intelligent systems. In the part about the state of the theory, attention is focused on the fact that researchers who could not get accurate analytical answers add to the scientific toolkit methods of experimental modeling either on digital machines or on mechanical models. In addition, it is noted that the model is not the result of research, but only a starting point for analyzing its behavior. In the part of artificial neural networks, the author touches on the following concepts: the logic of McCulloch and Pitts calculations in neural networks, the problems of assigning confidence coefficients, the principle of self-organization, which were first illustrated with the help of computer simulations, the principle of competitive learning, the Kohonen Self-Organizing Maps, multilayer networks of direct propagation taking into account the radial basis functions, which became an alternative to the multilayer perceptron, the support vector machine. As conclusions and as a result, the author receives a complete picture of the genesis of intelligent systems and the technology of artificial neural networks. The processes of development of scientific thought give a clear understanding of the features of intellectual technologies built with the help of artificial neural networks, features of functioning and calculation. Keywords: artificial neural networks, perceptron, theories of McCulloch-Pitts, intelligent computer systems, cyber-physical agent, mobile robot, robotics.

Effect of surface crack and undercut on the stability of cliff

By considering the modeling advantages of the lower bound finite element limit analysis (LBFELA), the present study introduces a novel and simple technique to analyze the influence of an existing surface crack on the stability of cliff having an undercut. By incorporating the different boundary conditions along the discontinuity edges, two types of existing cracks, i.e., fine and separated, are considered. The rock mass at collapse is modeled as the Generalized Hoek-Brown failure criterion with the help of power cone programming (PCP) in the self-developed LBFELA code. The variation in stability caused by the presence of both types of surface crack and undercut is presented in terms of a stability number, σci/γH; where σci represents the uniaxial compressive strength of rock sample, γ is the unit weight of the rock mass, and H is the height of cliff. The variation in the magnitudes of σci/γH is presented as design charts by considering the different depths of surface crack and the various strength parameters of rock mass. The reduction of stability is observed in the presence of surface crack and undercut. As expected, in the presence of a separated surface crack, lower stability is found in comparison with the presence of a fine surface crack on cliff. In addition, the prediction equations for the obtained stability number are presented by using both the classification and regression techniques with the help of artificial neural network (ANN). Furthermore, a sensitivity analysis is performed, and it is found that H/vu and GSI are the most sensitive parameters among all the input parameters. Failure patterns are also studied to find the extent of the plastic state during the collapse.

A comparative analysis of Indian sign language recognition using deep learning models

Sign language is a form of communication where people use bodily gestures, particularly those of hands and arms. This method of communication is put into motion when spoken communication is unattainable or disfavored. There are very few people who can translate sign language and readily understand them. It would be convenient for the hearing-impaired to have a platform where their sign language could be translated easily. Hence, through this study, with the help of artificial neural networks, we wish to compare how various widely implemented deep learning architectures respond to faultless translation of Indian sign language for the native audience. This research would streamline the development of software tools that can accurately predict or translate ISL. For the purpose of understanding the method of training the machine and exploring our model’s performance without any optimizations, a Convolutional Neural Network architecture was implemented. Over the course of our research, there have been several Pre-trained Transfer Learning Models implemented that have yielded promising results. The research aims to contrast how various convolutional neural networks perform while translating Indian Sign Actions on a custom dataset that factors in illumination, angles, and different backgrounds to provide a balanced and distinctive set of images. The goal of this study is to make clear comparisons between the various deep learning frameworks. Hence, a fresh Indian sign language dataset is introduced. Since every dataset in the field of deep learning has special properties that may be utilized for the betterment of the existing models, the development of a fresh dataset could be viewed as a development in the field. The optimum model for our task: classification of these gestures is found to be ResNet-50 (Accuracy = 98.25% and F1-score = 99.34%), and the least favorable was InceptionNet V3 (Accuracy = 66.75%, and F1-score = 70.89%).

Temporal-spatial monitoring of population growth with RS-GIS technology at Wasit province of Iraq

In this study, the growth rate of the population in a spatial-temporal manner has been modeled and explored by relying on the data from remote sensing and using the analytical functions of the geographic information system in Wasit province of Iraq during the period from 2000 to 2020. WorldPop layers were used to prepare population maps and forecast it in 2025 with the help of artificial neural networks. The predictive model was highly accurate (R 2 = 0.98). The next step was to measure the relationship between the rate of population growth and the changes in water areas and the primary production of vegetation with the help of time series of satellite data, which showed the distribution of the population. It is denser in the central, northwestern and southeastern areas of Wasit province. Low density populations have higher frequency. While from 2015 onwards, the frequency of some population classes with higher density increased compared to lower densities. In general, the trend of changes in the average population in the study area has been completely linear. But the maximum annual population density changes were upward and nonlinear. Changes in the area of ​​deciles representing denser areas have increased and the area of ​​deciles representing less densely populated areas has faced a decrease. The results and findings of this study showed that NPP changes were less predictable compared to population density changes because it is a complex function of climatic and human factors. In the estimated population density map in 2025, dense population cores have been formed in the northeastern areas of Wasit province in the vicinity of the border areas with Iran.

Sensitivity Analysis of Parameters Affecting Wetland Water Levels: A Study of Flood Detention Basin, Colombo, Sri Lanka

Wetlands play a vital role in ecosystems. They help in flood accumulation, water purification, groundwater recharge, shoreline stabilization, provision of habitats for flora and fauna, and facilitation of recreation activities. Although wetlands are hot spots of biodiversity, they are one of the most endangered ecosystems on the Earth. This is not only due to anthropogenic activities but also due to changing climate. Many studies can be found in the literature to understand the water levels of wetlands with respect to the climate; however, there is a lack of identification of the major meteorological parameters affecting the water levels, which are much localized. Therefore, this study, for the first time in Sri Lanka, was carried out to understand the most important parameters affecting the water depth of the Colombo flood detention basin. The temporal behavior of water level fluctuations was tested among various combinations of hydro-meteorological parameters with the help of Artificial Neural Networks (ANN). As expected, rainfall was found to be the most impacting parameter; however, apart from that, some interesting combinations of meteorological parameters were found as the second layer of impacting parameters. The rainfall-nighttime relative humidity, rainfall-evaporation, daytime relative humidity-evaporation, and rainfall-nighttime relative humidity-evaporation combinations were highly impactful toward the water level fluctuations. The findings of this study help to sustainably manage the available wetlands in Colombo, Sri Lanka. In addition, the study emphasizes the importance of high-resolution on-site data availability for higher prediction accuracy.

Simulation of Solar Based Smart Grid System Using Artificial Neural Network and Fuzzy Controller

To promote the economy and reliability of the energy trading systems, the use of interconnected smart grids is encouraging. A distributed energy management plan for the interconnected operation of the smart grid that maximizes the resident intake of renewable energy is required during operation. On the client side, possibilities and actions are being discussed in the research papers to incorporate the renewable energy sources. In this paper, the use of Artificial Intelligent Techniques to manage energy or power supply to meet the electricity demand of customers is illustrated. Simulation has been done using wind and solar power supply to manage the load demand for the client side in a smart grid system. Smart Grid has been simulated for all these energy sources to be used with the forecasted electric power requirements. All the required energy demand can be identified from the forecast data, allowing smart grids to deliver better results. For this purpose solar panels are first used in smart grids with the help of artificial neural networks and fuzzy controllers so that load shifts can be done easily and efficiently. Simulation work has been done in MATLAB/Simulink.

Soliton wave parameter estimation with the help of artificial neural network by using the experimental data carried out on the nonlinear transmission line

In this study, an artificial neural network (ANN) model is generated, which is used to estimate the output parameters of soliton waves produced as a result of nonlinear transmission lines (NLTLs). Three different output parameters are acquired as a consequence of the experiments carried out utilizing the five various input parameters that are set in the ANN-based study. Input parameters for NLTL designs with 116 different experiments; inductor (L), input voltage (Vi) value, number of nodes (n), capacitance (C(V)) and load resistance (RLoad) values. Output parameters values, which are maximum voltage (Vmax), center frequency (fcenter), and voltage modulation depth (VMD). Input and output data; 70 % is set aside for training, 15 % for validation and the remaining 15 % for testing. Training, validation, and testing steps are repeated for the output parameters, in which case more than 99 % correlation is found as a result of each operation. An absolute percentage error value is found for each output parameter. Moreover, Mean absolute percentage error (MAPE) is calculated for these output datasets. The data set is tested for the experimental studies carried out in the literature, and it is observed that there is a compliance of over 99 % for this situation.

Study on laser beam butt-welding of NiTinol sheet and input-output modelling using neural networks trained by metaheuristic algorithms

Though NiTinol, the equiatomic Ni-Ti alloy, is revolutionizing different fields of engineering, manufacturing and medicine since its discovery as a functionally advanced material, poor formability and machinability, and the limitations of available fabrication techniques applied for this alloy are restricting its applications in the form of various desired products. Now-a-days, laser welding is the mostly reported joining technique applied to the alloy. Though the difficulties associated with fabrication method and the cost of the alloy are high enough, a computationally efficient model for quick and precise prediction of operating parameters in order to obtain the specified attributes of the laser welded NiTinol sheets is significantly missing in the literature. In the present work, basic metallographic study related to laser welding of NiTinol sheets in butt-joint configuration was investigated. At the same time, an efficient forward and reverse model had been developed with the help of artificial neural network (ANN). These ANNs were trained with the help of regression equation model using five different metaheuristic techniques separately for the development of both forward and reverse models. Laser power, scan speed, frequency, duty factor and focal positions were treated as the input process variables and three different weld attributes, namely bead-area, micro hardness of the bead and tensile strength of the bead were considered as output variables of the process. The developed model was capable enough of predicting the outputs, which were in good agreement with the experimental data, for both forward and reverse models. The novelty of this study deals with the development and testing of feed-forward neural network and recurrent neural network trained using five different metaheuristic techniques for both the forward and reverse modelling of fibre laser welding of NiTinol alloys.

Artificial Neural Networks- An Introduction and Application in Animal Breeding and Production: A Review

With the advent of newer methods and tools for accurate analysis, the outcomes of researches have become increasingly precise. This increase in reliability of research findings and forecasting is well demanded in various fields of science including those under animal breeding as well as its allied aspects such as production. One such recent breakthrough is an artificial neural network (ANN), which is a system of hardware and/or software programmed to function like the operation of neurons in the human brain. ANNs are a variety of deep learning technology, which also falls under the umbrella of artificial intelligence. The determination of milk yield, quality of meat animals, predicting breeding values, inferring demography and recombination, genome-enabled prediction are few of the sectors where ANN has proved to be a valuable asset. The correlation coefficient between the experimental values and those predicted with the help of ANN was found to be close to 1. These studies were a significant indication of the impactful ability of ANN. The early selection of superior bulls, culling of low performing ones, frequent prediction of breeding values and taking into account the non linearity encountered in biological research are few of the many benefits of using ANN in researches of animal genetics and production. Hence, considering its prodigious role, this current review has been written to highlight the role and impact of ANN in livestock studies.

Multiparameter Neural Network Modeling of Facilitated Transport Mixed Matrix Membranes for Carbon Dioxide Removal.

Membranes for carbon capture have improved significantly with various promoters such as amines and fillers that enhance their overall permeance and selectivity toward a certain particular gas. They require nominal energy input and can achieve bulk separations with lower capital investment. The results of an experiment-based membrane study can be suitably extended for techno-economic analysis and simulation studies, if its process parameters are interconnected to various membrane performance indicators such as permeance for different gases and their selectivity. The conventional modelling approaches for membranes cannot interconnect desired values into a single model. Therefore, such models can be suitably applicable to a particular parameter but would fail for another process parameter. With the help of artificial neural networks, the current study connects the concentrations of various membrane materials (polymer, amine, and filler) and the partial pressures of carbon dioxide and methane to simultaneously correlate three desired outputs in a single model: CO2 permeance, CH4 permeance, and CO2/CH4 selectivity. These parameters help predict membrane performance and guide secondary parameters such as membrane life, efficiency, and product purity. The model results agree with the experimental values for a selected membrane, with an average absolute relative error of 6.1%, 4.2%, and 3.2% for CO2 permeance, CH4 permeance, and CO2/CH4 selectivity, respectively. The results indicate that the model can predict values at other membrane development conditions.

ВИБРОМОНИТОРИНГ ДВИГАТЕЛЯ ВНУТРЕННЕГО СГОРАНИЯ

The work is devoted to the problem of diagnostics of automotive internal combustion engines.The problem of monitoring the state of internal combustion engine is now most relevant dueto the increase in the number of cars and the tightening of environmental requirements. In thework the consequences of operation of faulty internal combustion engine are considered. The purposeof the work is to justify the choice from existing diagnostic methods of such a method, whichcan help to detect the fault most accurately and quickly. For this purpose, the work details moderndiagnostic tools, highlights the principles of work, advantages and disadvantages. With the adventof modern technologies, the long-known method of estimating the state of internal combustionengine by sound can become the most advanced, as the human factor is excluded, for signal processingthe computational technique of analysis of the audio spectrum in which is carried out withthe help of artificial neural networks is used. The use of artificial neural networks for sound spectrumanalysis has found application in speech recognition and for diagnosis of respiratory systemdiseases. The article considers mechanisms that are capable of generating sound signals duringinternal combustion engine operation, some of them are phased, i.e. they are tied to operatingcycles, some are not phased. The proposed diagnostic technique allows to distinguish "useful"sounds from the total number of internal combustion engine noises, after comparative analysis topoint to the node the sound of which differs from the reference, serviceable one. Scientific noveltyconsists in the fact that the diagnostic process becomes automated, all sounds captured by sensorsare processed in a computer or a special scanner, the display shows information about the condition of certain nodes, unlike traditional methods where the diagnosis is carried out visually or byear. This increases diagnostic accuracy and reduces overall labor intensity by avoiding partial orcomplete engine disassembly

Estimation of cutting forces and tool tip temperature in turning operation with help of artificial neural network

Estimation of cutting forces for different metal cutting processes are very important to get the idea about specific cutting power required for the machining and for the design of a machine-fixture-tool system. The main objective of this work is to estimate the machining variables and study the effect of cutting parameters on them. In this work cutting forces as main cutting force, feed force, thrust force and tool tip temperature have been selected as machining variables and their values have been estimated under different combination of cutting parameters such as tool geometry rake angle, entering angle and cutting speed. To study the effect of process parameters initially linear regression equations have been generated and then the effect of process parameters on selected machining variables have been shown with help of 3-D surface plots. For the estimation of machining variables as cutting forces and tool tip temperature, different models have been created with help of an expert system Artificial Neural Network (ANN). In this work different models with combinations of transfer functions, number of neurons, number of epochs have been taken ad best possible model has been found out. Then to train, test the different established Multilayer Feed-Forward Neural Network (MLFFNN) models and for validation the experimental data have been used. The value estimated with help of different ANN models have been collected and find out the coefficient of regression R2, Root Mean Square Error RMSE and Mean absolute percentage error MAPE with respect to actual or experimental values. Based on the higher value of R2, lower value of RMSE and MAPE best model has been selected. With help of selected model machining variables have been estimated and compared with actual values. From this research work it has been pointed out that the model with Bayesian Regularization transfer function, 30 number of neurons, 300 number of epochs performed well with R2 = 0.9996, RMSE = 6.161 and MAPE = 1.67 %. This model provide better performance as compared to other ANN models have been trained with Levenberg-Marquardt and Conjugate Gradient training function.

Prediction of Specific Fuel Consumption of 60 HP 2WD Tractor Using Artificial Neural Networks

In this study, specific fuel consumption was determined at different axle load, tire pressure and drawbar force for a 60 HP tractor. In addition, the results were also estimated with the help of Artificial Neural Networks (ANN), which is one of the machine learning methods. The testings were carried out on the Tractor Draft Test Track. In the study; three different drive tire inner pressures (P) (160 kPa, 120 kPa and 80 kPa), four different dynamic axle loads (W) (1796 daN, 2076 daN, 2276 daN, 2476 daN) and four different traction forces (500 daN,1000 daN, 1500 daN, 2000 daN) were tested. Specific fuel consump-tion values varied between 290.7-542.1 g/kWh depending on the draft force in the testings Despite the 38% increase in the axle load, a 3.5% decrease occurred in the specific fuel consumption values. Specific fuel consumption values in-creased when increased tire inner pressure. Specific fuel consumption in-creased by 1.03% when a 100% increase in tire pressure. In ANN, the most suc-cessful model was determined by trying different training algorithms, transfer functions and the number of neurons in the hidden layer. In the most successful network model, MAE, RMSE values for the prediction of specific fuel consump-tion were found to be 0.005331, 0.007551 respectively.

Optimized Task Group Aggregation-Based Overflow Handling on Fog Computing Environment Using Neural Computing

It is a non-deterministic challenge on a fog computing network to schedule resources or jobs in a manner that increases device efficacy and throughput, diminishes reply period, and maintains the system well-adjusted. Using Machine Learning as a component of neural computing, we developed an improved Task Group Aggregation (TGA) overflow handling system for fog computing environments. As a result of TGA usage in conjunction with an Artificial Neural Network (ANN), we may assess the model’s QoS characteristics to detect an overloaded server and then move the model’s data to virtual machines (VMs). Overloaded and underloaded virtual machines will be balanced according to parameters, such as CPU, memory, and bandwidth to control fog computing overflow concerns with the help of ANN and the machine learning concept. Additionally, the Artificial Bee Colony (ABC) algorithm, which is a neural computing system, is employed as an optimization technique to separate the services and users depending on their individual qualities. The response time and success rate were both enhanced using the newly proposed optimized ANN-based TGA algorithm. Compared to the present work’s minimal reaction time, the total improvement in average success rate is about 3.6189 percent, and Resource Scheduling Efficiency has improved by 3.9832 percent. In terms of virtual machine efficiency for resource scheduling, average success rate, average task completion success rate, and virtual machine response time are improved. The proposed TGA-based overflow handling on a fog computing domain enhances response time compared to the current approaches. Fog computing, for example, demonstrates how artificial intelligence-based systems can be made more efficient.

DDPG Algoritmasında Bulunan Ornstein–Uhlenbeck Gürültüsünün Standart Sapmasının Araştırılması

Reinforcement learning is a learning method that many creatures often unwittingly use to gain abilities such as eating and walking. Inspired by this learning method, machine learning researchers have reduced this learning method to subheadings as value learning and policy learning. In this study, the noise standard deviation of the deep deterministic policy gradient (DDPG) method, which is one of the policy learning algorithms, was examined to solve inverse kinematics of a 2 degrees-of-freedom planar robot. For this examination, 8 different functions were determined depending on the maximum value of the output of the action artificial neural network. Created artificial neural networks were trained by using these functions in 1000 iterations with 200 steps in each iteration. After the training, the statistical difference between the groups was examined and it was found that there was no statistical difference between the three best groups. For this reason, the best three groups were retrained 2500 iterations and 200 steps and tested for 100 different test scenarios after the training. After testing, the inverse kinematic equation of the 2 degrees-of-freedom planar robot with minimal errors was obtained with the help of artificial neural networks. In the light of the results, the importance of the choice of the standard deviation of noise and the correct range of selection was presented for researchers who will work in this field.