MLP Model Research Articles

Classification of Electromyography Signal with Machine Learning

The problem of classifying electromyography signals in each gesture occurs due to the use of a constant level of signal amplitude. This research presents an efficiency enhancement of electromyography signal classification in each gesture with machine learning. The performance efficiency of 5 models: SVM, RF, MLP, KNN, and Deep Leaning was compared. The signals were recorded by a low-cost signal sensor. Fist clenching and hand opening gestures were alternately performed every 5 second for 5 times each. Therefore, the total was 4,767 records divided into 3,274 records of hand opening gesture, 1,492 records of fist clenching gesture and 4,833 records of wrist rotating gesture. The results showed that the MLP model was found to have the highest accuracy at 81.45% for fist clenching and hand opening gestures. The Deep Learning model was found to have the highest accuracy at 89.03% for wrist rotating and hand opening gestures.

A Driving Decision Strategy (DDS) Based on Machine Learning for an Autonomous Vehicle

A current autonomous vehicle determines its driving strategy by considering only external factors (Pedestrians, road conditions, etc.) without considering the interior condition of the vehicle. To solve the problem, this paper proposes “A Driving Decision Strategy(DDS) Based on Machine learning for an autonomous vehicle” which determines the optimal strategy of an autonomous vehicle by analyzing not only the external factors, but also the internal factors of the vehicle (consumable conditions, RPM levels etc.). The DDS learns a genetic algorithm using sensor data from vehicles stored in the cloud and determines the optimal driving strategy of an autonomous vehicle. This paper compared the DDS with MLP and RF neural network models to validate the DDS. In the experiment, the DDS had a loss rate approximately 5% lower than existing vehicle gateways and the DDS determined RPM, speed, steering angle and lane changes 40% faster than the MLP and 22% faster than the RF[1]. Key Words:: Autonomous Vehicle, Machine Learning, Genetic Algorithm .

Depressed Mood Prediction of Elderly People with a Wearable Band.

Depression in the elderly is an important social issue considering the population aging of the world. In particular, elderly living alone who has narrowed social relationship due to bereavement and retirement are more prone to be depressed. Long-term depressed mood can be a precursor to eventual depression as a disease. Our goal is how to predict the depressed mood of single household elderly from unobtrusive monitoring of their daily life. We have selected a wearable band with multiple sensors for monitoring elderly people. Depression questionnaire has been surveyed periodically to be used as the labels. Instead of working with depression patients, we recruited 14 single household elderly people from a nearby community. The wearable band provided daily activity and biometric data for 71 days. From the data, we generate a depressed mood prediction model. Multiple features from the collected sensor data are exploited for model generation. One general model is generated to be used as the baseline for the initial model deployment. Personal models are also generated for model refinement. The general model has a high recall of 80% in an MLP model. Individual models achieved an average recall of 82.7%. In this study, we have demonstrated that we can generate depressed mood prediction models with data collected from real daily living. Our work has shown the feasibility of using a wearable band as an unobtrusive depression monitoring sensor even for elderly people.

Discrimination of ginseng origin by using laser‐induced breakdown spectrum and machine learning algorithms

AbstractIn this paper, the ginsengs from five ginseng origins are discriminated by using laser‐ induced breakdown spectrum (LIBS) combined with random forest‐ support vector machine (RF‐ SVM) and random forest‐ multilayer perception (RF‐ MLP) machine learning algorithms. The raw LIBS of ginseng is pretreated by using the wavelet threshold method, denoise the background information and normalazation to improve the signal‐ to‐ background ratio and the experimental reliability. The RF algorithm is used to select 10 characteristic spectral lines as the input vectors of the MLP and the SVM models to identify the ginseng orgin. The experimental results show that the discrimination accuracy rates of RF‐ MLP and RF‐ SVM models are 99.75% and 99.5%, respectively. The disrimination accuracy of ginseng origin used in the RF‐MLP machine algorithm model is slightly higher than that of the RF‐ SVM model, and then calculated the speed of the RF‐ MLP model is faster than the RF‐ SVM model. The results show that LIBS combined with machine algorithms are both promising rapid discrimination methods for ginseng origin.

A data‐driven Dir‐MUSIC method based on the MLP model

The directional multiple signal classification (Dir-MUSIC) algorithm based on antenna gain array manifold has been proposed to find the direction of the partial discharge source successfully in substations, however, a non-linear optimisation problem in this algorithm is usually time-consuming. To achieve real-time feature, a data-driven Dir-MUSIC method based on the multilayer perception model is proposed to speed up the computing process and simultaneously guarantee the accuracy. Pre-trained the multilayer perception model, the non-linear optimisation problem can be treated as a function can be calculated directly. Input of the model is the noise matrix which can be uniquely calculated with a certain matrix measurement, and output is the estimated direction of the partial discharge source. Simulation results demonstrate that the proposed method has an excellent efficiency and relatively high accuracy, and the computing time can match the real-time demand. Additionally, two effective improvements are proposed to raise the direction accuracy and stability. Specifically, mean error is reduced from 2.58° to 2.22° with the first improvement, and from 2.58° to 1.00° with the second improvement.

Prediction of 6 months endoscopic third ventriculostomy success rate in patients with hydrocephalus using a multi-layer perceptron network

ObjectiveDiscrimination between patients most likely to benefit from endoscopic third ventriculostomy (ETV) and those at higher risk of failure is challenging. Compared to other standard models, we have tried to develop a prognostic multi-layer perceptron model based on potentially high-impact new variables for predicting the ETV success score (ETVSS). MethodsClinical and radiological data of 128 patients have been collected, and ETV outcomes were evaluated. The success of ETV was defined as remission of symptoms and not requiring VPS for six months after surgery. Several clinical and radiological features have been used to construct the model. Then the Binary Gravitational Search algorithm was applied to extract the best set of features. Finally, two models were created based on these features, multi-layer perceptron, and logistic regression. ResultsEight variables have been selected (age, callosal angle, bifrontal angle, bicaudate index, subdural hygroma, temporal horn width, third ventricle width, frontal horn width). The neural network model was constructed upon the selected features. The result was AUC:0.913 and accuracy:0.859. Then the BGSA algorithm removed half of the features, and the remaining (Age, Temporal horn width, Bifrontal angle, Frontal horn width) were applied to construct models. The ANN could reach an accuracy of 0.84, AUC:0.858 and Positive Predictive Value (PPV): 0.92, which was higher than the logistic regression model (accuracy:0.80, AUC: 0.819, PPV: 0.89). ConclusionThe research findings have shown that the MLP model is more effective than the classic logistic regression tools in predicting ETV success rate. In this model, two newly added features, the width of the lateral ventricle's temporal horn and the lateral ventricle's frontal horn, yield a relatively high inter-observer reliability.

Diagnosis of triple negative breast cancer using expression data with several machine learning tools.

Breast cancer is one of the top three commonly caused cancers worldwide. Triple Negative Breast Cancer (TNBC), a subtype of breast cancer, lacks expression of the oestrogen receptor, progesterone receptor, and HER2. This makes the prognosis poor and early detection hard. Therefore, AI based neural models such as Binary Logistic Regression, Multi-Layer Perceptron and Radial Basis Functions were used for differential diagnosis of normal samples and TNBC samples collected from signal intensity data of microarray experiment. Genes that were significantly upregulated in TNBC were compared with healthy controls. The MLP model classified TNBC and normal cells with anaccuracy of 93.4%. However, RBF gave 74% accuracy and binary Logistic Regression model showed an accuracy of 90.0% in identifying TNBC cases.

PM2.5 volatility prediction by XGBoost-MLP based on GARCH models

In recent, air pollution has a sever impact on public health and economy development throughout the world. Air pollution consists of a variety of harming components, of which fine particulate matter (PM2.5) is considered to be one of the causes of health concerns. Under this circumstance, accurate prediction of atmospheric pollutant concentrations has become a hot research hotspot in the academic field of environment. The frequent changes of different factors cause random fluctuations in the concentration of PM2.5, which brings difficulties to the control of the concentration of air pollutants. By predicting concentration values within different areas and understanding the changes about PM2.5 concentrations, we can effectively warn and take actions to fluctuations in PM2.5 concentrations and help environment policy decision-makers provide sufficient information to guide their decisions. A hybrid model combining XGBoost, four GARCH models and MLP model（XGBoost-GARCH-MLP）is proposed to predict PM2.5 concentration values and volatility. The experimental research results show that the volatility forecasting model proposed in this study has good performance in the long-term forecasting process. If the volatility is used as the PM2.5 concentration prediction benchmark, a better prediction result will be obtained. In conclusion, the model established in this study can more effectively predict PM2.5 concentrations and fluctuations in different regions.

Finite volume method network for the acceleration of unsteady computational fluid dynamics: Non‐reacting and reacting flows

Despite rapid improvements in the performance of the central processing unit (CPU), the calculation cost of simulating chemically reacting flow using CFD remains infeasible in many cases. The application of the convolutional neural networks (CNNs) specialized in image processing in flow field prediction has been studied, but the need to develop a neural network design fitted for CFD has recently emerged. In this study, a neural network model introducing the finite volume method (FVM) with unique network architecture and physics-informed loss function was developed to accelerate CFD simulations. The developed network model, considering the nature of the CFD flow field where the identical governing equations are applied to all grids, can predict the future fields with only two previous fields unlike the CNNs requiring many field images (>10 000). The performance of this baseline model was evaluated using CFD time series data from non-reacting flow and reacting flow simulation; counterflow and hydrogen flame with 20 detailed chemistries. Consequently, we demonstrated that (a) the FVM-based network architecture provided significantly improved accuracy of multistep time series prediction compared to the previous MLP model (b) the physic-informed loss function prevented non-physical overfitting problem and ultimately reduced the error in time series prediction (c) observing the calculated residuals in an unsupervised manner could monitor the network accuracy. Additionally, under the reacting flow dataset, the computational speed of this network model was measured to be about 10 times faster than that of the CFD solver.

Machine Learning for the Estimation of Diameter Increment in Mixed and Uneven-Aged Forests

Estimating the diameter increment of forests is one of the most important relationships in forest management and planning. The aim of this study was to provide insight into the application of two machine learning methods, i.e., the multilayer perceptron artificial neural network (MLP) and adaptive neuro-fuzzy inference system (ANFIS), for developing diameter increment models for the Hyrcanian forests. For this purpose, the diameters at breast height (DBH) of seven tree species were recorded during two inventory periods. The trees were divided into four broad species groups, including beech (Fagus orientalis), chestnut-leaved oak (Quercus castaneifolia), hornbeam (Carpinus betulus), and other species. For each group, a separate model was developed. The k-fold strategy was used to evaluate these models. The Pearson correlation coefficient (r), coefficient of determination (R2), root mean square error (RMSE), Akaike information criterion (AIC), and Bayesian information criterion (BIC) were utilized to evaluate the models. RMSE and R2 of the MLP and ANFIS models were estimated for the four groups of beech ((1.61 and 0.23) and (1.57 and 0.26)), hornbeam ((1.42 and 0.13) and (1.49 and 0.10)), chestnut-leaved oak ((1.55 and 0.28) and (1.47 and 0.39)), and other species ((1.44 and 0.32) and (1.5 and 0.24)), respectively. Despite the low coefficient of determination, the correlation test in both techniques was significant at a 0.01 level for all four groups. In this study, we also determined optimal network parameters such as number of nodes of one or multiple hidden layers and the type of membership functions for modeling the diameter increment in the Hyrcanian forests. Comparison of the results of the two techniques showed that for the groups of beech and chestnut-leaved oak, the ANFIS technique performed better and that the modeling techniques have a deep relationship with the nature of the tree species.

A Fuzzy Approach to the Synthesis of Cognitive Maps for Modeling Decision Making in Complex Systems

The object of this study is fuzzy cognitive modeling as a means of studying semistructured socio-economic systems. The features of constructing cognitive maps, providing the ability to choose management decisions in complex semistructured socio-economic systems, are described. It is shown that further improvement of technologies necessary for developing decision support systems and their practical use is still relevant. This work aimed to improve the accuracy of cognitive modeling of semistructured systems based on a fuzzy cognitive map of structuring nonformalized situations (MSNS) with the evaluation of root-mean-square error (RMSE) and mean average squared error (MASE) coefficients. In order to achieve the goal, the following main methods were used: systems analysis methods, fuzzy logic and fuzzy sets theory postulates, theory of integral wavelet transform, correlation and autocorrelation analyses. As a result, a new methodology for constructing MSNS was proposed—a map of structuring nonformalized situations that combines the positive properties of previous fuzzy cognitive maps. The solution of modeling problems based on this methodology should increase the reliability and quality of analysis and modeling of semistructured systems and processes under uncertainty. The analysis using open datasets proved that compared to the classical ARIMA, SVR, MLP, and Fuzzy time series models, our proposed model provides better performance in terms of MASE and RMSE metrics, which confirms its advantage. Thus, it is advisable to use our proposed algorithm in the future as a mathematical basis for developing software tools for the analysis and modeling of problems in semistructured systems and processes. Doi: 10.28991/ESJ-2022-06-02-012 Full Text: PDF

A novel class of reliability-based parallel hybridization (RPH) models for time series forecasting

Hybridization of individual models emerged as a predominant alternative for increasing accuracy in time series forecasting. The literature is abundant on providing hybrid methods aiming at improving forecasting accuracy and comprehensive pattern recognition. The principle behind all hybrid models' success is improving forecasting accuracy. One of the most widely used combination methods in line with the common objective of the hybridization concept is a parallel approach in which the forecasting model applied on the original time series and the weighted forecasts generate the final hybrid result. In parallel hybridization, the key is how to select the weights of each model. The weighting algorithm plays a significant role and the degree of accuracy in such models directly depends on it. However, the traditional parallel hybrid models developed to enhance forecasting accuracy employing multiple individual models simultaneously, faced some limitations, e.g., missing considering the reliability and generalization criteria of developed hybrid models. From the literature, it is observed that none of the parallel hybrid modes proposed in the literature focused on the improving reliability of the hybrid model to obtain better model generalization for unseen data. Thus, the main objective of this study is to propose a novel class of hybrid models named reliability-based parallel hybridization (RPH). The main goal of RPH methodology is to improve hybrid models' reliability rather than accuracy using a new reliable-based weighting algorithm (RWA). The RWA instead of traditional accuracy-based weighting algorithms in which error measurements are minimized, the reliability of hybrid models is maximized to determine the exact optimum weights of individual models. The RWA computed the optimum weights of forecasts regarding minimizing performance changing of the hybrid model in the validation data set. The RPH model proposed two crucial concepts for the first time: (1) Bringing up reliability in hybridization procedure (2) Proposing a novel reliable-based weighting algorithm to maximize the generalization power of the hybrid model. The bi-component version of the RPH model is proposed in this paper using ARIMA and MLP models. The forecasting power of the proposed PRH constructed based on ARIMA and MLP models is verified using the benchmark data sets e.g. the closing of Standard and Poor's 500 indexes (S&P500), the closing of the Shenzhen Integrated Index (SZII), and the opening of the Dow Jones Industrial Average Index (DJIAI). The experimental results indicate that the forecasting performance of the RPH model is much better than traditional accuracy-based parallel hybrid models.

Modeling the infiltration rate of wastewater infiltration basins considering water quality parameters using different artificial neural network techniques

ABSTRACT Predicting the infiltration rate (IR) of treated wastewater (TWW) is essential in controlling clogging problems. Most researchers that predict the IR using neural network models considered the characteristics parameters of soil without considering those of TWW. Therefore, this study aims to develop a model for predicting the IR based on various combinations of TWW characteristics parameters (i.e. total suspended solids (TSS), biological oxygen demand (BOD), electric conductivity (EC), pH, total nitrogen (TN), total phosphorous (TP), and hydraulic loading rate (HLR)) as input parameters. Therefore, two different artificial neural network (ANN) architectures, multilayer perceptron model (MLP) and Elman neural network (ENN), were used to develop optimal model. The optimal model was selected through evaluating three stages: selecting the best division of data, selecting the best model, and deciding the best combination of input parameters based on several performance criteria. The study concluded that the first combination of inputs that include all the seven-parameter using MLP model associated with 90% division of data was the optimal model in predicting the IR depending on TWW characteristics parameters, achieving a promising result of 0.97 for the coefficient of determination, 0.97 for test regression, 0.012 for MSE with 32.4 of max relative percentage error. Abbreviations: IR: Infiltration Rate; TWW: Treated Wastewater; TSS: Total Suspended Solids; BOD: Biological Oxygen Demand; EC: Electric Conductivity; HC: Hydraulic Conductivity; TN: Total Nitrogen; TP: Total Phosphorous; HLR: Hydraulic Loading Rate; ANN: Artificial Neural Network; MLP: Multilayer Perceptron Model; ENN: Elman Neural Network; FFANN: Feedforward Artificial Neural Networks; R: Regression Values; SAR: Sodium Adsorption Ratio; DOC: Dissolved Organic Carbon; ANAMMOX: Anaerobic Ammonium Oxidation; CEC: Cation Exchange Capacity; BPNN: Back Propagation Neural Network; GRNN: General Regression Neural Networks; ELM: Extreme Learning Machine Neural Networks; TDNN: Time Delay Neural Network; TLRN: Time Lag Recurrent Network; NGWTP: North Gaza Wastewater Treatment Plant; MASL: Meters Above Sea Level; DNC: Dynamic Node Creation; PWA: Palestinian Water Authority; RBF: Radial Basis Function; ANFIS: Adaptive Neuro Fuzzy Inference System; BD: Bulk Density; RMSE: Root Mean Square Error; MAE: Mean Absolute Error; MSE: Mean Square Error; R 2: Determination Coefficient; LLR: Local Linear Regression; DLLR: Dynamic Linear Regression; MNN: Modular Neural Networks; RNN: Recurrent Neural Network; NARX: Nonlinear Autoregressive with Exogenous input network; WNN: Wavelet Neural Networks

Forecasting Water Levels in Krasnodar Krai Rivers with the Use of Machine Learning

The potential of construction of machine learning models was considered as applied to water level forecasting in mountain river reaches in Krasnodar Krai based on observation data on water levels at automated hydrological complexes of the Automated System of Flood Conditions Monitoring in Krasnodar Krai. The study objects were two mountain rivers in Krasnodar Krai―the Pshish and Mzymta. These rivers flow in different natural conditions and differ in their water regimes and the character of lateral inflow in the reaches under consideration. The study focused on three widely used machine learning architectures: regression model of decision trees M5P, gradient boosting of decision trees XGBoost, and artificial neural network based on multilayer perceptron. The forecast quality was evaluated for lead time from 1 to 20 h; variations for rivers with different water regimes and the potential of the examined models as applied to operational forecasting are discussed. The optimal lead time for the Pshish river was found to be 15–18 h (with S/σΔ varying within 0.38–0.39 for XGBoost model); the simulation quality for the Mzymta river is evaluated as good; however, the necessary forecast efficiency is not attained (at the lead time of 5 h, we have S/σΔ = 0.87 for MLP model). The obtained results allow the machine learning models to be regarded as acceptable for short-term hydrological forecasting based on high-frequency water level observation data.

PERBANDINGAN WAKTU EKSEKUSI PERAMALAN HARGA KOMODITAS PANGAN MENGGUNAKAN SPARKR DAN R STUDIO

The arrival of the big data era with characteristics such as large volumes of data makes the calculation of execution time a concern when carrying out data analytics processes, such as forecasting food commodity prices. This study aims to examine the effect of the big data framework through the use of sparkR. The test is carried out by varying several deep learning forecasting models, namely the multi-layer perceptron model and by using the price of one food commodity from 2018 to 2020. The results show that sparkR is significantly shorter its execution time when compared to R studio. The results of testing the influence of the MLP model also show that a model with two hidden layers with a maximum node of 13 nodes in hidden layers 1 and 2 produces the longest execution time compared to only using 1 hidden layer with 5 nodes or using two hidden layers with a number of nodes of 5 and 3.

Detection of DGA-Generated Domain Names with TF-IDF

Botnets often apply domain name generation algorithms (DGAs) to evade detection by generating large numbers of pseudo-random domain names of which only few are registered by cybercriminals. In this paper, we address how DGA-generated domain names can be detected by means of machine learning and deep learning. We first present an extensive literature review on recent prior work in which machine learning and deep learning have been applied for detecting DGA-generated domain names. We observe that a common methodology is still missing, and the use of different datasets causes that experimental results can hardly be compared. We next propose the use of TF-IDF to measure frequencies of the most relevant n-grams in domain names, and use these as features in learning algorithms. We perform experiments with various machine-learning and deep-learning models using TF-IDF features, of which a deep MLP model yields the best results. For comparison, we also apply an LSTM model with embedding layer to convert domain names from a sequence of characters into a vector representation. The performance of our LSTM and MLP models is rather similar, achieving 0.994 and 0.995 AUC, and average F1-scores of 0.907 and 0.891 respectively.

Deep machine learning-based power usage effectiveness prediction for sustainable cloud infrastructures

The expansion of online services, the advent of big data, and the development of Internet of Things (IoT) technology have led to an exponential growth in the number of data centers (DC). Within this new digital systems, DCs are the keystone. This poses major environmental problems through high energy consumption. The energy consumption growth of the DC’s systems are expected to account for 3.2% of global carbon emissions by 2025. This remarkable growth in the energy consumption of DCs represents today a major challenge for energy efficiency. To meet these challenges, Power Usage Effectiveness (PUE) can be used to measure and optimize DC energy efficiency. Thus, accurate PUE prediction is challenging. Moreover, the non-linearity of the different DCs subsystems interactions and their inter-dependencies make the prediction of PUE more difficult since it is affected by complex factors such as workload variation, in addition to weather conditions and humidity, etc.In this paper, we present three machine learning models, MLP, Resilient Backpropagation-based DNN and Attention-based LSTM, to predict PUE values. The performance of these models has been evaluated using two datasets gathered from two case studies of real DCs. For both DC cases, experimental results showed that the attention-based LSTM model outperforms resilient backpropagation-based DNN and MLP models in terms of prediction errors and PUE.

An adaptive fuzzy logic control of green tea fixation process based on image processing technology

In postharvest processing of green tea, fixing is the first and the most critical step for forming green tea's specific appearance and fragrance. In this study, green tea sample was firstly fixed at constant pot temperatures. The image information was captured to reflect colour changes. By observing the disappearance of the enzymatic activity, the fixation process was divided into the first and the last stage, where different concerns were emphasised on. After fixation, chemical components including enzymatic activity, tea polyphenols, amino acids and chlorophyll were analysed. The MLP, Grid-Search-SVR and GA-SVR models were constructed based on image information to predict chemical compositions. Results demonstrated GA-SVR could achieve superior performance than Grid-Search-SVR and MLP (1.9742>0.9167>0.7797 for average MSE, 0.3829< 0.5969<0.6557 for average R-Square, and 15.7132>8.8603> 8.5081 for average MAPE at first fixation stage; 0.3343>0.2552>0.2460 for MSE, 0.7393<0.8317<0.8658 for R-Square, and 5.2898 > 3.9612>3.8259 for MAPE at last fixation stage). An adaptive fuzzy logic control algorithm was designed to adjust the pot temperature during the fixation process. The pre-processed image information was fed into the controller to control the pot temperature continuously. With the intelligently controlled high temperature in the first stage, the enzymatic reaction could be suppressed and more polyphenols and chlorophyll were retained. In the last fixation stage, the temperature was automatically adjusted to low values to minimise oxidation, and more amino acids were formed. Consequently, the final product quality was significantly improved in terms of appearance, liquor colour, fragrance, taste, and residue colour, with the adaptive fuzzy logic controller.

Pemanfaatan Big Data dalam Monitoring Pola Aktivitas Aviasi di Indonesia

Abstract: Covid-19 which entered Indonesia in December 2019 has a significant impact on the aviation industry. According to BPS data for 2020, the aviation industry's contribution to Indonesia's GDP decreased from 1.21% to 0.28% in the second quarter of 2020. To overcome this setback, comprehensive monitoring by policy makers is needed. The use of big data in monitoring aviation industry activities can be an option. This study aims to analyze aviation activities using big data approach for monitoring basis. The data was collected by using web scraping method on one of the global aviation websites to obtain flight status data at 108 airports in Indonesia on April 2020 until June 2021. Other data used are google mobility index data, GDP data, and TPK. The analysis method used are descriptive analysis, correlation analysis and machine learning based time series modelling with ARNN, single layer ANN and MLP. The results show that the policy of restricting mobility has a significant effect on the productivity of aviation industry. Machine learning modeling shows that the MLP model is the best model for forecasting international aviation activity. In addition, it was found that the aviation industry has a strong correlation with the economy and tourism sector in Indonesia.

Prediction of spark ignition engine performance with bioethanol-gasoline mixes using a multilayer perception model

ABSTRACT: The current study examines the impact of bioethanol blends on spark-ignited engine performance using multilayer perception modeling. Waste pomegranate fruits (WPF) from a nearby fruit market are used to make bioethanol. After 72 hours, the fruit juice mixture yielded 1.1 ± 0.3 mLgm−1 ethanol. Each of four ethanol mixes was tested at different speeds to determine the engine's indicated and braking power, volumetric, thermal, and mechanical efficiency. The addition of ethanol increased volumetric efficiency by up to 25% and indicated power by up to 20%. In contrast, ethanol proportions showed thermal efficiency variations. In order to forecast performance parameters, a multilayer perception model with feed forward back propogation is used. 25% of the test data was used to validate the MLP model. The accuracy of designed network was checked by root mean square error, mean squared error and Mean Absolute Percentage Error and higher values of regression coefficient. The constructed MLP model predicted values that were highly accurate and with acceptable error. The results proved that the MLP model can be effectively implemented for predicting engine performance and hopeful prospects for waste pomegranate ethanol at commercial level.