Multi Linear Perceptron Research Articles

Prediction of Humidity using Multi Linear Perceptron and Support Vector Machine North Twenty-four Parganas , West Bengal

The ability to predict the weather is necessary for lifesaving. Weather prediction has important applications in transportation, agriculture, floods, and other natural phenomena. For weather forecasting to be accurate, air pressure prediction is essential. Among the methods available for Air Pressure prediction is multiple linear regression. To ascertain the relationship between one independent variable and one dependent variable The linear regression model is a very useful tool in statistics. An expansion of the linear regression model is multiple linear regression. To add variables to our experiment, we used MATLAB. Predicting air pressure is crucial to weather forecasting. We have selected Kolkata, or more precisely the Dum Dum Metropolitan area in North 24 Parganas, for the purpose of forecasting rainfall. Keyword: Humidity prediction, Multi Layer Perceptron Model, Support Vector Machine,Root Mean Square

Power transmission system’s fault location, detection, and classification: Pay close attention to transmission nodes

For transmission systems to operate safely and reliably, fault identification and classification are essential. However, power network physical architecture and data information cannot be fully utilized by conventional intelligent approaches. This study,therefore,presents a fault localization, detection, and classification model for transmission systems that concentrate on the key distribution nodes. The model makes use of a deep graph neural network with multi-scale attention and multi-linear perceptron block which accounts for the power network's structural composition during learning. The model's capacity to manage unusual data input and unidentified application situations is improved by the inclusion of multi-scale attention. Furthermore, it enables the model to precisely pinpoint fault areas by identifying patterns and connections among system parts, concentrating on specific areas or nodes. In addition, a multi-linear perceptron block is designed to enhance the capturing of amplitude information and increase comprehension. The efficiency and generalizability of the proposed model are improved by the implementation of a multi-task training approach for locating faults and their type. With the use of two IEEE 13-Bus systems and the PSS/E 23-Bus system, the proposed fault diagnosis model is tested. Examining various setups for fault analysis allows for a more thorough evaluation of the model's ability to generalize and disturbance resilience. Experimental findings show that the proposed model outperforms existing cutting-edge techniques in terms of efficacy with a balanced accuracy of 0.8204 for classification, 0.556 for localization, and a Macro MAE of 38.780 for detection.

Planning for a Crisis: Predicting Anxiety in a Population During COVID-19 Using Machine Learning.

COVID-19 impact on population mental health has been reported around the world. Statistics Canada has conducted a survey among Canadian population to gauge mental health challenges they experienced, specifically in terms of anxiety. We create a machine learning model to predict anxiety symptoms as measured by the General Anxiety Scale among the sample of 45,989 respondents to the survey. Eight algorithms including Logistic Regression, Random Forest, Naive Bayes, K Nearest Neighbours, Adaptive boost, Multi linear perceptron, XGBoost and LightBoost. LightBoost provided the highest performing model AUC score (AUC=87.45%). In addition, the features "perception of mental health compared to before physical distancing", "perceived life stress", and "perceived mental health" were found to be the most important three features to predict anxiety. A limitation of this study is that the sample is not representative of the Canadian population. Preparing for virtual care interventions during a crisis need to take into considerations these factors.

Prediction of air quality using vertical atmospheric condition and developing hybrid models

Most metropolitan areas experience increasing health and environmental pressure from air pollutants. Air pollutant concentrations are mostly influenced by meteorological factors, pollutant sources, and topography. The vertical atmospheric conditions can affect the surface air pollution concentration. In this paper, to evaluate the relationship between the vertical meteorological characteristics and air pollution concentrations (CO, O3, PM2.5, PM10 and SO2) four different models including multi-linear regression (MLR), multi-linear perceptron (MLP), generalized regression neural network (GRNN), and adaptive Neuro-Fuzzy inference system (ANFIS) were developed. The vertical temperature difference, relative humidity, U and V wind components in different altitudes were extracted from the operational archive of the European Center for Medium Range Weather Forecast (ECMWF 2019) from March 2011 to December 2017. The variance inflation factor (VIF) and tolerance tests were utilized to remove the independent variables, which made multi-collinearity. Results showed that among the studied air pollutant variables, variation of PM10 concentration was more influenced by vertical meteorological characteristics obtained using the GRNN model with R2 = 0.960, root Mean square error (RMSE) = 0.019 and mean absolute error (MAE) = 0.005 in tearing phase and R2 = 0.940, RMSE = 0.054 and MAE = 0.019 in testing phase. The results of ANFIS model for PM2.5 concentration were acquired highest among the other air pollutant variables in tearing phase (R2 = 0.819, RMSE = 0.036 and MAE = 0.025) and in testing phase (R2 = 0.960, RMSE = 0.001 and MAE = 0.001). The results illustrated that GRNN and ANFIS models outperform other models for air pollutants prediction using vertical atmospheric conditions in the Sanandaj, Iran.

Comparative Study of Experimental and Modeling of Fly Ash-Based Concrete.

The application of supplementary cementitious materials (SCMs) in concrete has been reported as the sustainable approach toward the appropriate development. This research aims to compare the result of compressive strength (C-S) obtained from the experimental method and results estimated by employing the various modeling techniques for the fly-ash-based concrete. Although this study covers two aspects, an experimental approach and modeling techniques for predictions, the emphasis of this research is on the application of modeling methods. The physical and chemical properties of the cement and fly ash, water absorption and specific gravity of the aggregate used, surface area of the cement, and gradation of the aggregate were analyzed in the laboratory. The four predictive machine learning (PML) algorithms, such as decision tree (DT), multi-linear perceptron (MLP), random forest (RF), and bagging regressor (BR), were investigated to anticipate the C-S of concrete. Results reveal that the RF model was observed more exact in investigating the C-S of concrete containing fly ash (FA), as opposed to other employed PML techniques. The high R2 value (0.96) for the RF model indicates the high precision level for forecasting the required output as compared to DT, MLP, and BR model R2 results equal 0.88, 0.90, and 0.93, respectively. The statistical results and cross-validation (C-V) method also confirm the high predictive accuracy of the RF model. The highest contribution level of the cement towards the prediction was also reported in the sensitivity analysis and showed a 31.24% contribution. These PML methods can be effectively employed to anticipate the mechanical properties of concretes.

Accelerated design of architectured ceramics with tunable thermal resistance via a hybrid machine learning and finite element approach

Topologically interlocked architectures can transform brittle ceramics into tougher materials, while making the material design procedure a cumbersome task since modeling the whole architectural design space is not efficient and, to a degree, is not viable. We propose an approach to design architectured ceramics using machine learning (ML), trained by finite element analysis data and together with a self-learning algorithm, to discover high-performance architectured ceramics in thermomechanical environments. First, topologically interlocked panels are parametrically generated. Then, a limited number of designed architectured ceramics subjected to a thermal load is studied. Finally, the multilinear perceptron is employed to train the ML model in order to predict the thermomechanical performance of architectured panels with varied interlocking angles and number of blocks. The developed feed-forward artificial neural network framework can boost the architectured ceramic design efficiency and open up new avenues for controllability of the functionality for various high-temperature applications. This study demonstrates that the architectured ceramic panels with the ML-assisted engineered patterns show improvement up to 30% in frictional energy dissipation and 7% in the sliding distance of the tiles and 80% reduction in the strain energy, leading to a higher safety factor and the structural failure delay compared to the plain ceramics.

Estimated Empirical Correlations Between Shear Wave Velocity and SPT-N Value for Indore City Using NLR and ANN

In this paper, an attempt has been made to propose a generalized correlation between shear wave velocity (Vs) and SPT-N values for all soil types for generalized depth using the concepts of regression. Around 40 correlations have been compiled and applied for estimating the shear wave velocity (Vs) correlation for the region and also to address the uncertainty issue. The generated correlation is then used for the computation of Vs for one-dimensional (1D) ground response analysis at two different site locations in Indore region. 1D ground response analysis is performed using DEEPSOILv6.1. Soil profiles at site taken as input for analysis were collected from 245 boreholes at 26 different locations in the Madhya Pradesh region (one of the central states in India), and it can be concluded that Vs–N correlations estimated after reducing the errors applying the multilinear perceptron and generalized regression neural network models using MATLAB coding gave better results over the linear regression analysis applied for the site-specific ground response analysis.

Spatial Multi-Layer Perceptron Model for Predicting Dengue Fever Outbreaks in Surabaya

Dengue fever (DF) is a tropical disease spread by mosquitoes of the Aedes type. Therefore, a DF outbreak needs to be predicted to minimize the spread and death caused by it. The spread of dengue fever is a spatial problem. In this paper, we adopted the Multi Linear Perceptron (MLP) to solve the spatial problem, and we called it a spatial multi-layer perceptron model (Spatial MLP). In this proposed model, we consider two types of input neurons in the Spatial MLP, a region and the neighbourhood of that region. The spatial inputs dynamically change to the region. Additionally, the neighbourhood numbers of a region are also varied. So, the spatial inputs are changed in terms of the number of inputs and the neighbourhoods. As a result, the proposed model is outperformed the traditional MLP since it can adapt to the neighbourhoods. We can conclude the spatial MLP model can manage the information and predict the dengue fever outbreak in Surabaya

Leachate generation rate modeling using artificial intelligence algorithms aided by input optimization method for an MSW landfill.

Leachate is one of the main surface water pollution sources in Selangor State (SS), Malaysia. The prediction of leachate amounts is elementary in sustainable waste management and leachate treatment processes, before discharging to surrounding environment. In developing countries, the accurate evaluation of leachate generation rates has often considered a challenge due to the lack of reliable data and high measurement costs. Leachate generation is related to several factors, including meteorological data, waste generation rates, and landfill design conditions. The high variations in these factors lead to complicating leachate modeling processes. This study aims at identifying the key elements contributing to leachate production and developing various AI-based models to predict leachate generation rates. These models included Artificial Neural Network (ANN)-Multi-linear perceptron (MLP) with single and double hidden layers, and support vector machine (SVM) regression time series algorithms. Various performance measures were applied to evaluate the developed model's accuracy. In this study, input optimization process showed that three inputs were acceptable for modeling the leachate generation rates, namely dumped waste quantity, rainfall level, and emanated gases. The initial performance analysis showed that ANN-MLP2 model-which applies two hidden layers-achieved the best performance, then followed by ANN-MLP1 model-which applies one hidden layer and three inputs-while SVM model gave the lowest performance. Ranges and frequency of relative error (RE%) also demonstrate that ANN-MLP models outperformed SVM models. Furthermore, low and peak flow criterion (LFC and PFC) assessment of leachate inflow values in ANN-MLP model with two hidden layers made more accurate values than other models. Since minimizing data collection and processing efforts as well as minimizing modeling complexity are critical in the hydrological modeling process, the applied input optimization process and the developed models in this study were able to provide a good performance in the modeling of leachate generation efficiently.

Estimation of rock uniaxial compressive strength for an Iranian carbonate oil reservoir: Modeling vs. artificial neural network application

Estimation of rock mechanic parameters is an important issue in reservoir management. Uniaxial compressive strength (UCS) and elastic modulus are the most important factors in determining the rock mechanic parameters in petroleum engineering studies. Accessibility to the parameters in fields such as designing fracture, analyzing of wellbore stability and drilling programming are very useful. The most accurate method to assign the aforementioned parameters is measuring these parameters in a laboratory. Laboratory determination of these parameters is problematic work due to technology issues, lack of laboratory equipment and coring problems in oil and gas wells, so indirect estimation of these parameters is required. Using well log data is the cheapest and most available approach in order to indirectly estimate these parameters. In this investigation, different models including multiple linear regression (MLR) and artificial neural network (ANN) (i.e., multi linear perceptron (MLP) and radial basis function (RBF)) were utilized for prediction of UCS via the three parameters of porosity, density and water saturation. These data were obtained from analysis of sonic, neutron, gamma ray and electric logs. The best results were obtained from a 3-15-1 MLP network which included one hidden layer and 15 neurons from the hidden layer using the trial and error method, and a 3-17-1 RBF which included 17 hidden neurons and a spread ó of 1.6. The core data from one of the carbonate Iranian oil fields (Asmari reservoir) were utilized for training, validation and testing of the networks, and correlation coefficients of 0.68, 0.90 and 0.83 were obtained for MLR, MLP and RBF, respectively.

Predicting kinetic triplets using a 1d convolutional neural network

In the past few years, methods of deep learning approaches such as convolutional neural networks have demonstrated their great power in tasks that are usually difficult, inefficient or expensive if conducted by human labor. Though these tools are very successful in the field of computer vision and are spreading soon in other fields, few papers have reported their uses in thermal analysis. This paper constructs a novel 1-dimensional convolutional neural network that is generally applicable for predicting kinetic parameters during pyrolysis. The proposed network makes efficient predictions of parameters in a unified pass instead of dealing with them separately. When compared with some classical methods including the commonly used Kissinger – Akahira – Sunose(KAS) method, Flynn-Wall-Ozawa(FWO) method and a multi-linear perceptron type artificial neural network, it demonstrates promising performance with high prediction accuracy and strong robustness to input noises.

A novel estimation method for capillary pressure curves based on routine core analysis data using artificial neural networks optimized by Cuckoo algorithm – A case study

Capillary pressure is one of the most important parameters affecting fluids distribution in a reservoir rock and is an essential input parameter for reservoir simulation. Measurement of capillary pressure data, in the context of special core analysis (SCAL) is a time and cost consuming process that does not often lead to accurate and reliable results. Routine core analysis (RCAL) data, on the other hand, can be obtained by simple, accurate, and cost-effective procedures. In this paper, the idea of using RCAL measurements to predict SCAL data (more specifically capillary pressure data) using Artificial Neural Network (ANN) approach is presented. An ANN with Multi-Linear Perceptron structure and feed-forward propagation was used to predict capillary pressure curves for a target reservoir under study. The ANN model was then optimized by Cuckoo optimization algorithm (COA). The ANN-COA model was used for 30 measurements, composed of both drainage and imbibition data points obtained from 15 core samples using centrifugation method. Out of this databank, 16 measurements were used for training and the remaining 14 measurements were used as the testing dataset. It was obtained that the optimized model shows a profound predicting performance based on the excellent value of coefficient of determination for predicted versus measured capillary pressure data.

A comparative analysis among computational intelligence techniques for dissolved oxygen prediction in Delaware River

Most of the water quality models previously developed and used in dissolved oxygen (DO) prediction are complex. Moreover, reliable data available to develop/calibrate new DO models is scarce. Therefore, there is a need to study and develop models that can handle easily measurable parameters of a particular site, even with short length. In recent decades, computational intelligence techniques, as effective approaches for predicting complicated and significant indicator of the state of aquatic ecosystems such as DO, have created a great change in predictions. In this study, three different AI methods comprising: (1) two types of artificial neural networks (ANN) namely multi linear perceptron (MLP) and radial based function (RBF); (2) an advancement of genetic programming namely linear genetic programming (LGP); and (3) a support vector machine (SVM) technique were used for DO prediction in Delaware River located at Trenton, USA. For evaluating the performance of the proposed models, root mean square error (RMSE), Nash–Sutcliffe efficiency coefficient (NS), mean absolute relative error (MARE) and, correlation coefficient statistics (R) were used to choose the best predictive model. The comparison of estimation accuracies of various intelligence models illustrated that the SVM was able to develop the most accurate model in DO estimation in comparison to other models. Also, it was found that the LGP model performs better than the both ANNs models. For example, the determination coefficient was 0.99 for the best SVM model, while it was 0.96, 0.91 and 0.81 for the best LGP, MLP and RBF models, respectively. In general, the results indicated that an SVM model could be employed satisfactorily in DO estimation.

Prediction of free flowing porosity and permeability based on conventional well logging data using artificial neural networks optimized by Imperialist competitive algorithm – A case study in the South Pars gas field

Nuclear Magnetic Resonance (NMR) logging is one of the most effective tools in determining permeability and porosity of a formation layer, so it is a reliable method to characterize a reservoir. Since NMR logging is not applicable in certain circumstances, its parameters are usually correlated with conventional logging parameters. In this research, an Artificial Neural Network (ANN) with Multi Linear Perceptron (MLP) structure and a feed-forward back-propagation algorithm is employed to predict the NMR logging parameters from their conventional counterparts. The ANN is optimized using the Imperialist Competitive Algorithm (ICA). The ANN-ICA model is applied to two data sets measured in two separate gas wells of south Pars gas field. The data obtained from one well are used as the training data set and the other well data are utilized to test the proposed model. Finally, a sensitivity analysis (based on the parameters of the ICA algorithm and the number of neurons in the ANN) is applied to explore their effects on the ANN's performance. According to the results, the accuracy and efficiency of the proposed model are more desirable than the traditional neural network. It is found that the optimization method is not sensitive to the ICA parameters.

Flood Prediction Model using Artificial Neural Network

This paper presents a Flood Prediction Model (FPM) to predict flood in rivers using Artificial Neural Network (ANN) approach. This model predicts river water level from rainfall and present river water level data. Though numbers of factors are responsible for changes in water level, only two of them are considered. Flood prediction problem is a non-linear problem and to solve this nonlinear problem, ANN approach is used. Multi Linear Perceptron (MLP) based ANN’s Feed Forward (FF) and Back Propagation (BP) algorithm is used to predict flood. Statistical analysis shows that data fit well in the model. We present our simulation results for the predicted water level compared to the actual water level. Results show that our model successfully predicts the flood water level 24 hours ahead of time.

Soft-Computing Techniques Applied to Short-Term Traffic Flow Forecasting

Multi Linear Perceptron (MLP) neural networks, Radial Basis Function (RBF) neural networks, and Fuzzy Logic (FL) were used as soft-computing (or artificial intelligent) modelling techniques to come to short-term forecasts of traffic flow. The field data used for modelling was collected through single loop induction detectors on freeways 405 and 22 in Orange County, California. The data consisted of 30-s time bins of traffic flow [vehicles/3Os], occupancy [seconds/3Os], and reliability indicators (value 0-7) that were transformed into 5-min time bins. The paper concludes that the MLP and the RBF(2) - with 1 output - method outperform the FL and the RBF(1)-with 2 outputs method.

Multilinear perceptron convergence theorem.

An adaptive perceptron with multilinear couplings is introduced. While an adaptive perceptron exhibits severe shortcomings if it is applied to complex tasks, this is not so for the adaptive multilinear perceptron.