Usage Of Artificial Neural Networks Research Articles

Optimization of biodiesel production parameters for hybrid oil using RSM and ANN technique and its effect on engine performance, combustion, and emission characteristics

The increased need for renewable energy sources and growing concerns about environmental pollution has driven the need for alternative fuels (particularly biodiesel) in the transportation industry. The most used technique for producing biodiesel is transesterification, which involves the oil reacting with alcohol in the presence of a catalyst. This study looks at the usage of artificial neural network (ANN) and response surface methodology (RSM) to optimize biodiesel synthesis factors for a hybrid oil feedstock (30% cottonseed and 70% spirulina microalgae oil). The parameters that were optimized were the methanol/oil ratio, reaction time, and catalyst concentration. Cottonseed oil was combined with spirulina microalgae oil to minimize its higher free fatty acid content to less than 1% and prevent soap formation during the transesterification process. The optimal biodiesel production was 94.37%, with 106.4 minutes of reaction time, 1.612% catalyst loading, and a methanol/oil ratio of 20:1. The optimized findings, when confirmed with experiments, gave a biodiesel yield of 91.03% with an error of 3.6%. To provide vital insights into the potential environmental benefits of using this alternative fuel, the study further investigates how the optimized biodiesel blend influences engine performance and emission characteristics. Testing was done at 1500 RPM and 17.5 CR for maximum loading conditions, diesel, HBD20, and HBD fuel produced 0.2746, 0.2805, and 0.288 kg/kWh of specific fuel consumption (SFC), respectively. The CO2 emissions of HBD and HBD20 were 2.49% and 8.30% lower, respectively, than pure diesel. NOx emissions increased by 14% and 18.3%. The highest cylinder pressure was 66.87 at 363 °C.

On the Usage of Artificial Neural Networks for the Determination of Optimal Wind Farms Allocation

Worldwide energy demand is constantly increasing. This fact, in combination with the ever growing need to reduce the energy production footprint on the environment, has led to the adoption of cleaner and more sustainable forms of energy production. Renewable Energy Sources (RES) are constantly developing in an effort to increase their conversion efficiency and improve their life cycle. However, not all types of RES are accepted by the general public. Wind Turbines (WTs) are considered by many researchers as the least acceptable type of RES. This is mostly because of how their installation alters the surrounding landscape, produces noise and puts birds in danger when they happen to fly over the installation area. This paper aims to apply a methodology which, by using Rational Basis Function Neural Networks (RBFNN), is capable of investigating the criteria used for the installation locations of WTs in a transparent way. The results from the Neural Network (NN) will be combined with protected areas and the Land Fragmentation Index (LFI), in order to determine possible new installation locations with increased social acceptance and, at the same time, increased energy production. A case study of the proposed methodology has been implemented for the entire Greek territory, which is considered one of the most suitable areas for the installation of wind farms due to its particular geomorphology.

A Scoping Review on the Use of Artificial Neural Networks (ANNs) in Decision Adoption Systems (DAS) for Psychological Data Interpretation

In the past decade, there has been a surge of interest in the potential of artificial neural networks (ANNs) to enhance decision-making processes in a variety of domains, including decision adoption systems (DAS). This scoping review focuses on the utilization of ANNs in DAS for the interpretation of psychological data. The major goal of this scoping review is to determine the current status of research on the usage of ANNs in DAS for psychological data interpretation and highlight the advantages and limitations of using ANNs in this context. Through a comprehensive search of relevant databases, a range of studies were identified that have employed ANNs in DAS for psychological data interpretation. These studies demonstrate the potential of ANNs to improve decision-making processes in psychological data interpretation, resulting in more accurate diagnoses.. The scoping review presents information on the actual status of research on the usage of ANNs in DAS for psychological data interpretation, offering a comprehensive understanding of the potential of ANNs in enhancing decision-making processes in this context. As such, the findings of this review have significant implications for future research on ANNs in DAS for psychological data interpretation, which may result in the development of more effective decision-making tools for this purpose.

Surrogate-assisted analysis of the parameter configuration landscape for meta-heuristic optimisation

Meta-heuristics can provide high-quality solutions to challenging problems in a reasonable amount of time, but are highly sensitive to the values assigned to their control parameters. The parameter configuration landscape (PCL) offers insight into the characteristics associated with optimisation of the parameter configuration of a meta-heuristic, but is poorly understood for most meta-heuristics. Further exacerbating this issue, determining the characteristics of the PCL is an extremely computationally expensive process. This study proposes the usage of artificial neural networks (ANNs) as surrogate models to greatly reduce the computational burden associated with characterising the PCL. Notably, this study represents the first usage of surrogate models in PCL research. Furthermore, this study presents a characterisation of the PCLs for both particle swarm optimization (PSO) and differential evolution (DE) employing ANN surrogate models, using five well-established fitness landscape analysis (FLA) metrics, and finds that the common assumption of correlation between the fitness and distance of control parameter settings is not strictly met. Overall, the training and usage of the surrogate models leads to a 99.86% reduction in the number of algorithm executions required to attain the PCL samples used in the characterisation.

Review of artificial neural networks-contribution methods integrated with structural equation modeling and multi-criteria decision analysis for selection customization

This study presents a review of literature on the usage of artificial neural networks (ANNs) architecture contribution method and structural equation modeling (SEM), and proposes a new selection process in the context of algorithm -based SEM-ANNs schemes. This study enriches academic literature by providing a review of all the main aspects of customization in ANNs and contribution methods in combination with SEM. Academic databases are examined for exhibition findings, yielding 253 papers published between 2016 and 2022. The retrieved papers are categorized according to inclusion criteria, and the final set of 73 articles are discussed based on two directions, namely, ‘Sector-based’ and ‘Algorithm-based’ as a new representation of taxonomy research. A state-of-the-art bibliographic analysis is presented. This review also identifies modern challenges and open issues in terms of multiple evaluation criteria, importance criteria, and data variations related to the selection of customizations in ANNs and contribution methods combined with SEM in different industrial cases. Several issues fall under multicriteria decision making for handling complexity problems in different ANNs and contribution methods. Thus, this study also presents a research proposal and recommends a solution based on a three-phase methodology for handling the selection and overcoming the identified issues, subsequently completing a strategic guideline solution.

Machine Learning Approach for House Price Prediction

In our ecosystem, real estate is clearly a distinct industry. Predicting house prices, significant housing characteristics, and many other things is made a lot easier by the capacity to extract data from raw data and extract essential information. Daily fluctuations in housing costs are still present, and they occasionally rise without regard to calculations. According to research, changes in property prices frequently have an impact on both homeowners and the real estate market.
 To analyze the key elements and the best predictive models for home prices, literature research is conducted. The analyses' findings supported the usage of artificial neural networks, support vector regression, and linear regression as the most effective modeling techniques. Our results also imply that real estate agents and geography play important roles in determining property prices. Finding the most crucial factors affecting housing prices and identifying the best machine learning model to utilize for this research would both be greatly aided by this study, especially for housing developers and researchers.

A new data-driven probabilistic fatigue life prediction framework informed by experiments and multiscale simulation

Traditional probabilistic fatigue life test requires long time, a large number of samples and high cost due to dispersion, randomness and complexity. A new data-driven probabilistic fatigue life prediction framework informed by experiments and multiscale simulation, was proposed and applied to a Ni-based superalloy FGH96. It exhibits the advantages of less tests and fully consideration of the effects of microstructure dispersion on fatigue crack initiation, small fatigue crack (SFC) and long fatigue crack (LFC) propagation. The fatigue crack initiation life was accurately predicted by a stored energy model of persistent slip band (PSB) based on microscale crystal plasticity (CP) theory. The usage of artificial neural network (ANN) leads to the capability of rapidly obtaining CP parameters through the macroscopic Ramberg-Osgood (RO) relationship. Bayesian neural networks (BNN) was trained to predict probabilistic fatigue crack initiation life, SFC and LFC growth rates based on results obtained from CP modellings and carefully designed experiments. With BNN as a probabilistic distribution generator, a Monte Carlo (MCs) model is developed to capture the complete fatigue failure processes, including the crack initiation, SFC and LFC propagation. The total fatigue life and the proportions of life at different stages of superalloy FGH96 were predicted by MCs, which agree well with the experimental data. This work provides a new pathway for structural safety assessment and damage tolerance design.

Application of machine learning technologies in biodiesel production process—A review

The search for renewable, affordable, sustainable, and ecologically benign fuels to substitute fossil-based diesel fuels has led to increased traction in the search for biodiesel production and utilization in recent times. Biodiesel, a form of liquid biofuel, has been found to alleviate environmental degradation, enhance engine performance, and reduce emissions of toxic gases in transportation and other internal combustion engines. However, biodiesel production processes have been dogged with various challenges and complexities which have limited its expected progression. The introduction of data-based technologies is one of the remedies aimed at deescalating the challenges associated with biodiesel synthesis. In this study, the application of machine learning (ML) –based technologies including artificial neural network (ANN), response surface methodology (RSM), adaptive network-based fuzzy inference system (ANFIS), etc. As tools for the prediction, modeling, and optimization of the biodiesel production process was interrogated based on the outcomes of previous studies in the research domain. Specifically, we review the influence of input variables like alcohol: oil molar ratio, catalyst concentration, reaction temperature, residence time, and agitation speed on the biodiesel yield (output variable). The outcome of this investigation shows that the usage of ANN, RSM, ANFIS, and other machine learning technologies raised biodiesel yield to between 84% and 98% while the statistical verification shows that the Pearson correlation coefficient and coefficient of determination are close to 1. Going forward, more targeted and collaborative research is needed to escalate the use of innovative technologies for the entire biodiesel value chain to enhance production efficiency, ensure economic feasibility, and promote sustainability.

Reconfigurable Architecture for Noise Cancellation in Acoustic Environment Using Single Multiply Accumulate Adaline Filter

The creation of multiple applications with a higher level of complexity has been made possible by the usage of artificial neural networks (ANNs). In this research, an efficient flexible finite impulse response (FIR) filter structure called ADALINE (adaptive linear element) that makes use of a MAC (multiply accumulate) core is proposed. The least mean square (LMS) and recursive least square (RLS) algorithms are the most often used methods for maximizing filter coefficients. Despite outperforming the LMS, the RLS approach has not been favored for real-time applications due to its higher design arithmetic complexity. To achieve less computation, the fundamental filter has utilized an LMS-based tapping delay line filter, which is practically a workable option for an adaptive filtering algorithm. To discover the undiscovered system, the adjustable coefficient filters have been developed in the suggested work utilizing an optimal LMS approach. The 10-tap filter being considered here has been analyzed and synthesized utilizing field programmable gate array (FPGA) devices and programming in hardware description language. In terms of how well the resources were used, the placement and postrouting design performed well. If the implemented filter architecture is compared with the existing filter architecture, it reveals a 25% decrease in resources from the existing one and an increase in clock frequency of roughly 20%.

Artificial-Neural-Network-Assisted Sensor Clustering for Robust Communication Network in IoT-Based Electricity Transmission Line Monitoring

As an Internet of Things (IoT) application in the smart grid, dynamic thermal rating (DTR) requires real-time measurement of conductor temperature from field sensors that are installed at remote transmission lines. For such IoT-based transmission line monitoring, we need a robust communication network. This article proposes to group sensors with similar measurement characteristics into a cluster such that each member can accurately represent the entire cluster. Then, communication robustness can be achieved by establishing multiple routes to the control center, where each route may originate from a different member in the cluster. First, we formulate a global constrained optimization for sensor clustering. We use the optimization solutions to train a set of artificial neural networks (ANNs), where each ANN is deployed to make a local decision at one sensor. Specifically, we propose the novel usage of ANN as a tool to transfer knowledge from a global decision maker to a set of local decision makers. Evaluation results show that there remains a noticeable knowledge gap between global and local decision makers, where in average, the global decision maker and an ANN make an identical decision in only about 70% of the times. Despite this less than ideal success probability, the number of clusters produced by the ANN-assisted local scheme is only 1.9 more than that by the global scheme.

Identification of Factors Affecting Environmental Contamination Represented by Post-Hatching Eggshells of a Common Colonial Waterbird with Usage of Artificial Neural Networks.

Artificial Neural Networks are used to find the influence of habitat types on the quality of the environment expressed by the concentrations of toxic and harmful elements in avian tissue. The main habitat types were described according to the Corine Land Cover CLC2012 model. Eggs of free-living species of a colonial waterbird, the grey heron Ardea cinerea, were used as a biological data storing media for biomonitoring. For modeling purposes, pollution indices expressing the sum of the concentration of harmful and toxic elements (multi-contamination rank index) and indices for single elements were created. In the case of all the examined indices apart from Cd, the generated topologies were a multi-layer perceptron (MLP) with 1 hidden layer. Interestingly, in the case of Cd, the generated optimal topology was a network with a radial basis function (RBF). The data analysis showed that the increase in environmental pollution was mainly influenced by human industrial activity. The increase in Hg, Cd, and Pb content correlated mainly with the increase in the areas characterized by human activity (industrial, commercial, and transport units) in the vicinity of a grey heron breeding colony. The decrease in the above elements was conditioned by relative areas of farmland and inland waters. Pollution with Fe, Mn, Zn, and As was associated mainly with areas affected by industrial activities. As the location variable did not affect the quality of the obtained networks, it was removed from the models making them more universal.

Implementation of ANN and GARCH for Stock Price Forecasting

For simulating intricate goalfunctions, neural networks are a technology that is employed in artificial intelligence. The usage of artificial neural networks is becoming more popular.(ANNs) to certain sorts of tasks, for example learning to comprehend complicated sensor data collected in the real world, is one of the most effective methods of learning approaches available. The usage of time series models in financial time series prediction has grown significantly over the past decade, and their relevance in this area continues to expand. To be more specific, the goal of this research is to determine whether neural networks have the ability to predict financial time series in general, or, more specifically, whether they have the ability to predict future patterns i The stock market in the United States is characterized by the European Union, and Brazil, among other things. They are compared to a well-known forecasting approach, generalized autoregressive conditional heteroskedasticity, in this research, and their accuracy is shown to be superior (GARCH). Aside from that, the optimal network design for each data sample is developed for each data sample. According to this article, ANNs are capable of forecasting the stock markets under examination, and their resilience may be increased by varying the network topology utilized to construct them. Aside from that, the results of this research demonstrate that ANNs outperform GARCH models in terms of efficiency of statistical performance.

Using Neural Networks for Bicycle Route Planning

This paper presents the usage of artificial neural networks (NNs) in bicycle route planning. This research aimed to check the possibility of NNs to transfer human expertise in bicycle route design by training the NN on an already established set of bicycle routes and then using the trained NN to design the routes on the novel area. We created two NNs capable of choosing the best route among the given road network by training them on two different areas. The bicycle routes produced by NNs were the same at best and had 75% overlap at the worst compared to those produced by human experts. Furthermore, the mean square error for all of our NN models varied from 0.015 and 0.081. We compared this new approach to the traditional multicriteria GIS (geographic information system) analysis (MA) that requires the human expert to define the bicycle route selection criteria. The benefit of using NN over the MA was that the NN directly transfers the human expertise to a model. In contrast, the MA needs the expert to select multiple criteria and adjust their weights carefully.

Predicting rice diseases across diverse agro-meteorological conditions using an artificial intelligence approach.

With the aid of a plant disease forecasting model, the emergence of plant diseases in a given region can be predicted ahead of time. This makes it easier to take proactive steps to reduce losses before they occur. The proposed model attempts to find an association between agrometeorological parameters and the occurrence of the four types of rice diseases. Rice is the staple food of people in Maharashtra. The four major diseases that occur on rice crops are focused on this paper (namely Rice Blast, False Smut, Bacterial Blight and Brown Spot) as these diseases spread rapidly and lead to economic loss. This research paper demonstrates the usage of artificial neural network (ANN) to detect, classify and predict the occurrence of rice diseases based on diverse agro-meteorological conditions. The results were carried out on two cases of dataset split that is 70–30% and 80–20%. The various types of activation function (AF) such as sigmoid, tanH, ReLU and softmax are implemented and compared based on various evaluation metrics such as overall Accuracy, Precision, Recall and F1 score. It can be concluded that the softmax AF applied to 70–30% split of dataset gives the highest accuracy of 92.15% in rice disease prediction.

Single and Multi-label Fault Classification in rotors from unprocessed multi-sensor data through deep and parallel CNN architectures

An attempt has been made in this study to address two issues related to fault classification in machinery. The first concerns the need of pre-processing raw data collected by sensors and the other is identification in cases where more than one fault exist simultaneously, i.e. where multi-label faults are present. We describe a Convolution Neural Network (CNN) based Deep architecture for classification of Single faults from raw time domain data and a similar but shallower Parallel Multiple Binary Classifier Network for Multi-label Fault Classification. Data from previously conducted experiments on a Rotor-Bearing Fault Simulator are used. In the case of Single-Label fault classification, Support Vector Machines (SVMs), Clustering, Artificial Neural Networks (ANNs) and other algorithms have been used in the past . These procedures require the raw time-domain data collected by sensors, to be first processed and handcrafted into parameters like Fast Fourier Transform (FFT) coefficients, Statistical Moments, etc. before being fed as inputs. Usage of ANN with raw time domain data is inadequate as it suffers from the vanishing gradient problem. We propose a Deep Learning Multi-channel Convolutional Neural Network (McCNN) architecture here, which eliminates this problem and employs the RGB image analogy for channelizing raw time-domain vibration signals from various sub-systems of the rotor-bearing installation. It is shown that this architecture effectively works on raw time-domain data and recognizes all kinds of Single-Label Faults. For Multi-Label faults also, which generally get classified as erroneous Single-Label type through routine codes, the parallel architecture is demonstrated to give good results.

Hydrological Models and Artificial Neural Networks (ANNs) to Simulate Streamflow in a Tropical Catchment of Sri Lanka

Accurate streamflow estimations are essential for planning and decision-making of many development activities related to water resources. Hydrological modelling is a frequently adopted and a matured technique to simulate streamflow compared to the data driven models such as artificial neural networks (ANNs). In addition, usage of ANNs is minimum to simulate streamflow in the context of Sri Lanka. Therefore, this study presents an intercomparison between streamflow estimations from conventional hydrological modelling and ANN analysis for Seethawaka River Basin located in the upstream part of the Kelani River Basin, Sri Lanka. The hydrological model was developed using the Hydrologic Engineering Centre-Hydrologic Modelling System (HEC-HMS), while the data-driven ANN model was developed in MATLAB. The rainfall and streamflows’ data for 2003–2010 period have been used. The simulations by HEC-HMS were performed by four types of input rainfall data configurations, including observed rainfall data sets and three satellite-based precipitation products (SbPPs), namely, PERSIANN, PERSIANN-CCS, and PERSIANN-CDR. The ANN model was trained using three well-known training algorithms, namely, Levenberg–Marquadt (LM), Bayesian regularization (BR), and scaled conjugate gradient (SCG). Results revealed that the simulated hydrological model based on observed rainfall outperformed those of based on remotely sensed SbPPs. BR algorithm-based ANN algorithm was found to be superior among the data-driven models in the context of ANN model simulations. However, none of the above developed models were able to capture several peak discharges recorded in the Seethawaka River. The results of this study indicate that ANN models can be used to simulate streamflow to an acceptable level, despite presence of intensive spatial and temporal data sets, which are often required for hydrologic software. Hence, the results of the current study provide valuable feedback for water resources’ planners in the developing region which lack multiple data sets for hydrologic software.

Fatigue Life Evaluation of Delaminated GFRP Laminates Using Artificial Neural Networks

Delamination between any two plies is an important damage commonly seen in composite structures. It may initiate and grow in the composite laminates for different loading conditions, and it may finally lead to failure of the component under the cyclic loading. Therefore, fatigue life prediction in these structures is important to avoid the effects of delaminations in economic and safety considerations. The usage of artificial neural network (ANN) in estimating fatigue failure in composites with delaminations would be high. In this work, experimental fatigue data were obtained for glass fiber-reinforced composite beams with and without delaminations. The experimental results were used to train and test the neural network. Finally, ANN was found to be accurate tool for fatigue life estimation for composite materials with delaminations as it produces reasonably good fatigue life prediction for delaminated composites.

Predicting energy cost of public buildings by artificial neural networks, CART, and random forest

The paper deals with modeling the cost of energy consumed in public buildings by leveraging three machine learning methods: artificial neural networks, CART, and random forest regression trees. Energy consumption is one of the major issues in global and national policies, therefore scientific efforts in creating prediction models of energy consumption and cost are highly important. One of the largest energy consumers in every state is its public sector, consisting of educational, health, public administration, military, and other types of public buildings. Recent technologies based on sensor networks and Big data platforms enable collection of large amounts of data that could be used to analyze energy consumption and cost. A real data from Croatian public sector is used in this paper including a large number of constructional, energetic, occupational, climate and other attributes. The algorithms for data pre-processing and modeling by optimizing parameters are suggested. Three strategies were tested: (1) with all available variables, (2) with a filter-based variable selection, and (3) with a wrapper-based variable selection which integrates Boruta algorithm and random forest. Prediction models of energy cost are created using two approaches: (a) comparative usage of artificial neural networks and two types of regression trees, CART and random forest, and (b) integration of RF-Boruta variable selection and machine learning methods for prediction. A cross-validation procedure was used to optimize the artificial neural network and regression tree topology, as well to select the most appropriate activation function. Along with creating a prediction model, the aim of the paper was also to extract the relevant predictors of energy cost in public buildings which are important in planning the construction or renovation of buildings. The results have shown that the second approach which integrates machine learning with Boruta method, where the random forest algorithm is used for both variable reduction and prediction modeling, has produced a higher accuracy of prediction than the individual usage of three machine learning methods. Such findings confirm the potential of hybrid machine learning methods which are suggested in previous research, but in favor of random forest method over CART and artificial neural networks. Regarding the variable selection, the model has extracted heating and occupational data as the most important, followed by constructional, cooling, electricity, and lighting attributes. The model could be implemented in public buildings information systems and their IoT networks within the concept of smart buildings and smart cities.

Predicting the behavior of granules of complex shapes using coarse-grained particles and artificial neural networks

The quality of discrete element simulations is connected to the right choice of material contact parameters. In this work, the usage of artificial neural networks in combination with numerical simulations using coarse-grained shapes to obtain the material contact parameters that replicate the behavior of particles of complex shapes is proposed. Dynamic angle of repose and void fraction are input parameters for the training of an artificial neural network using static and rolling friction as output parameters. The frictional parameters are combined with a coarse-grained shape and successfully replicate the experimental static angle of repose obtained for octahedral and cubic shape particles. The static angle of repose is not involved in the training process. This work demonstrates the capabilities of the artificial neural network to predict contact-equivalent properties for coarse-grained shape in discrete element method, which is commonly adopted in molecular dynamics, but not yet reported for granular media.

Extended Forgery Detection Framework for COVID-19 Medical Data Using Convolutional Neural Network

Medical data tampering has become one of the main challenges in the field of secure-aware medical data processing. Forgery of normal patients’ medical data to present them as COVID-19 patients is an illegitimate action that has been carried out in different ways recently. Therefore, the integrity of these data can be questionable. Forgery detection is a method of detecting an anomaly in manipulated forged data. An appropriate number of features are needed to identify an anomaly as either forged or non-forged data in order to find distortion or tampering in the original data. Convolutional neural networks (CNNs) have contributed a major breakthrough in this type of detection. There has been much interest from both the clinicians and the AI community in the possibility of widespread usage of artificial neural networks for quick diagnosis using medical data for early COVID-19 patient screening. The purpose of this paper is to detect forgery in COVID-19 medical data by using CNN in the error level analysis (ELA) by verifying the noise pattern in the data. The proposed improved ELA method is evaluated using a type of data splicing forgery and sigmoid and ReLU phenomenon schemes. The proposed method is verified by manipulating COVID-19 data using different types of forgeries and then applying the proposed CNN model to the data to detect the data tampering. The results show that the accuracy of the proposed CNN model on the test COVID-19 data is approximately 92%.