Implementation Of Artificial Neural Networks Research Articles

Implementation of Exploratory Data Analysis and Artificial Neural Networks to Predict Student Graduation on-Time

Almost all universities in Indonesia face the problem of a low number of students graduating on time. This will affect higher education accreditation. For this reason, universities must pay attention to the timely graduation of their students. The way that can be taken is to predict students' graduation on time. This research aims to predict students' timely graduations using a combination of exploratory data analysis and artificial neural networks. Exploratory data analysis is used to study the relationship between features that influence students' on-time graduation, while artificial neural networks are used to predict on-time graduation. This research goes through method stages, starting with determining the dataset, exploratory data analysis, data preprocessing, dividing training and test data, and applying artificial neural networks. From the research, it was found that Work features and GPS features greatly influence graduation on time. Students who study while working are less likely to graduate on time compared to students who do not work. Students who have an average GPS above 3.00 for eight consecutive semesters will find it easier to graduate on time. Meanwhile, Age and Gender features have no effect on graduating on time. With a percentage of 50% training data and 50% test data, epoch 100, and learning rate 0.001, the best network model was obtained to predict graduation on time with an accuracy rate of 69.84%. The research results also show that the amount of test data and the learning rate can influence the level of accuracy. Meanwhile, the number of epochs does not affect the level of accuracy.

Parametric appraisal and wear prediction of hybrid composites using an integrated soft computing approach

AbstractThis article reports on the implementation of artificial neural network (ANN) and statistical methods to analyze and predict the erosion performance of titania (TiO2) filled ramie‐epoxy based composites. These hybrid composites are prepared by conventional hand lay‐up route and subjected to solid particle erosion tests as per Taguchi's L27 orthogonal array. The effects of different control factors on erosion rate of these composites are studied using Taguchi method. It reveals that impact velocity and filler content have significant effect on the erosion wear rate followed by other least significant factors. The individual effect of each control factor while keeping other factors constant is ascertained by performing steady state erosion experiments. Further, a computational model based on ANN is used as a tool to effectively predict the erosion rates of the composites. The results show that the predicted values are in reasonably good agreement with the experimental ones with an accuracy of 90% and relative error lying within a range of 1%–10%. Further, the trained ANN model is validated by considering the erosion rates obtained during steady state erosion process as the input parameter. The possible mechanisms causing the wear loss are identified using electron microscopy.Highlights Successful fabrication of titanium oxide reinforced hybrid composites. Steady state erosion experiments are performed. Erosion rates are predicted using ANN and compared with the experimental data. Wear loss mechanisms are identified using electron microscopy.

Enhancing Microwave Photonic Interrogation Accuracy for Fiber-Optic Temperature Sensors via Artificial Neural Network Integration

In this paper, an application of an artificial neural network algorithm is proposed to enhance the accuracy of temperature measurement using a fiber-optic sensor based on a Fabry–Perot interferometer (FPI). It is assumed that the interrogation of the FPI is carried out using an optical comb generator realizing a microwave photonic approach. Firstly, modelling of the reflection spectrum of a Fabry–Perot interferometer is implemented. Secondly, probing of the obtained spectrum using a comb-generator model is performed. The resulting electrical signal of the photodetector is processed and is used to create a sample for artificial neural network training aimed at temperature detection. It is demonstrated that the artificial neural network implementation can predict temperature variations with an accuracy equal to 0.018 °C in the range from −10 to +10 °C and 0.147 in the range from −15 to +15 °C.

Impact of Arrhenius activation energy on magnetic nanofluid flow over a slendering stretchable sheet with nonlinear radiative heat transfer: A machine learning algorithm

Thermal systems in the contemporary world need effective cooling and heating methods. Heat transfer technology plays a vital role in various industries, including aerospace, electronic equipment, automobiles, and transportation. Considering the importance of effective cooling and heating processes, this framework explores the hydromagnetic stagnation point flow with binary chemical reactions, ohmic heating, Arrhenius activation energy, nonlinear thermal radiation, thermophoresis, and Brownian motion. At first, the flow equations are determined in a formal way as dimensional partial differential equations. Then, they are transformed into simpler, dimensionless ordinary differential equations using self-similar variables. The present study describes a novel approach to intelligent numerical computing, utilizing a Levenberg-Marquard algorithm-based MLP (Multi-Layer Perceptron) feed-forward back-propagation ANN (Artificial Neural Networks) implementation. The collection of data was conducted to facilitate the evaluation, validation, and instruction of the artificial neural network model. The utilization of appropriate self-similarity variables has facilitated the conversion of fluid transport equations into ordinary differential equations. The Runge–Kutta–Fehlberg (RKF) technique was used to solve these equations. The numerical results are presented visually for numerous constraints of the governing parameters. The increased values of the velocity ratio enhanced the fluid velocity. The nonlinear thermal radiation and temperature differential characteristics significantly raise the temperature of the fluid. Increasing the nonlinear radiation and magnetic field parameters improves the rate of heat transfer. The temperature of the fluid decreases as the size of stagnation increases. The skin friction coefficients decrease as the wall thickness and magnetic parameters increase.

Ionic Diffusive Nanomemristors with Dendritic Competition and Cooperation Functions for Ultralow Voltage Neuromorphic Computing.

Realization of dendric signal processing in the human brain is of great significance for spatiotemporal neuromorphic engineering. Here, we proposed an ionic dendrite device with multichannel communication, which could realize synaptic behaviors even under an ultralow action potential of 80 mV. The device not only could simulate one-to-one information transfer of axons but also achieve a many-to-one modulation mode of dendrites. By the adjustment of two presynapses, Pavlov's dog conditioning experiment was learned successfully. Furthermore, the device also could emulate the biological synaptic competition and synaptic cooperation phenomenon through the comodulation of three presynapses, which are crucial for artificial neural network (ANN) implementation. Finally, an ANN was further constructed to realize highly efficient and anti-interference recognition of fashion patterns. By introducing the cooperative device, synaptic weight updates could be improved for higher linearity and larger dynamic regulation range in neuromorphic computing, resulting in higher recognition accuracy and efficiency. Such an artificial dendric device has great application prospects in the processing of more complex information and the construction of an ANN system with more functions.

Artificial neural networks optimize the establishment of a Brazilian germplasm core collection of winter squash (Cucurbita moschata D.)

With widespread cultivation, Cucurbita moschata stands out for the carotenoid content of its fruits such as β and α-carotene, components with pronounced provitamin A function and antioxidant activity. C. moschata seed oil has a high monounsaturated fatty acid content and vitamin E, constituting a lipid source of high chemical–nutritional quality. The present study evaluates the agronomic and chemical–nutritional aspects of 91 accessions of C. moschata kept at the BGH-UFV and propose the establishment of a core collection based on multivariate approaches and on the implementation of Artificial Neural Networks (ANNs). ANNs was more efficient in identifying similarity patterns and in organizing the distance between the genotypes in the groups. The averages and variances of traits in the CC formed using a 15% sampling of accessions, were closer to those of the complete collection, particularly for accumulated degree days for flowering, the mass of seeds per fruit, and seed and oil productivity. Establishing the 15% CC, based on the broad characterization of this germplasm, will be crucial to optimize the evaluation and use of promising accessions from this collection in C. moschata breeding programs, especially for traits of high chemical–nutritional importance such as the carotenoid content and the fatty acid profile.

Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges.

Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.

Comparative energy and exergy analysis of water-LiBr absorption chiller configurations with ejector integration, and implementation of artificial neural network on the optimal selection

Comparative energy and exergy analysis of water-LiBr absorption chiller configurations with ejector integration, and implementation of artificial neural network on the optimal selection

Comparative Energy and Exergy Analysis of Water-LiBr Absorption Chiller Configurations with Ejector Integration, and Implementation of Artificial Neural Network on the Optimal Selection

Comparative Energy and Exergy Analysis of Water-LiBr Absorption Chiller Configurations with Ejector Integration, and Implementation of Artificial Neural Network on the Optimal Selection

An artificial neural network analysis of the thermal distribution of a fractional-order radial porous fin influenced by an inclined magnetic field

<abstract><p>Fins and radial fins are essential elements in engineering applications, serving as critical components to optimize heat transfer and improve thermal management in a wide range of sectors. The thermal distribution within a radial porous fin was investigated in this study under steady-state conditions, with an emphasis on the impact of different factors. The introduction of an inclined magnetic field was investigated to assess the effects of convection and internal heat generation on the thermal behavior of the fin. The dimensionless form of the governing temperature equation was utilized to facilitate analysis. Numerical solutions were obtained through the implementation of the Hybrid Cuckoo Search Algorithm-based Artificial Neural Network (HCS-ANN). The Hartmann number (M) and the Convection-Conduction parameter (Nc) were utilized in the evaluation of heat transfer efficiency. Enhanced efficiency, as evidenced by decreased temperature and enhanced heat removal, was correlated with higher values of these parameters. Residual errors for both M and Nc were contained within a specified range of $ 10^{-6} $ to $ 10^{-14} $, thereby offering a quantitative assessment of the model's accuracy. As a crucial instrument for assessing the performance and dependability of predictive models, the residual analysis highlighted the impact of fractional orders on temperature fluctuations. As the Hartmann number increased, the rate of heat transfer accelerated, demonstrating the magnetic field's inhibitory effect on convection heat transport, according to the study. The complex relationship among Nc, fractional order (BETA), and temperature was underscored, which motivated additional research to improve our comprehension of the intricate physical mechanisms involved. This study enhanced the overall understanding of thermal dynamics in radial porous fins, providing significant implications for a wide array of applications, including aerospace systems and heat exchangers.</p></abstract>

Investigating the Accuracy of Artificial Neural Network Models in Predicting Surface Roughness in Drilling Processes

In recent times, the application of Artificial Intelligence (AI) has become widespread across various fields, including machining operations like milling, drilling, shaping, turning, grinding, counter drilling, and counter sinking. Among the techniques used in these applications, Artificial Neural Networks (ANN) have gained popularity. This study focuses on utilizing ANN to optimize drilling hardened non-shrinking (OHNS) die steel. The methodology presented in this research involves the implementation of ANN to analyze the impact of drilling process parameters on surface roughness. MATLAB 2023 software was used to effectively train the neural network. The dataset for this study consists of input and output expressions derived from experimental analysis. The input data includes variables such as cutting speed, feedrate, drill size, and depth of cut. The objective of this study is to predict surface roughness based on input datasets, with 70% of the samples allocated as training data and the remaining 30% for testing and validation. The experimental results demonstrate that ANN provides a reliable prediction capability, with Coefficient of Determination (R2) and Mean Square Error (MSE) values of 0.997 and 0.231893, respectively. The low MSE value indicate better model performance, also the R2 value obtained indicate a strong correlation between the predicted and actual values, suggesting that the ANN model provides a satisfactory fit to the data, indicating a high level of confidence in the statistical results. Thus, it can be concluded that the results obtained from the ANN model are statistically significant, slightly superior to the classical model, and exhibit a good fit.

Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey.

With the adoption of smart systems, artificial neural networks (ANNs) have become ubiquitous. Conventional ANN implementations have high energy consumption, limiting their use in embedded and mobile applications. Spiking neural networks (SNNs) mimic the dynamics of biological neural networks by distributing information over time through binary spikes. Neuromorphic hardware has emerged to leverage the characteristics of SNNs, such as asynchronous processing and high activation sparsity. Therefore, SNNs have recently gained interest in the machine learning community as a brain-inspired alternative to ANNs for low-power applications. However, the discrete representation of the information makes the training of SNNs by backpropagation-based techniques challenging. In this survey, we review training strategies for deep SNNs targeting deep learning applications such as image processing. We start with methods based on the conversion from an ANN to an SNN and compare these with backpropagation-based techniques. We propose a new taxonomy of spiking backpropagation algorithms into three categories, namely, spatial, spatiotemporal, and single-spike approaches. In addition, we analyze different strategies to improve accuracy, latency, and sparsity, such as regularization methods, training hybridization, and tuning of the parameters specific to the SNN neuron model. We highlight the impact of input encoding, network architecture, and training strategy on the accuracy-latency tradeoff. Finally, in light of the remaining challenges for accurate and efficient SNN solutions, we emphasize the importance of joint hardware-software codevelopment.

ARTIFICIAL NEURAL NETWORKS TO ENHANCE THE RING MACHINE EFFICIENCY AND YARN QUALITY BY DETERMINATION AND OPTIMIZATION OF DYNAMIC YARN TENSION

The yarn spinning process involves the interaction of large varieties of variables. The relation between the dynamic yarn tension (DYT), yarn quality, and production efficiency of the spinning frame cannot be established conclusively. Artificial neural network (ANN) is a promising step in this filed. In this research work, ANNs simulation and modeling is applied for the optimization of the DYT n to improve the production efficiency and quality of yarn. The research to date in DYT is insufficient to meet the developmental requirement of the high-speed and efficient ring spinning frame. One of the major problems facing the effective use of the ANN is the correct selection of the input parameters to be fed for the training of ANNs. Data of various input variables such as count, traveler no., spindle speed and dynamic yarn tension etc., was used for ANN modeling and simulation. DYT plays a significant role in the determination of yarn quality and its productivity in terms of end breakage rate. However, it has never been explained in terms of displacement from the original yarn path. This work is aimed to the determination and optimization of DYT at ring spinning frame. The influence of different yarn geometry parameters on DYT, measured by the tensiometer was investigated. The optimized DYT values for the machines, running at different speed and different counts were determined using ANN modeling. It is found that the optimized values predicted from ANN resulted in better quality, high production, and decreased end-breakage at industrial ring spinning frames. By the implementation of ANNs the optimum speed and effective utilization of textile raw materials can be achieved.

Analog HfxZr1‐xO2 Memristors with Tunable Linearity for Implementation in a Self‐Organizing Map Neural Network

AbstractDoped‐metal oxide‐based memristors, with the potential for improved switching performance and capability for multi‐bit information storage, are attractive candidates in the implementation of artificial neural network (ANN) hardware systems. However, performance and process considerations such as switching behavior and complementary‐metal‐oxide‐semiconductor (CMOS) process compatibility remain a challenge. This study shows that amorphous Zr‐doped HfO2 (HZO) memristors fabricated via a co‐sputtering approach improve the switching performance by providing a controllable knob to modulate defects in the switching layer. At the same time, it satisfies the CMOS process compatibility requirements for industry adoption. HZO memristors with optimized stoichiometry exhibit 30% reduced switching voltages and 50% faster switching as compared to control HfO2 memristors. Concurrently, this study shows that high linearity analog states tuning is achievable via a programming scheme that utilizes voltage pulses with increasing amplitudes. This study further shows via simulation evaluation that HZO memristors implemented in a self‐organizing‐map (SOM) network for Fashion MNIST database classification, achieve an accuracy of 92% with short training cycles. The results thus pave a potential pathway for further development of CMOS process compatible HZO memristors for use in future storage and computing applications.

Artificial physics engine for real-time inverse dynamics of arm and hand movement.

Simulating human body dynamics requires detailed and accurate mathematical models. When solved inversely, these models provide a comprehensive description of force generation that considers subject morphology and can be applied to control real-time assistive technology, for example, orthosis or muscle/nerve stimulation. Yet, model complexity hinders the speed of its computations and may require approximations as a mitigation strategy. Here, we use machine learning algorithms to provide a method for accurate physics simulations and subject-specific parameterization. Several types of artificial neural networks (ANNs) with varied architecture were tasked to generate the inverse dynamic transformation of realistic arm and hand movement (23 degrees of freedom). Using a physical model, we generated representative limb movements with bell-shaped end-point velocity trajectories within the physiological workspace. This dataset was used to develop ANN transformations with low torque errors (less than 0.1 Nm). Multiple ANN implementations using kinematic sequences solved accurately and robustly the high-dimensional kinematic Jacobian and inverse dynamics of arm and hand. These results provide further support for the use of ANN architectures that use temporal trajectories of time-delayed values to make accurate predictions of limb dynamics.

Implementation of Backpropagation Artificial Neural Network on Forecasting Export of Palm Oil in Indonesia

Export activities are one of the largest revenues in Indonesia with the largest contributor to export is being palm oil. Increasing volume of palm oil exports, it will be able to spur economic growth in Indonesia. In this research, palm oil export forecasting in Indonesia is carried out based on the main destination countries using the Artificial Neural Network (ANN) method with the Backpropagation algorithm. The data used is palm oil export data for 2012-2022 obtained from the Central Statistics Agency (BPS) website. From the data used, the optimal architecture model is 10-1-3-3-1 with a MAPE of 9.68%, which means that this architecture uses 10 input data, 3 hidden layers with the number of each input neuron (1,3,3), and there is 1 output output. From this study, it is estimated that 90% of the results of palm oil export forecasting using the ANN method are close to the actual value.

The Implementation of Response Surface Methodology and Artificial Neural Networks to Find the Best Germination Conditions for Lycopersicon esculetum Based on Its Phenological Development in a Greenhouse

The incorporation of biodegraded substrates during the germination of horticultural crops has shown favorable responses in different crops; however, most of these studies evaluate their effect only in the first days of seedling life, and do not follow up on the production process under greenhouse or open field conditions. The objective of this study was to evaluate the phenological development of Lycopersicon esculetum (tomato) seedlings in greenhouses that were germinated with biodegraded substrate mixed with peat moss. To find the best plant performance condition and determine whether the biodegraded substrate allows tomato plants to be obtained with the conditions for their production, the response surface methodology (RSM) and artificial neural network (ANN) were used. Three response surface models and three neural network models were developed to analyze the plant growth, the leaf length and the leaf width. The results obtained show that plant height during the first days presented statistically significant differences among the different treatments, with an initial average height of 5.3 cm. The length of the leaves at transplantation was statistically different, maintaining a length of 2.4, and the width of the leaves at transplantation measured 1.8 cm. The RSM and ANN models allowed the estimation of the optimal value of the adequate amount of degraded substrate to germinate Lycopersicon esculetum and reduce the use of peat moss. The coefficient of determination (r2) indicates that the ANNs presented a better data fit (r2 > 0.99) to predict the experimental conditions that maximize the study variables; in this sense, the plants obtained with 100% biodegraded substrate showed a better development, which suggests its use as an alternative substrate in the germination process and to reduce the use of peat moss.

Extremely energy-efficient, magnetic field-free, skyrmion-based memristors for neuromorphic computing

The human brain can process information more efficiently than computers due to the dynamics of neurons and synapses. Mimicking such a system can lead to the practical implementation of artificial spiking neural networks. Spintronic devices have been shown to be an ideal solution for realizing the hardware required for neuromorphic computing. Skyrmions prove to be an effective candidate as information carriers owing to their topological protection and particle-like nature. Ferrimagnet and antiferromagnet-based spintronics have been employed previously to obtain an ultrafast simulation of artificial synapses and neurons. Here, we have proposed a ferromagnetic device of stack Ta3nmPt3nmCu0.65nmCo0.5nmPt1nm that is capable of ultrafast simulation of artificial neurons and synapses, owing to the high velocity of the stabilized skyrmions in the system. Electrical pulses of nanosecond pulse width were used to control the accumulation and dissipation of skyrmions in the system, analogous to the variations in the synaptic weights. Lateral structure inversion asymmetry is used to bring about a field-free switching in the system, leading to an energy-efficient switching process. Magnetic field-free deterministic switching and low pulse width current pulses drastically reduce energy consumption by 106 times compared to the existing ferromagnet-based neuromorphic devices. Artificial neuron, synapse, and memristor functionalities have been reproduced on the same device with characteristic time scales and field-free switching, better than any existing ferromagnet-based neuromorphic devices. The results recognize ferromagnet-based skyrmions as viable candidates for ultrafast neuromorphic spintronics capable of executing cognitive tasks with extremely high efficiency.

The Implementation of Artificial Neural Networks for Stock Price Prediction

The Implementation of Artificial Neural Networks for Stock Price Prediction

Implementation of Fast Fourier Transform and Artificial Neural Network in Series Arc Fault Identification and Protection System on DC Bus Microgrid

A microgrid is a cluster of electrical sources and loads that are interconnected and synchronized. Microgrid operation is typically divided into two modes, isolated or connected to the grid with a single or standalone control system. In this context, it can enhance the reliability and quality of electricity supply for connected customers. When using a microgrid system, it is important to consider the risk of series arc faults. Series arc faults are sudden bursts of flames resulting from ionization of gas between two electrode gaps. These faults can occur due to manufacturing defects, installation Errors, aging, or corrosion on conductor rods, leading to imperfect connections. Detecting series arc faults in DC microgrid system operations can be challenging using standard protective devices. Failure in the protection system can pose risks of fire, electrical shock hazards, and power loss in the DC microgrid.Therefore, a device has been designed to detect series arc faults by utilizing the fast Fourier transform method and artificial neural network, which function to analyze DC signal and make decisions when faults occur by examining the average sum of current frequency values during normal and fault conditions. In this study, the average sum of current frequency values during normal conditions was found to range from 0.35437 to 0.36906 A, while during fault conditions, it ranged from 0.21450 to 0.22793 A, with an average protection identification time of 1087 ms and an ANN output accuracy of 99.98%.