Artificial Neural Network Learning Research Articles

A two-dimensional MoS2 array based on artificial neural network learning for high-quality imaging

A two-dimensional MoS2 array based on artificial neural network learning for high-quality imaging

A Study to Predict Ignition Delay of an Engine Using Diesel and Biodiesel Fuel Based on the ANN and SVM Machine Learning Methods.

Over time, machine learning methods have developed, but there have not been many studies comparing how well they predict ignition delays. In this study, a model that forecasts the ignition delay of a diesel engine utilizing diesel fuel and biodiesel fuel was developed using Artificial Neural Network (ANN) and Support Vector Machine (SVM) machine learning techniques. This work has clarified the problems in designing and training the model. The effectiveness of the ANN and SVM machine learning methods' ignition delay prediction models has been evaluated under various input variable conditions. The authors employed a data set of over 700 input data sets from diesel fuel and biodiesel in the B0 to B60 range for this purpose. To evaluate the accuracy of the models, the authors compared the average accuracy of the overall classification as well as the standard deviation. The results after training and verifying the accuracy of the models show that the SVM model has a better ability to predict the fire ignition delay than the ANN model. Specifically, with the test data set and the SVM model at compression ratio (ε) = 15, RMSE = 34.45 μs, MAPE = 1.30%, MAE = 28.33 μs, MAE = 28.33 μs, and R 2 = 0.967, respectively, and the SVM model can predict well. At compression ratio ε = 17, RMSE = 30.18 μs, MAPE = 1.30%, MAE = 23.48 μs, and R 2 = 0.908, respectively. With an ANN neural network model, the prediction error value at compression ratio ε = 15 is RMSE = 41.29 μs, MAPE = 1.35%, MAE = 29.68 μs, and R 2 = 0.952, respectively; at compression ratio ε = 17, it is RMSE = 30.28 μs, MAPE = 1.25%, MAE = 23.00 μs, and R 2 = 0.975, respectively. With this accuracy, the SVM model is fully capable of forecasting the ignition delay combustion time of diesel/biodiesel engines.

Automatic Generation of Literary Sentences in French

In this paper, we describe a model for the automatic generation of literary sentences in French. Although there has been much recent effort directed towards automatic text generation in general, the generation of creative, literary sentences that is not restricted to a specific genre, which we approached in this work, is a difficult task that is not commonly treated in the scientific literature. In particular, our present model has not been previously applied to the generation of sentences in the French language. Our model was based on algorithms that we previously used to generate sentences in Spanish and Portuguese and on a new corpus, which we constructed and present here, consisting of literary texts in French, called MegaLitefr. Our automatic text generation algorithm combines language models, shallow parsing, the canned text method, and deep learning artificial neural networks. We also present a manual evaluation protocol that we propose and implemented to assess the quality of the artificial sentences generated by our algorithm, by testing if they fulfil four simple criteria. We obtained encouraging results from the evaluators for most of the desired features of our artificially generated sentences.

Quantum approximate optimization algorithm applied to the binary perceptron

We apply digitized quantum annealing (QA) and quantum approximate optimization algorithm (QAOA) to a paradigmatic task of supervised learning in artificial neural networks: the optimization of synaptic weights for the binary perceptron. At variance with the usual QAOA applications to MaxCut, or to quantum spin-chains ground-state preparation, here the classical cost function is characterized by highly nonlocal multispin interactions. Yet, we provide evidence for the existence of optimal smooth solutions for the QAOA parameters, which are transferable among typical instances of the same problem, and we prove numerically an enhanced performance of QAOA over traditional QA. We also investigate on the role of the classical cost-function landscape geometry in this problem. By artificially breaking this geometrical structure, we show that the detrimental effect of a gap-closing transition, encountered in QA, is also negatively affecting the performance of our QAOA implementation.

Learning of neural network with optimal control tools

Any learned artificial neural network on a given set of observations represents a function of several variables with vector values or real values. However, in general it is unknown except very simply cases and we have trouble to tell anything about its properties behind very general results received from learning data. In applications, such as medicine, it needs to say not only that on training data we get some error, we have to know that an error is not greater than some ɛ for all data for which we consider the system.It is well known that the learned neural network define a function. However, we check correctness of it only on finite number of observed data. We develop an optimal control approach allowing to find approximation of an unknown function realizing the given observable data, parametrized by a set of controls and defined as ordinary differential equations. Moreover, to measure discrepancy, of the output of the network we define a functional into which we include probability distribution function estimating distribution of the data.We develop a dual dynamic programming ideas to formulate a new optimization problem. We apply it to derive and to prove sufficient approximate optimality conditions for approximate neural network which should work correctly for given ɛ with respect to built functional, on a data different than the set of observations.

USE OF ARTIFICIAL NEURAL NETWORKS OF DIFFERENT ARCHITECTURE AND LEARNING RATE TO PREDICT SOIL HUMUS CONTENT USING NORMALIZED DIFFERENCE VEGETATION INDEX

As far as remotely sensed normalized difference vegetation index (NDVI) applications extend to more specific subjects than plants vegetation conditions assessment, studies are conducted to adopt this spatial index for evaluation of soil properties, e.g., soil nutrients and organic matter content, electrical conductivity, pH, etc. [1–3]. Our studies are directed to the development of mathematical model for derivation of soil humus content using normalized difference vegetation index values. Although some success has been achieved in this field by the means of regression analysis, the prediction accuracy and model fitting quality are still insufficient to provide it for practical implementation [4]. As it is known that artificial neural networks (ANN) in many cases provide much better results than traditional regression analysis, the study was performed with different ANN architecture and learning rates to establish the relationship and improve the quality of soil humus content prediction based on the values of spatial vegetation index [5].

Detecting Information Relays in Deep Neural Networks.

Deep learning of artificial neural networks (ANNs) is creating highly functional processes that are, unfortunately, nearly as hard to interpret as their biological counterparts. Identification of functional modules in natural brains plays an important role in cognitive and neuroscience alike, and can be carried out using a wide range of technologies such as fMRI, EEG/ERP, MEG, or calcium imaging. However, we do not have such robust methods at our disposal when it comes to understanding functional modules in artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here, we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information IR. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to identify computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

Prediction of Future Land Use/Land Cover Changes Using a Coupled CA-ANN Model in the Upper Omo–Gibe River Basin, Ethiopia

Land use/land cover change evaluation and prediction using spatiotemporal data are crucial for environmental monitoring and better planning and management of land use. The main objective of this study is to evaluate land use/land cover changes for the time period of 1991–2022 and predict future changes using the CA-ANN model in the Upper Omo–Gibe River basin. Landsat-5 TM for 1991, 1997, and 2004, Landsat-7 ETM+ for 2010, and Landsat-8 (OLI) for 2016 and 2022 were downloaded from the USGS Earth Explorer Data Center. A random forest machine learning algorithm was employed for LULC classification. The LULC classification result was evaluated using an accuracy assessment technique to assure the correctness of the classification method employing the kappa coefficient. Kappa coefficient values of the classification indicate that there was strong agreement between the classified and reference data. Using the MOLUSCE plugin of QGIS and the CA-ANN model, future LULC changes were predicted. Artificial neural network (ANN) and cellular automata (CA) machine learning methods were made available for LULC change modeling and prediction via the QGIS MOLUSCE plugin. Transition potential modeling was computed, and future LULC changes were predicted using the CA-ANN model. An overall accuracy of 86.53% and an overall kappa value of 0.82 were obtained by comparing the actual data of 2022 with the simulated LULC data from the same year. The study findings revealed that between 2022 and 2037, agricultural land (63.09%) and shrubland (5.74%) showed significant increases, and forest (−48.10%) and grassland (−0.31%) decreased. From 2037 to 2052, the built-up area (2.99%) showed a significant increase, and forest and agricultural land (−2.55%) showed a significant decrease. From 2052 to 2067, the projected LULC simulation result showed that agricultural land (3.15%) and built-up area (0.32%) increased, and forest (−1.59%) and shrubland (−0.56%) showed significant decreases. According to the study’s findings, the main drivers of LULC changes are the expansion of built-up areas and agricultural land, which calls for a thorough investigation using additional data and models to give planners and policymakers clear information on LULC changes and their environmental effects.

Результаты использования технологии машинного обучения для расчета оптической силы интраокулярных линз

Purpose. To evaluate possibility of using the mathematical models obtained as a result of deep learning of artificial neural networks (ANNmodels) to predict the optical power of modern intraocular lenses (IOL). Material and methods. The dataset included 455 depersonalized records of patients (26 columns of input factors and one column – output factor – calculation of IOL (dptr). For convenient construction of ANN models, a simulator program previously developed by the authors and Python language tools in the Google Colaboratory were used. Results. This article describes the possibility of using mathematical models obtained as a result of deep learning of ANN models to predict the optical power of modern IOLs, widely used in the surgical cataract treatment in ophthalmology. A distinctive feature of such ANN models in comparison with the wellknown formulas SRK II, SRK/T, Hoffer-Q, Holladay II, Haigis, Barrett is their ability to take into account a significant number of recorded input quantities, which makes it possible to reduce the mean relative error in calculating the optical power of IOL from 10 –12 to 3.5%. Conclusion. The resulting models, in contrast to the traditionally used formulas, reflect the regional specificity of patients to a much greater extent. They also make it possible to retrain and optimize the structure based on newly received data, which allows taking into account the non-stationarity of the object. Keywords: optical power of an intraocular lens, IOL, artificial neural networks, ANN-models, deep learning, training dataset

Prognostic Prediction of Cancer Based on Radiomics Features of Diagnostic Imaging: The Performance of Machine Learning Strategies.

Tumor phenotypes can be characterized by radiomics features extracted from images. However, the prediction accuracy is challenged by difficulties such as small sample size and data imbalance. The purpose of the study was to evaluate the performance of machine learning strategies for the prediction of cancer prognosis. A total of 422 patients diagnosed with non-small cell lung carcinoma (NSCLC) were selected from The Cancer Imaging Archive (TCIA). The gross tumor volume (GTV) of each case was delineated from the respective CT images for radiomic features extraction. The samples were divided into 4 groups with survival endpoints of 1 year, 3 years, 5 years, and 7 years. The radiomic image features were analyzed with 6 different machine learning methods: decision tree (DT), boosted tree (BT), random forests (RF), support vector machine (SVM), generalized linear model (GLM), and deep learning artificial neural networks (DL-ANNs) with 70:30 cross-validation. The overall average prediction performance of the BT, RF, DT, SVM, GLM and DL-ANNs was AUC with 0.912, 0.938, 0.793, 0.746, 0.789 and 0.705 respectively. The RF and BT gave the best and second performance in the prediction. The DL-ANN did not show obvious advantage in predicting prognostic outcomes. Deep learning artificial neural networks did not show a significant improvement than traditional machine learning methods such as random forest and boosted trees. On the whole, the accurate outcome prediction using radiomics serves as a supportive reference for formulating treatment strategy for cancer patients.

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.

Identification of Color and Texture of Ripe Passion Fruit with Perceptron Neural Network Method

Research using artificial neural network methods has been developed as a tool that can help human tasks, one of which is for passion fruit UMKM entrepreneurs. The problem so far that has been faced by UMKM entrepreneurs of passion fruit is that it is difficult to identify ripe passion fruit with sweet and sour taste, because there are 6 colors of passion fruit and the color of passion fruit skin is visually slightly different, as well as the texture of maturity. The main purpose of this study was to identify the color structure and texture of the ripeness of passion fruit, in order to recognize the color and texture of the ripeness of passion fruit which is good for processing into syrup, jam, jelly, juice, passion fruit juice powder by entrepreneurs of UMKM of passion fruit. This study empirically tested the color and texture of the ripeness of 10 passion fruit using the perceptron artificial neural network learning method. The data is obtained from an image that will be entered into the program. The results of the identification process using the perceptron artificial neural network from the tests that have been carried out previously, the highest calculation results obtained with the best results using a learning rate of 0.8 and 500 epoch iterations and producing an accuracy of 80%.

An Intrusion Detection Mechanism for MANETS based on Deep Learning Artificial Neural Networks (ANNS)

Mobile Ad-hoc Network (MANET) is a distributed, decentralized network of wireless portable nodes connecting directly without any fixed communication base station or centralized administration. Nodes in MANET move continuously in random directions and follow an arbitrary manner, which presents numerous challenges to these networks and make them more susceptible to different security threats. Due to this decentralized nature of their overall architecture, combined with the limitation of hardware resources, those infrastructure-less networks are more susceptible to different security attacks such as black hole attack, network partition, node selfishness, and Denial of Service (DoS) attacks. This work aims to present, investigate, and design an intrusion detection predictive technique for Mobile Ad hoc networks using deep learning artificial neural networks (ANNs). A simulation-based evaluation and a deep ANNs modelling for detecting and isolating a Denial of Service (DoS) attack are presented to improve the overall security level of Mobile ad hoc networks.

Artifical Neural Network for Forecasting Electricity Consumption in Energy Enterprises

The concept of "Digital Transformation 2030", which defines the national goals and strategic objectives of the development of the Russian Federation for the period up to 2030, specifies specialized goals and objectives. These goals and objectives are an important message for the introduction of intelligent information management systems based on digital technologies in the electric power industry in general and energy consumption in particular. The main challenges for the transition to digital transformation are: increasing the rate of tariff growth for the end consumer; increasing deterioration of the network infrastructure; the presence of excessive network construction; increasing requirements for the quality of energy consumption. Based on the above, this article is devoted to the development of a method for the formation of an intelligent con­trol system at an energy enterprise by obtaining an early forecast of the amount of electricity required. The predicted values will help not only to increase the energy efficiency of the company through the implementation of specialized energy saving measures, but also to reduce the financial costs of electricity. The solution to this problem is presented in the form of an intelligent neural network system. The main advantages of this artificial neural network are versatility, high-speed and accurate learning, as well as a small amount of training data. The artificial neural network itself is based on the freely distributed TensorFlow machine learning software library, and a modified error backpropagation method is used as training, the main difference of which is the addition of an artificial neural network learning rate increase factor. The results of the analysis of the effectiveness of the method showed that the proposed intelligent neural network system is more accurate (including relative to similar solutions): the average error does not exceed 3.08 % over the entire time of the experiment. This will allow companies to carry out energy saving measures, which will be especially useful in the current economic realities.

What are recent observations telling us in light of improved tests of distance duality relation?

As an exact result required by the Etherington reciprocity theorem, the cosmic distance duality relation (CDDR), η(z)=DL(z)(1+z)−2/DA(z)=1 plays an essential part in modern cosmology. In this paper, we present a new method (η(zi)/η(zj)) to use the measurements of ultra-compact structure in radio quasars (QSO) and the latest observations of type Ia supernova (SN Ia) to test CDDR. By taking the observations directly from SN Ia and QSOs, one can completely eliminate the uncertainty caused by the calibration of the absolute magnitudes of standard candles (MB) and the linear sizes of standard rulers (lm). Benefit from the absence of nuisance parameters involved in other currently available methods, our analysis demonstrates no evidence for the deviation and redshift evolution of CDDR up to z=2.3. The combination of our methodology and the machine learning Artificial Neural Network (ANN) would produce 10−3 level constraints on the violation parameter at high redshifts. Our results indicate perfect agreement between observations and predictions, supporting the persisting claims that the Etherington reciprocity theorem could still be the best description of our universe.

Comparison of Artificial Neural Network and Polynomial Approximation Models for Reflectance Spectra Reconstruction

Knowledge of surface reflection of an object is essential in many technological fields, including graphics and cultural heritage. Compared to direct multi- or hyper-spectral capturing approaches, commercial RGB cameras allow for a high resolution and fast acquisition, so the idea of mapping this information into a reflectance spectrum (RS) is promising. This study compared two modelling approaches based on a training set of RGB-reflectance pairs, one implementing artificial neural networks (ANN) and the other one using multivariate polynomial approximation (PA). The effect of various parameters was investigated: the ANN learning algorithm-standard backpropagation (BP) or Levenberg-Marquardt (LM), the number of hidden layers (HLs) and neurons, the degree of multivariate polynomials in PA, the number of inputs, and the training set size on both models. In the two-layer ANN with significantly fewer inputs than outputs, a better MSE performance was found where the number of neurons in the first HL was smaller than in the second one. For ANNs with one and two HLs with the same number of neurons in the first layer, the RS reconstruction performance depends on the choice of BP or LM learning algorithm. RS reconstruction methods based on ANN and PA are comparable, but the ANN models' better fine-tuning capabilities enable, under realistic constraints, finding ANNs that outperform PA models. A profiling approach was proposed to determine the initial number of neurons in HLs-the search centre of ANN models for different training set sizes.

PRESSURE GRADIENT COMPUTATION FOR FOAMS WITH DIFFERENT GEOMETRIC PROPERTIES: BASED ON ANN AND SVR MACHINE LEARNING MODEL AND TRAINED BY CFD SIMULATIONS

In this research work, a combination of computational fluid dynamics (CFD) simulation and artificial intelligence (AI) methods are conducted to study the effects of geometric properties of aluminum foams on airflow and to compute and predict pressure gradients in foams with such varied geometric parameters as porosity (65-90%) and pore diameter (200-2000 μm). The 3D foam structures are created by the Laguerre-Voronoi tessellations method. Based on the CFD results, pressure gradient for 114 different foams can be calculated in terms of inlet flow velocity (in the range 0.1-8 m/s). Foam pressure gradient is found to increase with increasing inlet flow velocity but with decreasing pore diameter and porosity. Comparisons reveal that the results obtained in the present study for pressure gradient are consistent with the data reported in the literature. It is, therefore, concluded that CFD simulation is a useful tool for pressure gradient estimation in a variety of foam types. Unique simulations are, however, needed each time foam structural properties change, which entails significant increases in the associated computation costs. This drawback may, nonetheless, be at least partially addressed by taking advantage of soft computing methods such as machine learning (ML). Artificial neural network (ANN) and support vector regression (SVR) as subsets of AI are designed (models with input variables inlet velocity and the foam structural parameters: porosity, pore diameter, and strut diameter) and trained using CFD results to predict pressure gradients in a large number of foams. When applied to new foam samples, the ML models exhibit an acceptable performance in predicting pressure gradients. Using such provisions, the method can be effectively used for predicting pressure gradient in various porous media at minimum computation costs.

Frequency Control Approach and Load Forecasting Assessment for Wind Systems

Frequency deviation has to be controlled in power generation units when there are fluctuations in system frequency. With several renewable energy sources, wind energy forecasting is majorly focused in this work which is a tough task due to its variations and uncontrollable nature. Whenever there is a mismatch between generation and demand, the frequency deviation may arise from the actual frequency 50 Hz (in India). To mitigate the frequency deviation issue, it is necessary to develop an effective technique for better frequency control in wind energy systems. In this work, heuristic Fuzzy Logic Based Controller (FLC) is developed for providing an effective frequency control support by modeling the complex behavior of the system to enhance the load forecasting in wind based hybrid power systems. Frequency control is applied to reduce the frequency deviation due to fluctuations and load prediction information using ANN (Artificial Neural Network) and SVM (Support Vector Machine) learning models. The performance analysis of the proposed method is done with different machine learning based approaches. The forecasting assessment is done over various climates with the aim to decrease the prediction errors and to demote the forecasting accuracy. Simulation results show that the Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE) and Normalized Mean Absolute Error (NMAE) values are scaled down by 41.1%, 9.9% and 23.1% respectively in the proposed method while comparing with existing wavelet and BPN based approach.

Machine learning-assisted flexible wearable device for tyrosine detection.

Early diagnosis of pathological markers can significantly shorten the rate of viral transmission, reduce the probability of infection, and improve the cure rate of diseases. Therefore, analytical techniques for identifying pathological markers and environmental toxicants have received considerable attention from researchers worldwide. However, the most popular techniques used in clinical settings involve expensive precision instruments and complex detection processes. Thus, a simpler, more efficient, rapid, and intelligent means of analysis must be urgently developed. Electrochemical biosensors have the advantages of simple processing, low cost, low sample preparation requirements, rapid analysis, easy miniaturization, and integration. Thus, they have become popular in extensive research. Machine learning is widely used in material-assisted synthesis, sensor design, and other fields owing to its powerful data analysis and simulation learning capabilities. In this study, a machine learning-assisted carbon black-graphene oxide conjugate polymer (CB-GO/CP) electrode, in conjunction with a flexible wearable device, is proposed for the smart portable detection of tyrosine (Tyr). Input feature value data are obtained for the artificial neural network (ANN) and support vector machines (SVM) model learning via multiple data collections in artificial urine and by recording the pH and temperature values. The results reveal that a machine-learning model that integrates multiple external factors is more accurate for the prediction of Tyr concentration.

Accurate Phase Detection for ZigBee Using Artificial Neural Network

The IEEE802.15.4 standard has been widely used in modern industry due to its several benefits for stability, scalability, and enhancement of wireless mesh networking. This standard uses a physical layer of binary phase-shift keying (BPSK) modulation and can be operated with two frequency bands, 868 and 915 MHz. The frequency noise could interfere with the BPSK signal, which causes distortion to the signal before its arrival at receiver. Therefore, filtering the BPSK signal from noise is essential to ensure carrying the signal from the sender to the receiver with less error. Therefore, removing signal noise in the BPSK signal is necessary to mitigate its negative sequences and increase its capability in industrial wireless sensor networks. Moreover, researchers have reported a positive impact of utilizing the Kalmen filter in detecting the modulated signal at the receiver side in different communication systems, including ZigBee. Meanwhile, artificial neural network (ANN) and machine learning (ML) models outperformed results for predicting signals for detection and classification purposes. This paper develops a neural network predictive detection method to enhance the performance of BPSK modulation. First, a simulation-based model is used to generate the modulated signal of BPSK in the IEEE802.15.4 wireless personal area network (WPAN) standard. Then, Gaussian noise was injected into the BPSK simulation model. To reduce the noise of BPSK phase signals, a recurrent neural networks (RNN) model is implemented and integrated at the receiver side to estimate the BPSK’s phase signal. We evaluated our predictive-detection RNN model using mean square error (MSE), correlation coefficient, recall, and F1-score metrics. The result shows that our predictive-detection method is superior to the existing model due to the low MSE and correlation coefficient (R-value) metric for different signal-to-noise (SNR) values. In addition, our RNN-based model scored 98.71% and 96.34% based on recall and F1-score, respectively.