Artificial Neural Network Classifier Research Articles

Advanced deep operator networks to predict multiphysics solution fields in materials processing and additive manufacturing

Unlike classical artificial neural networks, which require retraining for each new set of parametric inputs, the Deep Operator Network (DeepONet), a lately introduced deep learning framework, approximates linear and nonlinear solution operators by taking parametric functions (infinite-dimensional objects) as inputs and mapping them to complete solution fields. In this paper, two newly devised DeepONet formulations with sequential learning and Residual U-Net (ResUNet) architectures are trained for the first time to simultaneously predict complete thermal and mechanical solution fields under variable loading histories, process parameters, and even variable geometries. Two real-world applications are demonstrated: 1- coupled thermo-mechanical analysis of steel continuous casting with multiple visco-plastic constitutive laws and 2- sequentially coupled directed energy deposition for additive manufacturing. Despite highly challenging spatially variable target distributions, DeepONets can infer reasonably accurate full-field temperature and stress solutions several orders of magnitude faster than traditional and highly optimized finite-element analysis (FEA), even when FEA simulations are run on the latest high-performance computing platforms. The proposed DeepONet model’s ability to provide field predictions almost instantly for unseen input parameters opens the door for future preliminary evaluation and design optimization of these vital industrial processes.

Improved Artificial Neural Network Classification Model based Metaheuristic Optimization for Handwritten Character Recognition

This study addresses the concerns regarding the performance of Handwritten Character Recognition (HCR) systems, focusing on the classification stage. It is widely acknowledged that the development of the classification model significantly impacts the overall performance of HCR. The problems identified specifically pertain to the classification model, particularly in the context of the Artificial Neural Network (ANN) learning problem, leading to low accuracy in recognizing handwritten characters. The objective of this study is to improve and refine the ANN classification model to achieve better HCR. To achieve this goal, this study proposed a hybrid Flower Pollination Algorithm with Artificial Neural Network (FPA-ANN) classification model for HCR. The FPA is one of the metaheuristic approaches is utilized as an optimization technique to enhance the performance of ANN, particularly by optimizing the network training process of ANN. The experimentation phase involves using the National Institute of Standards and Technology (NIST) handwritten character database. Finally, the proposed FPA-ANN classification model is analysed based on generated confusion matrix and evaluated performance of the classification model in terms of precision, sensitivity, specificity, F-score and accuracy.

Artificial Neural Networks for Gas‐Liquid Flow Regime Classification in Small Channels

AbstractThe reliable design of multiphase micro‐structured apparatus requires a precise knowledge of the internal flow regime. Previous research indicated that classifiers based on artificial neural networks (ANN) are relatively simple to develop and provide a reasonable accuracy when trained with data for specific inlet designs. This paper introduces advanced ANN classifiers capable of predicting all relevant flow regimes regardless of the inlet design with a recall of 94 % and above for Taylor, churn, dispersed, rivulet, and parallel flows, between 89 % and 94 % for annular and bubbly flows, and 83 % for Taylor‐annular flow. These classifiers were trained and validated by using more than 13,000 experimental data points extracted from 97 flow maps.

Learning spiking neuronal networks with artificial neural networks: neural oscillations.

First-principles-based modelings have been extremely successful in providing crucial insights and predictions for complex biological functions and phenomena. However, they can be hard to build and expensive to simulate for complex living systems. On the other hand, modern data-driven methods thrive at modeling many types of high-dimensional and noisy data. Still, the training and interpretation of these data-driven models remain challenging. Here, we combine the two types of methods to model stochastic neuronal network oscillations. Specifically, we develop a class of artificial neural networks to provide faithful surrogates to the high-dimensional, nonlinear oscillatory dynamics produced by a spiking neuronal network model. Furthermore, when the training data set is enlarged within a range of parameter choices, the artificial neural networks become generalizable to these parameters, covering cases in distinctly different dynamical regimes. In all, our work opens a new avenue for modeling complex neuronal network dynamics with artificial neural networks.

Application of artificial neural networks and Langmuir and Freundlich isotherm models to the removal of textile dye using biosorbents: A comparative study among methodologies

AbstractAdsorption isotherms are valuable tools for describing the interaction between adsorbate and adsorbent since they demonstrate the equilibrium relationship. The Langmuir and Freundlich models are the most commonly used isotherm models to describe these relationships; still, they cannot consistently deliver efficient results due to the assumptions of the model not predicting more complex situations as occurs in biosorption. Artificial neural networks (ANN) are a set of algorithms modelled loosely after the human brain and are designed to recognize patterns. The ANN tool can overcome problems isotherm models have in describing the interactions mentioned and help define the best conditions for a given adsorption process. This paper reports the application of ANNs for predicting the removal efficiency of textile dye Neolan Black WA (Acid Black 52) using orange peel and sugarcane bagasse as biosorbents. The Freundlich, Langmuir, pseudo‐first‐order, and pseudo‐second‐order models were applied and compared to the ANN model. The parameters evaluated were initial dye concentration (10–600 mg/L), final dye concentration (0–83.44 mg/L), biosorbent mass (1.5 g), pH (2), and contact time of dye (0.167–24 h). Two classes of ANNs, Elman and feed‐forward networks, were tested with a mean square error of 0.0212 and 0.7274 for the isotherm and kinetics, respectively. Compared to the conventional isotherm and kinetic models, the Elman network predicted the amount adsorbed by the biosorbents with higher precision, acquiring a determination coefficient of 0.9998 and a mean square error of 8.75 × 10−5.

Neural harmony: revolutionizing thyroid nodule diagnosis with hybrid networks and genetic algorithms

In the contemporary world, thyroid disease poses a prevalent health issue, particularly affecting women’s well-being. Recognizing the significance of maternal thyroid (MT) hormones in fetal neurodevelopment during the first half of pregnancy, this study introduces the HNN-GSO model. This groundbreaking hybrid approach, utilizing the MT dataset, integrates ResNet-50 and Artificial Neural Network (ANN) within a Glow-worm Swarm Optimization (GSO) framework for optimal parameter tuning. With a comprehensive methodology involving dataset preprocessing and Genetic Algorithm (GA) for feature selection, our model leverages ResNet-50 for feature extraction and ANN for classification tasks. Implemented in Python, the HNN-GSO model outperforms existing models, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), ResNet, GoogleNet, and ANN, achieving an impressive accuracy rate of 98%. This success underscores the effectiveness of our approach in complex classification tasks within machine learning (ML) and pattern recognition, specifically tailored to the Thyroid Ultrasound Images (TUI) Dataset. To provide a comprehensive understanding of performance, additional statistical measures such as precision, recall, and F1 score were considered. The HNN-GSO model consistently outperformed competitors across these metrics, showcasing its superiority in MT classification. The HNN-GSO model seamlessly combines ResNet-50's feature extraction, ANN's classification robustness, and GSO's optimization for unparalleled performance. This research offers a promising framework for advancing ML methodologies, enhancing accuracy, and efficiency in classification tasks related to MT health.

Machine intelligence based early prediction methods for Cardiovascular Diseases (CVDs)

Exploring early indications of heart disease is challenging in today's society. It may lead to death if not detected early. Early identification of cardiac disease in remote, rural, and semi-urban locations in developing nations can be greatly aided by an accurate decision support system (DSS). To assist in heart-related disease detection at an early stage, this system offers a DSS which uses artificial learning techniques using the patient's clinical details. A hybridized class balancing methodology using the chi2 feature selection algorithm, random oversampling, and undersampling techniques were used to find the suitable features from the presented dataset. Standard scalar approaches have also been utilized for data preprocessing. In the last stage of developing the suggested Artificial Intelligence (AI) system, the system used support vector machines (SVM), naive Bayes, random forest classifiers, logistic regression, and improved Artificial Neural Network (ANN) classifiers. Tests were conducted on the Python-based simulation environment to evaluate the proposed system. Evaluation of the system is completed using the Cleveland heart disease dataset by the machine repository at UCI. A 96.74% accuracy rate was reached, which is better than some previously published models for heart-related disease prediction.

Recurrent Neural Networks and classical machine learning methods for concentrations prediction of aluminum alloy in laser Induced breakdown spectroscopy

Recurrent Neural Networks are classes of Artificial Neural Networks that establish connections between various nodes in a directed or undirected graph for investigation of the temporal dynamical. In this study, different Recurrent Neural Network (RNN) architectures are utilized for quantitative analysis of aluminum alloys by the laser induced breakdown spectroscopy (LIBS) technique. The fundamental harmonic (1064 nm) of a nanosecond Nd:YAG laser pulse is employed to generate the LIBS plasma for the prediction of constituent concentrations of the aluminum standard samples. For the purpose of predicting concentration, Recurrent Neural Networks based on different networks, such as Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Simple Recurrent Neural Network (Simple RNN), and as well as Recurrent Convolutional Networks comprising of Conv-SimpleRNN, Conv-LSTM and Conv-GRU are employed. Then, a comparison is made among prediction by classical machine learning methods of support vector regressor (SVR), the Multilayer Perceptron (MLP), Decision Tree algorithm, Gradient Boosting Regression (GBR), Random Forest Regression (RFR), Linear Regression, and k-Nearest Neighbor (KNN) algorithm. Results demonstrated that the machine learning tools based on Convolutional Recurrent Networks had the best efficiencies in prediction of the most of the elements among other multivariate methods.

Measuring Color Index of Transformer Oil–Enabling Single-Wavelength Spectroscopy With Artificial Neural Network-Fuzzy Logic Model

Conventionally, the color index of transformer oil is determined by a color comparator based on the American Society for Testing and Materials (ASTM) D 1500 standard. The equipment requires humans to operate, which leads to human error and limited number of samples tested per day. This work proposes the utilization of single-wavelength spectroscopy with 405 nm laser diode using artificial neural network (ANN) to determine the color index of transformer oil. Two ANN models were developed using data collected from 50 oil samples with different optical pathlengths of 1 to 10 mm, and laser output powers of 1 to 15 mW. The first model classified the input into different color indices and another model correlated the input parameters through regression analysis to determine the color index. A hybrid ANN-fuzzy logic model was also developed to improve the color index prediction. The root-mean-squared error (RMSE) obtained from the prediction by ANN regressor and ANN classifier are 0.5602 and 0.6416, respectively. The hybrid ANN-fuzzy logic model improves the RMSE especially for optical pathlengths <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&lt;$</tex-math> </inline-formula> 5 mm, which is required for measuring samples with high color index. This proposed method reduces the dependency on complex optoelectronic hardware to obtain highly accurate results. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Unlike the conventional testing method for color index of transformer oil that requires human observation, the findings of this study enables the possibility of compact and smart portable device through the utilization of single wavelength spectroscopy with machine learning models. With no human involvement, more computational power with lesser hardware dependency, the maintenance cost and error can be reduced. This proposed method can potentially be applied to measure the color of other amber-colored liquid products such as olive oil, honey and others.

Masked facial recognition using ensemble convolutional neural network and grey-level co-occurrence matrix

The COVID-19 pandemic proved how face masks became necessary to stop the spread of infection. Due to this, effective identification of people wearing face mask became challenging. Masked facial recognition has significantly increased in accuracy because of developments in convolutional neural networks (CNNs). Small size of the dataset of masked facial images has been a problem in earlier research. As would be expected, this results in poorer accuracy when the model tries to identify faces. In this study, a novel model is proposed with textural feature extraction using grey-level co-occurrence matrix (GLCM) and an ensemble of two pre-trained CNNs DenseNet-121 and VGG-16. Using the minimum redundancy and maximum relevance, the model has improved accuracy by choosing the most important features of the image. The model was trained using in-house dataset that included 38,290 photos of 2,500 people with approximately equal distribution of properly masked, partially masked, and unmasked images. In this, we evaluated the performance of the model on different classifiers multi-class logistic regression (LR) and support vector machine (SVM) with one-vs-rest (OvR) classification and artificial neural network (ANN) and applied a soft voting scheme. The model achieved the highest accuracy of 98.56% at a learning rate of 0.001 on the ANN classifier.

Efficient water-related failure detection in PEM fuel cells: Combining a PEMFCs fractional order impedance model with FFT-PWM techniques and artificial neural network classification

Water management and early detection of faults in proton exchange membrane fuel cells (PEMFCs) are among the most critical constraints that limit the optimal spread of this type of energy. Consequently, it is necessary to enhance the reliability and durability of PEMFCs by developing an approach to diagnose and identify water failure modes. This paper proposes an effective and simple method to detect, diagnose, and classify various water failure modes in PEMFCs using a hybrid diagnostic approach. This approach combines the PEMFC fractional order impedance model (FOIM) with fast Fourier transform pulse width modulation (FFT-PWM) techniques and artificial neural network pattern recognition (ANN-PR) classification. The results show an accurate match between the electrochemical impedance spectroscopy (EIS) experimental data, the Nyquist impedance spectra of FOIM, and the FFT-PWM algorithm as a proposed alternative technique to EIS measurements. Learning of ANN-PR was performed using the frequency spectrum amplitude (FSA) database of the voltage and current signals produced by the PEMFCs FOIM DC/DC boost converter, which was generated using the FFT-PWM algorithm. The ANN-PR achieved low values for error accuracy, with the Low Square Error and Learning Error reaching 6.676 × 10−19 and 1.888 × 10−16, respectively. The elements inside the confusion matrix and the rest of the matrices confirm that the proposed model's accuracy, precision, recall, and high F1 score reached 100%. Furthermore, all predictions made by the ANN-PR model were consistently accurate across all areas of failure detection. Overall, the proposed method helps in analyzing, diagnosing, and classifying fuel cell failure modes such as flooding and drying, which may simplify the health assessment of PEMFC.

Enhanced lung cancer detection: Integrating improved random walker segmentation with artificial neural network and random forest classifier

BackgroundMedical image segmentation is a vital yet difficult job because of the multimodality of the acquired images. It is difficult to locate the polluted area before it spreads. MethodsThis research makes use of several machine learning tools, including an artificial neural network as well as a random forest classifier, to increase the system's reliability of pulmonary nodule classification. Anisotropic diffusion filtering is initially used to remove noise from a picture. After that, a modified random walk method is used to get the region of interest inside the lung parenchyma. Finally, the features corresponding to the consistency of the picture segments are extracted using texture-based feature extraction for pulmonary nodules. The final stage is to identify and classify the pulmonary nodules using a classifier algorithm. ResultsThe studies employ cross-validation to demonstrate the validity of the diagnosis framework. In this instance, the proposed method is tested using CT scan information provided by the Lung Image Database Consortium. A random forest classifier showed 99.6 percent accuracy rate for detecting lung cancer, compared to a artificial neural network's 94.8 percent accuracy rate. ConclusionsDue to this, current research is now primarily concerned with identifying lung nodules and classifying them as benign or malignant. The diagnostic potential of machine learning as well as image processing approaches are enormous for the categorization of lung cancer.

Machine intelligence based early prediction methods for Cardiovascular Diseases (CVDs)

Exploring early indications of heart disease is challenging in today's society. It may lead to death if not detected early. Early identification of cardiac disease in remote, rural, and semi-urban locations in developing nations can be greatly aided by an accurate decision support system (DSS). To assist in heart-related disease detection at an early stage, this system offers a DSS which uses artificial learning techniques using the patient's clinical details. A hybridized class balancing methodology using the chi2 feature selection algorithm, random oversampling, and undersampling techniques were used to find the suitable features from the presented dataset. Standard scalar approaches have also been utilized for data preprocessing. In the last stage of developing the suggested Artificial Intelligence (AI) system, the system used support vector machines (SVM), naive Bayes, random forest classifiers, logistic regression, and improved Artificial Neural Network (ANN) classifiers. Tests were conducted on the Python-based simulation environment to evaluate the proposed system. Evaluation of the system is completed using the Cleveland heart disease dataset by the machine repository at UCI. A 96.74% accuracy rate was reached, which is better than some previously published models for heart-related disease prediction.

Mitigating Peak Sidelobe Levels in Pulse Compression Radar using Artificial Neural Networks

In this paper, Artificial Neural Networks (ANNs) are being considered to obtain low sidelobe pattern for binary codes and thereby to improve the performance of pulse compression radar. Pulse compression is a popular technique used for improving range resolution in the radar systems. This paper proposes a new approach for Pulse Compression using various types of ANN networks like Multi-Layer Perception (MLP), Recursive Neural Networks (RNN), Radial Basis Function (RBF) and Recurrent Radial Basis Function (RRBF) and a special class of Feed-Forward Wavelet Neural Network (WNN) with one input layer, one output layer and one hidden layer are being considered. Networks of 13-bit Barker code and extended binary Barker codes of 35, 55 and 75 length codes were used for the implementation and thereby to improve the performance of pulse compression radar. WNN-based networks using Morlet and Sigmoid activation function in hidden and output layers respectively, a special class of Artificial Neural Network is considered in this paper. The performance metrics used are Peak Sidelobe Ratio (PSLR), Integrated Sidelobe Ratio (ISLR) and Signal-to-Sidelobe Ratio (SSR). Further the performance in terms of range and Doppler resolution is also presented in this paper. Better performance in terms of sidelobe reduction can be achieved with ANNs compared to Autocorrelation Function (ACF) called as matched filter. If the sidelobe values are high there is possibility of masking weaker return signals and there by detection becomes difficult. From this paper it can be established that RRBF gives better result than other ANN networks. Further, WNN gives the best performance even compared with RRBF in terms of sidelobe reduction in pulse compression radar.

Automatic Detection of Epileptic Seizures from EEG Signals Using Artificial Intelligence Methods

Epilepsy is a neurological disorder in which involuntary contractions, sensory abnormalities, and changes occur as a result of abrupt and uncontrolled discharges in the neurons in the brain, which disrupt the systems regulated by the brain. In epilepsy, abnormal electrical impulses from cells in various brain areas are noticed. The accurate interpretation of these electrical impulses is critical in the illness diagnosis. This study aims to use different machine-learning algorithms to diagnose epileptic seizures. The frequency components of EEG data were extracted using parametric approaches. This feature extraction approach was fed into machine learning classification algorithms, including Artificial Neural Network (ANN), Gradient Boosting, and Random Forest. The ANN classifier was shown to have the most significant test performance in this investigation, with roughly 97% accuracy and a 91% F1 score in recognizing epileptic episodes. The Gradient Boosting classifier, on the other hand, performed similarly to the ANN, with 96% accuracy and a 93% F1 score.

Artificial Neural Network Prediction Model for Maternal Health Services Quality in Nigeria

This study presents an innovative approach in predicting the quality of maternal health services in Nigeria using artificial neural networks (ANNs). It focuses on a binary classification task in categorizing maternal health services facilities into "High_Quality" and "Low_Quality" classes. Dataset was collected from diverse healthcare facilities in Nigeria through a WHO Health Resources and Services Availability Monitoring System (HeRAMS) cross sectional-survey report. The collected data was preprocessed; the ANN architecture was developed and trained using back-propagation method. The network was modeled using feed-forward modeling approach with 16 variables at the input layer, 2 hidden layers of 65 and 55 neurons each, and an output of 2 neurons. Hence, 87.17% accuracy with only 2.48% deviation at the 50 epoch was achieved. The model's performance was evaluated using standard metrics of accuracy (87%), precision (88%), recall (89%), and F1-score (88%) to assess its ability to accurately classify maternal health services facilities. The findings of the study can have significant implications to policymakers, healthcare providers, and maternal health advocates to optimize healthcare resources and achieve better maternal health outcomes in Nigeria. Data availability, potential biases in the data, and the subjective nature of some quality-related indicators were acknowledged as limitations. However, despite these challenges, the ANN classification model remains a valuable tool for supporting decision-making in maternal healthcare facility delivery service in Nigeria. Artificial neural network, Binary classification, Health services, Maternal health, Predictive modeling

Solar desalination system for fresh water production performance estimation in net-zero energy consumption building: A comparative study on various machine learning models.

This study employs diverse machine learning models, including classic artificial neural network (ANN), hybrid ANN models, and the imperialist competitive algorithm and emotional artificial neural network (EANN), to predict crucial parameters such as fresh water production and vapor temperatures. Evaluation metrics reveal the integrated ANN-ICA model outperforms the classic ANN, achieving a remarkable 20% reduction in mean squared error (MSE). The emotional artificial neural network (EANN) demonstrates superior accuracy, attaining an impressive 99% coefficient of determination (R2) in predicting freshwater production and vapor temperatures. The comprehensive comparative analysis extends to environmental assessments, displaying the solar desalination system's compatibility with renewable energy sources. Results highlight the potential for the proposed system to conserve water resources and reduce environmental impact, with a substantial decrease in total dissolved solids (TDS) from over 6,000 ppm to below 50 ppm. The findings underscore the efficacy of machine learning models in optimizing solar-driven desalination systems, providing valuable insights into their capabilities for addressing water scarcity challenges and contributing to the global shift toward sustainable and environmentally friendly water production methods.

Sarcasm Detection in Pidgin Tweets Using Machine Learning Techniques

Detecting sarcasm in social media is of growing importance for applications such as monitoring, consumer feedback, and sentiment analysis. However, detecting sarcasm in Pidgin tweets poses unique challenges due to the blend of English and Pidgin languages, along with local cultural references. Existing models for sarcasm detection in English lack appropriate annotated data for Pidgin. This scarcity hinders the development of effective machine learning models. This research aims to address these challenges and create a model for accurate sarcasm detection in Pidgin tweets. Logistic Regression, XGBoost, Random Forest, and Vanilla Artificial Neural Network (ANN) classifiers were assessed, focusing on accuracy, precision, recall, and F1-score metrics on sarcasm data collected by curating and pre-processing a dataset of Nigerian Pidgin tweets. The XGBoost model demonstrated notable performance, attaining an accuracy of 85.78%, precision of 88.57%, recall of 94.44%, and F1-score of 91.41%. These outcomes underscored the model's prowess in discerning sarcastic and non-sarcastic expressions. By unfolding the intricacies of language in the Nigerian context, this research into sarcasm identification in Nigerian Pidgin text data introduced a comprehensive pipeline encompassing data curation, exploratory analysis, culturally tailored pre-processing, model training, evaluation, and prediction.

Enabling Efficient On-Edge Spiking Neural Network Acceleration with Highly Flexible FPGA Architectures

Spiking neural networks (SNNs) promise to perform tasks currently performed by classical artificial neural networks (ANNs) faster, in smaller footprints, and using less energy. Neuromorphic processors are set out to revolutionize computing at a large scale, but the move to edge-computing applications calls for finely-tuned custom implementations to keep pushing towards more efficient systems. To that end, we examined the architectural design space for executing spiking neuron models on FPGA platforms, focusing on achieving ultra-low area and power consumption. This work presents an efficient clock-driven spiking neuron architecture used for the implementation of both fully-connected cores and 2D convolutional cores, which rely on deep pipelines for synaptic processing and distributed memory for weight and neuron states. With them, we developed an accelerator for an SNN version of the LeNet-5 network trained on the MNIST dataset. At around 5.5 slices/neuron and only 348 mW, it is able to use 33% less area and four times less power per neuron as current state-of-the-art implementations while keeping low simulation step times.

Object recognition using cognition based decision tree clustering in multi-level artificial neural network classifier and self similarity as feature criterion

Object recognition using cognition based decision tree clustering in multi-level artificial neural network classifier and self similarity as feature criterion