Sigmoid Activation Function Research Articles

An artificial intelligence model to predict 12-month mortality among patients with myocardial infarction

Abstract Funding Acknowledgements Type of funding sources: None. Background Ischemic heart disease and acute myocardial infarction (AMI) are the number one causes of death and disability, affecting around 126 million individuals worldwide [1]. About 30% of all cases of AMI lead to death. According to different sources, 8-20% of people with AMI die within 1 year of the event, and every second patient is rehospitalized [1-2]. Thus, it is necessary to assess the risk and to predict the outcomes during the first admission to the hospital, in order to guide the management and treatment after AMI [2]. Conventional risk rating scales and methods have a lot of drawbacks, so novel approaches such as artificial intelligence (AI) and deep learning (DL) methods have the potential to provide an accurate risk assessment and share decision-making in patients who experienced AMI [3-4]. Purpose To develop and validate a deep-learning-based risk stratification model to predict the 12-months mortality in patients with AMI. Methods A cohort of 250 AMI patients with Killip class I-IV was enrolled in the study. The data was collected on the admission day and a year after the event and included anamnesis as well as the results of the physical and laboratory-instrumental examination (72 values). All patients were randomly divided into 2 groups: the derivation cohort, which consisted of 215 individuals, and the validation cohort consisted of 35 patients. Our model was created using the Python programming language in GoogleColab and it is a convolutional neural network (CNN) with 1 input layer, 4 hidden layers, and 1 output layer consisting of neurons with a sigmoid activation function (Fig. 1). We used MaxAbsScaler for data normalization and Adam for optimization. Also, we calculated the GRACE risk score and compared the performance of the models only for the validation cohort that was not used for the model development. Results We developed our DL-based model using the derivation data during the 30 cycles of work, receiving the maximum value of training accuracy of 96.7%. The mortality risk, calculated by our model for the validation group was compared with real 12-months mortality, and the CNN "lied" only 2 times (Table 1). The test of the validation cohort showed such results of our DL-based model: 94% - accuracy, 71% - sensitivity, 100% - specificity, 100% - positive, and 93% - negative prognostic value. These results significantly outperformed the GRACE scale, which showed 63%, 71%, 54%, 26%, and 94% respectively. Conclusions In summary, we develop and validate a DL-based risk stratification model to predict the 12-months mortality in patients with AMI. The accuracy of the created model is significantly higher than conventional risk scales (GRACE score). Thus, it is proved that algorithms based on deep learning may be more effective to predict mortality and guide the management of cardiac patients.

Extreme learning machine computational method of modeling energy gap of doped zinc selenide nano-material semiconductor

Zinc selenide (ZnSe) semiconductor belongs to a class of wide energy gap material with low visible region optical absorption, high optical coefficient (nonlinear) and fascinating optoelectronic as well as photocatalytic features which foster and strengthen its applications in resisting thermal shock, photoelectric fields (which include dielectric mirrors, shot wavelength lasers and light emitting diode), buffer layer of solar cell and many photocatalytic environmental cleanliness applications. Nanostructured ZnSe semiconductors occupy a special place in application domain due to the characteristic features attached to the crystallite size of the material which include high fluorescence quantum yields, solvent dispersibility and adjustable emission color among others. Effective utilization of nanostructured ZnSe semiconductor involves tuning of its energy gap through doping mechanisms which is accompanied with distortion in the parent lattice structure. In this contribution, extreme learning machine (ELM) computational intelligent method is proposed for predicting the band gap energy of doped ZnSe nanostructured semiconductor using the material crystallite size and lattice parameter as descriptors to the models. The developed ELM based model using sine (Sine), sigmoid (Sig) and transig (Trang) activation functions were compared with the existing SVR-GA and SPR models in the literature using various performance metrics. The developed Sine-ELM model shows superior performance over Sig-ELM, Trang-ELM, SVR-GA (2021) and SPR (2021) models with performance improvement of 12.74%, 64.89%, 68.87% and 75.62% using mean squared error (MSE) metric for testing data samples. The superiority of the model developed was further justified through validation with external set of data. The precision and superiority of the ELM based models developed would eventually ease quick characterization and tuning of energy gap of ZnSe nanostructured semiconductors for various applications.

Optimizing Parameters of Artificial Intelligence Deep Convolutional Neural Networks (CNN) to improve Prediction Performance of Load Forecasting System

Load Forecasting is an approach that is implemented to foresee the future load demand projected on some physical parameters such as loading on lines, temperature, losses, pressure, and weather conditions etc. This study is specifically aimed to optimize the parameters of deep convolutional neural networks (CNN) to improve the short-term load forecasting (STLF) and Medium-term load forecasting (MTLF) i.e. one day, one week, one month and three months. The models were tested based on the real-world case by conducting detailed experiments to validate their stability and practicality. The performance was measured in terms of squared error, Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). We optimized the parameters using three different cases. In first case, we used single layer with Rectified Linear Unit (ReLU) activation function. In the second case, we used double layer with ReLU – ReLU activation function. In the third case, we used double layer with ReLU – Sigmoid activation function. The number of neurons in each case were 2, 4, 6, 8, 10 and 12. To predict the one day ahead load forecasting, the lowest prediction error was yielded using double layer with ReLU – Sigmoid activation function. To predict ahead one-week load forecasting demands, the lowest error was obtained using single layer ReLU activation function. Likewise, to predict the one month ahead forecasting using double layer with ReLU – Sigmoid activation function. Moreover, to predict ahead three months forecasting using double layer ReLU – Sigmoid activation function produced lowest prediction error. The results reveal that by optimizing the parameters further improved the ahead prediction performance. The results also show that predicting nonstationary and nonlinear dynamics of ahead forecasting require more complex activation function and number of neurons. The results can be very useful in real-time implementation of this model to meet load demands and for further planning.

Hyperspectral Image Classification using Hybrid Deep Convolutional Neural Network

The Hyperspectral Images (HSI) are now being widely popular due to the evolution of satellite imagery and camera technology. Remote sensing has also gained popularity and it is also closely related to HSI. HSI possesses a wide variety of spatial and spectral features. However, HSI also has a consider-able amount of useless or redundant data. This redundant data causes a lot of trouble during classifications as it possesses a huge range in contrast to RGB. Traditional classification techniques do not apply efficiently to HSI. Even if somehow the traditional techniques are applied to it, the results produced are inefficient and undesirable. The Convolutional Neural Network (CNN), which are widely famous for the classification of images, have their fair share of trouble when dealing with HSI. 2D CNNs is not very efficient and 3D CNNs increases the computational complexity. To overcome these issues a new hybrid CNN approach is used which uses sigmoid activation function at the output layer, using a 2D CNN with 3D CNN to generate the desired output. Here, we are using HSI classification using hybrid CNN i.e., 2D and 3D. The dataset used is the Indian pines dataset sigmoid classifier for classification. And we gain the Overall accuracy 99.34 %, average accuracy 99.27%, kappa 99.25%.

Domain Wall Leaky Integrate-and-Fire Neurons With Shape-Based Configurable Activation Functions

Complementary metal oxide semiconductor (CMOS) devices display volatile characteristics, and are not well suited for analog applications such as neuromorphic computing. Spintronic devices, on the other hand, exhibit both non-volatile and analog features, which are well-suited to neuromorphic computing. Consequently, these novel devices are at the forefront of beyond-CMOS artificial intelligence applications. However, a large quantity of these artificial neuromorphic devices still require the use of CMOS, which decreases the efficiency of the system. To resolve this, we have previously proposed a number of artificial neurons and synapses that do not require CMOS for operation. Although these devices are a significant improvement over previous renditions, their ability to enable neural network learning and recognition is limited by their intrinsic activation functions. This work proposes modifications to these spintronic neurons that enable configuration of the activation functions through control of the shape of a magnetic domain wall track. Linear and sigmoidal activation functions are demonstrated in this work, which can be extended through a similar approach to enable a wide variety of activation functions.

Accurate Prediction of Anti-hypertensive Peptides Based on Convolutional Neural Network and Gated Recurrent unit.

Hypertension (HT) is a general disease, and also one of the most ordinary and major causes of cardiovascular disease. Some diseases are caused by high blood pressure, including impairment of heart and kidney function, cerebral hemorrhage and myocardial infarction. Due to the limitations of laboratory methods, bioactive peptides for the treatment of HT need a long time to be identified. Therefore, it is of great immediate significance for the identification of anti-hypertensive peptides (AHTPs). With the prevalence of machine learning, it is suggested to use it as a supplementary method for AHTPs classification. Therefore, we develop a new model to identify AHTPs based on multiple features and deep learning. And the deep model is constructed by combining a convolutional neural network (CNN) and a gated recurrent unit (GRU). The unique convolution structure is used to reduce the feature dimension and running time. The data processed by CNN is input into the recurrent structure GRU, and important information is filtered out through the reset gate and update gate. Finally, the output layer adopts Sigmoid activation function. Firstly, we use Kmer, the deviation between the dipeptide frequency and the expected mean (DDE), encoding based on grouped weight (EBGW), enhanced grouped amino acid composition (EGAAC) and dipeptide binary profile and frequency (DBPF) to extract features. For Kmer, DDE, EBGW and EGAAC, it is widely used in the field of protein research. DBPF is a new feature representation method designed by us. It corresponds dipeptides to binary numbers, and finally obtains a binary coding file and a frequency file. Then these features are spliced together and input into our proposed model for prediction and analysis. After a tenfold cross-validation test, this model has a better competitive advantage than the previous methods, and the accuracy is 96.23% and 99.10%, respectively. From the results, compared with the previous methods, it has been greatly improved. It shows that the combination of convolution calculation and recurrent structure has a positive impact on the classification of AHTPs. The results show that this method is a feasible, efficient and competitive sequence analysis tool for AHTPs. Meanwhile, we design a friendly online prediction tool and it is freely accessible at http://ahtps.zhanglab.site/ .

New approach to computer-aided learning based on digital library user behavior

The author introduces the mathematical model of recurrent neural network with external memory. It is intended for predicting efficient education trajectory in digital information environments, e. g. digital libraries. The goal of computer-aided learning based on neural networks is to personalize user trajectories. In the study, user behavior is modeled for the more precise personalization in various aspects using recurrent neural networks. The method is designed for two types of recurrent neural networks, i. e. the classic one with sigmoidal activation function and that with LSTM (Long Short-Term Memory). The experiments demonstrated serious advantages of recurrent neural networks over analogous methods in predicting education trajectory. Thus, the proposed model is the more efficient in predictive accuracy (by 15–20% higher than analogous methods). Its prime application area is prediction of optimum user education trajectory in the digital information environment, and digital library, in particul

FPGA Implementation for the Sigmoid with Piecewise Linear Fitting Method Based on Curvature Analysis

The sigmoid activation function is popular in neural networks, but its complexity limits the hardware implementation and speed. In this paper, we use curvature values to divide the sigmoid function into different segments and employ the least squares method to solve the expressions of the piecewise linear fitting function in each segment. We then adopt an optimization method with maximum absolute errors and average absolute errors to select an appropriate function expression with a specified number of segments. Finally, we implement the sigmoid function on the field-programmable gate array (FPGA) development platform and apply parallel operations of arithmetic (multiplying and adding) and range selection at the same time. The FPGA implementation results show that the clock frequency of our design is up to 208.3 MHz, while the end-to-end latency is just 9.6 ns. Our piecewise linear fitting method based on curvature analysis (PWLC) achieves recognition accuracy on the MNIST dataset of 97.51% with a deep neural network (DNN) and 98.65% with a convolutional neural network (CNN). Experimental results demonstrate that our FPGA design of sigmoid function can obtain the lowest latency, reduce absolute errors, and achieve high recognition accuracies, while the hardware cost is acceptable in practical applications.

Fast nonlinear Hoyergram for bearings fault diagnosis under random impact interference

Random impact interference has always been an important subject in fault diagnosis. In the fast kurtogram (FK), kurtosis is a sparsity index used to locate optimal resonance frequency bands. However, the shortcomings of the kurtosis measure are a tendency to select the random impact with a large amplitude and a relatively weak sparse measure ability, which reduces the accuracy and anti-interference of the FK method. To overcome the effects of random impact interference, this paper proposes a novel bearing fault diagnosis method named the fast nonlinear Hoyergram (FNH), in which the nonlinear Hoyer index is employed to replace kurtosis to improve the fault representation capability under random impulse interference. Firstly, Z-score normalization and a generalized nonlinear sigmoid activation function are used for signal preprocessing, and the scale distribution of the signal is changed to weaken the impact of random impact interference. Secondly, the Hoyer index, which can be viewed as the normalized form of the norm, is used to replace kurtosis to improve the sparsity measure capability. Thirdly, in the Hoyergram, the frequency band with the largest Hoyer value can be chosen as the best resonance frequency band for the squared envelope analysis. Finally, the proposed FNH is compared with the FK method through simulation and experimental signals, and the effectiveness of the proposed method is verified.

Multistability analysis of delayed recurrent neural networks with a class of piecewise nonlinear activation functions

This paper studies the multistability of delayed recurrent neural networks (DRNNs) with a class of piecewise nonlinear activation functions. The coexistence as well as the stability of multiple equilibrium points (EPs) of DRNNs are proved. With the Brouwer’s fixed point theorem as well as the Lagrange mean value theorem, it is obtained that under some conditions, the n-neuron DRNNs with the proposed activation function can have at least 5n EPs and 3n of them are locally stable. Compared with the DRNNs with sigmoidal activation functions, DRNNs with this kind of activation function can have more total EPs and more locally stable EPs. It implies that when designing DRNNs with the proposed activation function to apply in associative memory, it can have an even larger storage capacity. Furthermore, it is obtained that there exists a relationship between the number of the total EPs/stable EPs and the frequency of the sinusoidal function in the proposed activation function. Last, the above obtained results are extended to a more general case. It is shown that, DRNNs with the extended activation function can have (2k+1)n EPs, (k+1)n of which are locally stable, therein k is closely related to the frequency of the sinusoidal function in the extended activation function. Two simulation examples are given to verify the correctness of the theoretical results.

Developing neural networks-based prediction model of real-time fuel consumption rate for motorcycles: A case study in Vietnam

ABSTRACT This paper presents a study on simulation of the on-road fuel consumption for motorcycles using the Neural Networks. Ten representative streets in the inner city of Hanoi were selected to collect the on-road operation characteristics of the test motorcycle, consisting of instantaneous speed and fuel consumption rate. The collected data, including 14,000 data points, was divided into 70% for the training process and 30% for the validating and testing process. An ANN architecture consisting of one layer of suitable input variables, two hidden layers with 20 neurons, and one layer of output fuel consumption rate was proposed. The Levenberg-Marquardt ANN fitting tool and the sigmoid activation function were used in developing model architecture. Three powerful input variables were identified, consisting of instantaneous speed, acceleration of motorcycle, and engine revolution speed. In the model development, the mean absolute percentage errors were 5.10% and 11.10%, and the correlation coefficient R values were greater than 0.8 for the training and testing dataset. The developed model performance was post-evaluated using on-road and laboratory datasets. More than 75.40% of the predicted instantaneous fuel consumption values had a relative deviation less than 20% compared to the on-road measured values. The difference in average fuel consumption (L/100 km) between predicted and measured values was less than 10%. Following the datasets from the laboratory test on the motorcycle chassis dynamometer AVL CD20”, including the World motorcycle test cycle and Hanoi motorcycle driving cycle, the fuel consumption rate determined using the developed model correlated well with the measured ones, with the R2 values were 0.67 and 0.72.

Coefficient bounds for Al-Oboudi type bi-univalent functions connected with a modified sigmoid activation function and k -Fibonacci numbers

Using the Al-Oboudi type operator, we present and investigate two special families of bi-univalent functions connected with the activation function \(% \phi (s)=\ 2/(1+e^{-s}),\,s\in \mathbb{R}\) and \(k\)-Fibonacci numbers. We derive the bounds on initial coefficients and the Fekete-Szego functional for functions of the type \(g_{\phi }(z)=z+\sum \limits_{j=2}^{\infty }\phi (s)d_{j}z^{j}\) in these introduced families. Furthermore, we present interesting observations of the results investigated.

A sigmoid‐optimized encoder–decoder network for crack segmentation with copy‐edit‐paste transfer learning

AbstractThe automatic recognition of cracks is an essential requirement for the cost‐efficient maintenance of concrete structures, such as bridges, buildings, and roads. It should allow the localization and the determination of the crack type and the evaluation of the crack severity by providing information on the shape, orientation, and crack area and width. The first step in this direction is the automatized segmentation of cracks. This paper provides a concrete crack data set (370 images) and proposes two solutions that achieve the best results on two different crack data sets. Our first solution concerns the segmentation architecture. We provide an encoder–decoder‐based network with a particular interconnection of layers between the encoder and decoder parts that outperforms several other methods. In addition, this network is enhanced by squeeze‐and‐excitation blocks equipped with a modified sigmoid activation function. We introduce a stretch coefficient into the sigmoid function and declare it a trainable parameter, allowing more differentiated calibration of the feature map during network training. Our second solution concerns kernel initialization by transfer learning (TL). We propose the Copy‐Edit‐Paste Transfer Learning (CEP TL). By copying, geometric editing, and pasting crack masks onto new concrete background images, we generate thousands of semisynthetic images used to pretrain the network. This CEP TL method increases model performance with significant differences. For data set A (ours), we achieve F1‐scores 76.06 ± 0.06% without CEP TL and 92.32 ± 0.82% with CEP TL. For data set B (DeepCrack data set), we achieve F1‐scores 88.56 ± 0.01% without CEP TL and 90.59 ± 0.80% with CEP TL.

A novel rolling bearing fault diagnosis method based on generalized nonlinear spectral sparsity

In the fast kurtogram (FK), kurtosis is used as an indicator to locate the fault frequency band, and is widely aplied to fault diagnosis. However, kurtosis has been proven to favor a single large impulse rather than the required small fault characteristics, especially in the strong interference environment. To eliminate the impact of large-amplitude impact and further improve the accuracy of fault extraction, a method based on generalized nonlinear spectral sparsity (GNSS) is proposed for fault diagnosis of bearings. First, Z-score normalization and generalized nonlinear sigmoid activation function are used for signal preprocessing, and the scale distribution of the signal will be changed to eliminate the effects of large amplitude shocks under noisy environment. Then, to improve the sparsity measure capability, an improved L3/2 norm is used to replace kurtosis as the basis for selecting the best resonance frequency band. Finally, the effectiveness of the GNSS is verified by simulation data and experimental data. Compared with FK method, the performance of fault extraction of the proposed method is significantly improved, especially for the interference of abnormal impact.

Predictability of higher heating value of biomass feedstocks via proximate and ultimate analyses – A comprehensive study of artificial neural network applications

Higher heating value (HHV) is a key characteristic for the assessment and selection of biomass feedstocks as a fuel source. The HHV is usually measured using an adiabatic oxygen bomb calorimeter; however, this method can be time consuming and expensive. In response, researchers have attempted to use artificial neural network (ANN) systems to predict HHV using proximate and ultimate analysis data, but these efforts were hampered by varying case specific approaches and methodologies. Based on the complex ANN structures, a clear state of the art ANN understanding must be required for the prediction of biomass HHV. This study provides a comprehensive ANN application for HHV prediction in terms of how the activation functions, algorithms, hidden layers, dataset, and randomisation of the dataset affects the prediction of HHV of biomass feedstocks. In this paper we present a comparative qualitative and quantitative analysis of thirteen different algorithms, four different activation functions (logsig, tansig, poslin, purelin) with a wide range of hidden layer (3–15) for ANN models, used to predict the HHV of the biomass feedstocks. ANN models trained by the combination of ultimate-proximate analyses (UAPA) datasets provided more accurate predictions than the models trained by ultimate analysis or proximate analysis datasets. Regardless of the used datasets, sigmoidal activation functions (tansig and logsig) provide better prediction results than linear activation function (poslin and purelin). Furthermore, as training activation functions, “Levenberg-Marquardt (lm)” and “Bayesian Regularization (br)” algorithms provide the best HHV prediction. The best average correlation coefficients of 30 randomised run were observed with tansig as 0.962 and 0.876 for the ANN model developed by the UAPA dataset with a relatively high confidence levels of ∼96% for training and ∼92% for testing.

Suboptimal Local Minima Exist for Wide Neural Networks with Smooth Activations

Does a large width eliminate all suboptimal local minima for neural nets? An affirmative answer was given by a classic result published in 1995 for one-hidden-layer wide neural nets with a sigmoid activation function, but this result has not been extended to the multilayer case. Recently, it was shown that, with piecewise linear activations, suboptimal local minima exist even for wide nets. Given the classic positive result on smooth activation and the negative result on nonsmooth activations, an interesting open question is: Does a large width eliminate all suboptimal local minima for deep neural nets with smooth activation? In this paper, we give a largely negative answer to this question. Specifically, we prove that, for neural networks with generic input data and smooth nonlinear activation functions, suboptimal local minima can exist no matter how wide the network is (as long as the last hidden layer has at least two neurons). Therefore, the classic result of no suboptimal local minimum for a one-hidden-layer network does not hold. Whereas this classic result assumes sigmoid activation, our counterexample covers a large set of activation functions (dense in the set of continuous functions), indicating that the limitation is not a result of the specific activation. Together with recent progress on piecewise linear activations, our result indicates that suboptimal local minima are common for wide neural nets.

Technip Energies gets FEED contract for Encina[StQuote]s commercial PFCC unit

One of the most promising renewable energy sources (RES) is photovoltaic energy system. It generates power by using a photovoltaic (PV) module. The solar illumination and temperature value are the main parameters for the PV module because a small change can affect the entire power generation. The PV module is based on the double diode equation for extracting unknown parameter values and tracking maximum power point using basic analytical methods (Newton Raphson and Lambert W-function), particle swarm optimization (PSO) and artificial neural network (ANN) algorithms are performed. Then, a deep neural network (DNN) algorithm is proposed in this work for alleviating the disadvantages of the existing methods. Particularly, the DNN algorithm is proposed for reducing the mismatching power loss. Firstly, two-parameter values retrieve from a specific location at NASA open-access source for the year 2020. Then, the parameter values optimization through two analytical methods such as Newton Raphson (NR) and Lambert-W function (W-function) methods. Based on these analytical methods, the characteristic curve is executed. It is compared one among one and also the analytical methods evaluates with soft computing algorithms. The soft computing algorithm represents particle swarm optimization and the artificial neural network. Both the analytical methods and the soft computing algorithms compare for the extraction of the unknown parameter value for the PV module. Then, the existing algorithm is compared with advanced soft computing algorithms. In that deep neural network, the algorithm is implemented for the maximum power point tracking (MPPT) process. The DNN algorithm contains two inputs, three hidden layers and one output. The input neuron is defined with the voltage and current value and the hidden layer contains the sigmoid activation function. The result evaluates in terms of percentage of error for maximum power point (PEmpp).

Deep learning for sleep stages classification: modified rectified linear unit activation function and modified orthogonal weight initialisation

Background and Aim: Each stage of sleep can affect human health, and not getting enough sleep at any stage may lead to sleep disorder like parasomnia, apnea, insomnia, etc. Sleep-related diseases could be diagnosed using Convolutional Neural Network Classifier. However, this classifier has not been successfully implemented into sleep stage classification systems due to high complexity and low accuracy of classification. The aim of this research is to increase the accuracy and reduce the learning time of Convolutional Neural Network Classifier. Methodology: The proposed system used a modified Orthogonal Convolutional Neural Network and a modified Adam optimisation technique to improve the sleep stage classification accuracy and reduce the gradient saturation problem that occurs due to sigmoid activation function. The proposed system uses Leaky Rectified Linear Unit (ReLU) instead of sigmoid activation function as an activation function. Results: The proposed system called Enhanced Sleep Stage Classification system (ESSC) used six different databases for training and testing the proposed model on the different sleep stages. These databases are University College Dublin database (UCD), Beth Israel Deaconess Medical Center MIT database (MIT-BIH), Sleep European Data Format (EDF), Sleep EDF Extended, Montreal Archive of Sleep Studies (MASS), and Sleep Heart Health Study (SHHS). Our results show that the gradient saturation problem does not exist anymore. The modified Adam optimiser helps to reduce the noise which in turn result in faster convergence time. Conclusion: The convergence speed of ESSC is increased along with better classification accuracy compared to the state of art solution.

Investigating the corrosion performance of Ti-6Al-4V biomaterial alloy with hydroxyapatite coating by artificial neural network

As a result of its excellent mechanical characteristics and bio-compatibility, the Ti-6Al-4V alloy offers a wide-ranging applications in the medical industry. However, long-term application of these alloys may lead to a decline in corrosion resistance as well as other serious problems in these alloys. To resolve these problems, it is possible to modify the implant surface to enhance the corrosion and bio-compatibility properties. On the Ti-6Al-4V substrate surface, the TiN coating was applied by the Plasma-Assisted Chemical Vapour Deposition (PACVD) method together with the hydroxyapatite coating (HA) using the sol–gel method. Furthermore, the corrosion performance of bio-active hydroxyapatite layer coating on Ti-6Al-4V implant surface was evaluated through the application of the Artificial Neural Network (ANN) and Gene Expression Programming (GEP) models. The generated models were analysed and compared to a response surface methodology (RSM). The hydroxyapatite sol–gel parameters on Ti-6Al-4V implant materials were used as independent variables (input variables). The Ecorr values computed from potentiodynamic polarization measurements were used as a dependent variable (output variable) in the models. The results of the ANN technique (sigmoid activation function, LM training algorithm and 9 neurons in hidden layer) were in good consistent with the experimental Ecorr values, indicating this model is slightly better than the GEP and RSM models. Finally, the findings demonstrated that the ANN technique is an appropriate and robust tool for quantitative modeling of corrosion resistance, and that it can be applied to a variety of surface engineering applications.

Feedback Control Systems Stabilization Using a Bio-inspired Neural Network

The proportional–integral–derivative (PID) control systems, which have become a standard for technical and industrial applications, are the fundamental building blocks of classical and modern control systems. In this paper, a three-layer feed-forward neural network (NN) model trained to replicate the behavior of a PID controller is employed to stabilize control systems through a NN feedback controller. A novel bio-inspired weights-and-structure-determination (BIWASD) algorithm, which incorporates a metaheuristic optimization algorithm dubbed beetle antennae search (BAS), is used to train the NN model. More presicely, the BIWASD algorithm identifies the ideal weights and structure of the BIWASD-based NN (BIWASDNN) model utilizing a power sigmoid activation function while handling model fitting and validation. The results of three simulated trials on stabilizing feedback control systems validate and demonstrate the BIWASDNN model’s exceptional learning and prediction capabilities, while achieving similar or better performance than the corresponding PID controller. The BIWASDNN model is compared to three other high-performing NN models, and a MATLAB repository is accessible in public through GitHub to encourage and enhance this work.