Neurons In Layer Research Articles

Mission-Driven Inverse Design of Blended Wing Body Aircraft with Machine Learning

The intent of this work was to investigate the feasibility of developing machine learning models for calculating values of airplane configuration design variables when provided time-series, mission-informed performance data. Shallow artificial neural networks were developed, trained, and tested using data pertaining to the blended wing body (BWB) class of aerospace vehicles. Configuration design parameters were varied using a Latin-hypercube sampling scheme. These data were used by a parametric-based BWB configuration generator to create unique BWBs. Performance for each configuration was obtained via a performance estimation tool. Training and testing of neural networks was conducted using a K-fold cross-validation scheme. A random forest approach was used to determine the values of predicted configuration design variables when evaluating neural network accuracy across a blended wing body vehicle survey. The results demonstrated the viability of leveraging neural networks in mission-dependent, inverse design of blended wing bodies. In particular, feed-forward, shallow neural network architectures yielded significantly better predictive accuracy than cascade-forward architectures. Furthermore, for both architectures, increasing the number of neurons in the hidden layer increased the prediction accuracy of configuration design variables by at least 80%.

Outer layer of Vb neurons in medial entorhinal cortex project to hippocampal dentate gyrus in mice.

Entorhinal cortical (EC)-hippocampal (HPC) circuits are crucial for learning and memory. Although it was traditionally believed that superficial layers (II/III) of the EC mainly project to the HPC and deep layers (V/VI) receive input from the HPC, recent studies have highlighted the significant projections from layers Va and VI of the EC into the HPC. However, it still remains unknown whether Vb neurons in the EC provide projections to the hippocampus. In this study, using a molecular marker for Vb and retrograde tracers, we identified that the outer layer of Vb neurons in the medial EC (MEC) directly project to both dorsal and ventral hippocampal dentate gyrus (DG), with a significant preference for the ventral DG. In contrast to the distribution of DG-projecting Vb cells, anterior thalamus-projecting Vb cells are distributed through the outer to the inner layer of Vb. Furthermore, dual tracer injections revealed that DG-projecting Vb cells and anterior thalamus-projecting Vb cells are distinct populations. These results suggest that the roles of MEC Vb neurons are not merely limited to the formation of EC-HPC loop circuits, but rather contribute to multiple neural processes for learning and memory.

Modeling of the biosorption of Fe(III) ions by olive‐stone activated carbon

This study deals with the optimization of Fe(III) ion removal using activated carbon from olive stone waste using advanced machine learning models. The main objective is to evaluate and compare the performance of machine learning models, specifically multilayer perceptron artificial neural network (MLP‐ANN), general regression artificial neural network (GR‐ANN), radial basis function artificial neural network (RBF‐ANN), and particle swarm optimization artificial neural network (PSO‐ANN) in predicting Fe(III) removal efficiency. Experimental data on adsorption parameters were used to train and test the models. Techniques such as tuning hidden layer neurons, optimizing propagation values, and using a Taguchi approach PSO algorithm were applied to improve the models. For the MLP‐ANN model, the optimal configuration contains 13 neurons in the hidden layer. Concerning the parameters involved in the PSO‐ANN model, the coefficient C2 and the particle have the main effect on the reduction of the error. Their contributions are respectively 49% and 19%. The PSO‐ANN model showed superior performance with the highest regression coefficient (0.9997) and remarkable prediction accuracy, surpassing other models such as MLP‐ANN and GR‐ANN. This research suggests that innovative optimization techniques, particularly using PSO algorithms, significantly enhance the predictive capabilities of machine learning models in complex adsorption processes, contributing to more accurate Fe(III) removal models.

Vehicle Driving Safety of Underground Interchanges Using a Driving Simulator and Data Mining Analysis

In the process of driving in an underground interchange, drivers are faced with many challenges, such as being in a closed space, visual changes alternating between light and dark conditions, complex road conditions in the confluence section, and dense signage, which directly affect the safety and comfort of drivers in an underground interchange. Thus, driving simulation, building information modeling (BIM), and data mining were used to analyze the impact of underground interchange safety facilities on driving safety and comfort. Acceleration disturbance and steering wheel comfort loss values were used to assist the comfort analysis. The CART algorithm, classification decision trees, and neural networks were used for data mining, which uses a dichotomous recursive partitioning technique where multiple layers of neurons are superimposed to fit and replace very complex nonlinear mapping relationships. Ten different scenarios were designed for comparison. Multiple linear regression combined with ANOVA was used to calculate the significance of the control variables for each scenario on the evaluation index. The results show that appropriately reducing the length of the deceleration section can improve driving comfort, setting reasonable reminder signs at the merge junction can improve driving safety, and an appropriate wall color can reduce speed oscillation. This study indicates that the placement of traffic safety facilities significantly influences the safety and comfort of driving in underground interchanges. This study may provide support for the optimization of the design of underground interchange construction and internal traffic safety facilities.

Simultaneous spectrophotometric determination of Co (II) and Co (III) in acidic medium with partial least squares regression and artificial neural networks

This study aims at the application of two chemometric techniques to visible spectra of acetic acid solutions of Co (II) and Co (III) for simultaneous determination thereof. Spectral data of 145 samples in the range of 400–700 nm were used to build the models. Partial least squares regression models were developed for which latent variables were determined using internal cross-validation with a leave-one-out strategy and 3 and 2 latent variables were selected for Co(II) and Co(III) based on root mean square error of cross-validation. For these models, root mean square errors of prediction were 1.16 and 0.536 mM and coefficients of determination were 0.975 and 0.892 for Co (II) and Co (III). As an alternate method, artificial neural networks consisting of three layers, with 10 neurons in hidden layer, were trained to model spectra and concentrations of cobalt species. Levenberg-Marquardt algorithm with feed-forward back-propagation learning resulted root mean square errors of prediction of 0.316 and 0.346 mM for Co (II) and Co (III) respectively and coefficients of determination were 0.996 and 0.988.

Developing an intelligent prediction system for successful aging based on artificial neural networks.

Due to the growing number of disabilities in elderly, Attention to this period of life is essential to be considered. Few studies focused on the physical, mental, disabilities, and disorders affecting the quality of life in elderly people. SA1 is related to various factors influencing the elderly's life. So, the objective of the current study is to build an intelligent system for SA prediction through ANN2 algorithms to investigate better all factors affecting the elderly life and promote them. This study was performed on 1156 SA and non-SA cases. We applied statistical feature reduction method to obtain the best factors predicting the SA. Two models of ANNs with 5, 10, 15, and 20 neurons in hidden layers were used for model construction. Finally, the best ANN configuration was obtained for predicting the SA using sensitivity, specificity, accuracy, and cross-entropy loss function. The study showed that 25 factors correlated with SA at the statistical level of P < 0.05. Assessing all ANN structures resulted in FF-BP3 algorithm having the configuration of 25-15-1 with accuracy-train of 0.92, accuracy-test of 0.86, and accuracy-validation of 0.87 gaining the best performance over other ANN algorithms. Developing the CDSS for predicting SA has crucial role to effectively inform geriatrics and health care policymakers decision making.

Spontaneous slow wave oscillations in extracellular field potential recordings reflect the alternating dominance of excitation and inhibition.

In the resting state, cortical neurons can fire action potentials spontaneously but synchronously (Up state), followed by a quiescent period (Down state) before the cycle repeats. Extracellular recordings in the infragranular layer of cortex with a micro-electrode display a negative deflection (depth-negative) during Up states and a positive deflection (depth-positive) during Down states. The resulting slow wave oscillation (SWO) has been studied extensively during sleep and under anaesthesia. However, recent research on the balanced nature of synaptic excitation and inhibition has highlighted our limited understanding of its genesis. Specifically, are excitation and inhibition balanced during SWOs? We analyse spontaneous local field potentials (LFPs) during SWOs recorded from anaesthetised rats via a multi-channel laminar micro-electrode and show that the Down state consists of two distinct synaptic states: a Dynamic Down state associated with depth-positive LFPs and a prominent dipole in the extracellular field, and a Static Down state with negligible ( ) LFPs and a lack of dipoles extracellularly. We demonstrate that depth-negative and -positive LFPs are generated by a shift in the balance of synaptic excitation and inhibition from excitation dominance (depth-negative) to inhibition dominance (depth-positive) in the infragranular layer neurons. Thus, although excitation and inhibition co-tune overall, differences in their timing lead to an alternation of dominance, manifesting as SWOs. We further show that Up state initiation is significantly faster if the preceding Down state is dynamic rather than static. Our findings provide a coherent picture of the dependence of SWOs on synaptic activity. KEY POINTS: Cortical neurons can exhibit repeated cycles of spontaneous activity interleaved with periods of relative silence, a phenomenon known as 'slow wave oscillation' (SWO). During SWOs, recordings of local field potentials (LFPs) in the neocortex show depth-negative deflection during the active period (Up state) and depth-positive deflection during the silent period (Down state). Here we further classified the Down state into a dynamic phase and a static phase based on a novel method of classification and revealed non-random, stereotypical sequences of the three states occurring with significantly different transitional kinetics. Our results suggest that the positive and negative deflections in the LFP reflect the shift of the instantaneous balance between excitatory and inhibitory synaptic activity of the local cortical neurons. The differences in transitional kinetics may imply distinct synaptic mechanisms for Up state initiation. The study may provide a new approach for investigating spontaneous brain rhythms.

Prediction Models Applying Convolutional Neural Network based Deep Learning to Cervical Cancer Outcomes

Early identification of Cervical Cancer (CC) helps in reducing the death rate of CC patients. A Pap smear/Pap test, which is also a widely used method, is used to detect CC in its early stages. The automatic detection and categorization of Pap smear images is a difficult task. So, it is important to design and implement a high-efficiency with low-cost screening system. Therefore, this paper compares the efficiency of two deep learning-based cervical cancer screening strategies. The first technique taken for comparison is the Mutation based Atom Search Optimization (MASO) optimized DenseNet 121 architecture. The MASO technique is used to adjust hyperparameters such as learning rate value, batch sizes, and the number of neurons in the dense layer in the DenseNet 121 architecture. The second technique taken is the Sooty Tern optimized CNN-based Long Short-Term Memory (ST-CNN-LSTM) classifier to identify the different types of cervical cancer stages. The areas affected by the cancer are identified using Kernel-Weighted Fuzzy Local Information C-Means clustering (KWFLICM) model. This model removes the nucleus and cytoplasm from the background area of the cell. Normal, mild dysplastic, severe dysplastic, and carcinoma are among the CC classifications offered by these two classifiers. The efficiency of these classifiers is compared in two datasets (Hervel and SIPaKMeD) via different performance metrics such as specificity, precisions, F-score, accuracy, confusion matrix, sensitivity, and recall. The ST-CNN-LSTM offers improved performance in terms of accuracy (99.80%), sensitivity (98.83%), and specificity (99%) when compared to other classifiers.

Investigation of Hydrodynamics Characteristics of Fluidized Bed with back propagation Artificial Neural Network (BPANN)

Correlations have also been developed with system parameters by using dimensional analysis and an artificial neural network approach. The paper describes an investigation for the thermal design of a fluidized bed cooler and prediction of heat transfer rate among the media categories. It is devoted to the thermal design of such equipment and their application in the industrial fields. In the present work, an extensive ANN by using back propagation (BP) has been carried out to correlate the expansion ratio, fluctuation ratio in gas-solid fluidized bed. Back propagation network is the most well-known and widely used among the current types of neural network system, several applications of ANN for modeling of nonlinear process systems and subsequent control were reported. In back-propagation, different ANN structures (I×H×O) with varying number of neurons in the hidden layer were used as a tool for training input and output data for prediction value of hydrodynamic characteristics of the bed system. It was noted that ring models are the best ones in reducing bed expansion ratio and fluctuation ratio around (25%) and (23.22%).

Astrocytes of the Anterior Commissure Regulate the Axon Guidance Pathways of Newly Generated Neocortical Neurons in the Opossum Monodelphis domestica.

In marsupials, upper-layer cortical neurons derived from the progenitors of the subventricular zone of the lateral ventricle (SVZ) mature morphologically and send their axons to form interhemispheric connections through the anterior commissure. In contrast, eutherians have evolved a new extra callosal pathway, the corpus callosum, that interconnects both hemispheres. In this study, we aimed to examine neurogenesis during the formation of cortical upper layers, including their morphological maturation in a marsupial species, namely the opossum (Monodelphis domestica). Furthermore, we studied how the axons of upper layers neurons pass through the anterior commissure of the opossum, which connects neocortical areas. We showed that upper-layer II/III neurons were generated within at least seven days in the opossum neocortex. Surprisingly, these neurons expressed special AT-rich sequence binding protein 2 (Satb2) and neuropilin 1 interacting protein (Nrp1), which are proteins known to be essential for the formation of the corpus callosum in eutherians. This indicates that extrinsic, but not intrinsic, cues could be key players in guiding the axons of newly generated cortical neurons in the opossum. Although oligodendrocyte precursor cells were present in the neocortex and anterior commissure, newly generated upper-layer neurons sent unmyelinated axons to the anterior commissure. We also found numerous GFAP-expressing progenitor cells in both brain structures, the neocortex and the anterior commissure. However, at P12-P17 in the opossums, a small population of astrocytes was observed only in the midline area of the anterior commissure. We postulate that in the opossum, midline astrocytes allow neocortical axons to be guided to cross the midline, as this structure resembles the glial wedge required by fibers to cross the midline area of the corpus callosum in the rodent.

Optimization of Neurons Number in Artificial Neural Network Model for Predicting the Power Production of PV Module

In this work, an Artificial Neural Network (ANN) with a backward-propagation technique was used to predict the power generation of the Photovoltaic (PV) module in weather conditions of Baghdad city-Iraq. Experiment tests were investigated in the summer of 2022. Three weather parameters, including: (solar radiation, ambient temperature, and wind speed), the output electrical characteristics of the PV module (voltage, current, power), and module temperature (were measured. Therefore, the dataset of the ANN system consists of four input and one output parameter. Furthermore, the structure of ANN includes a single hidden layer with a backward propagation technique. The main goal of this study was to optimize the number of neurons in the training process. The evaluation of the ANN model depended on the determination coefficient (R) and Root Mean Squared Error (RMSE). The obtained results show that the architecture of ANN is appropriate for predicting the power generated from the PV module. The developed ANN model has good accuracy. Where the MSE is 0.002747 at epoch 9 in the model. Furthermore, the R is recorded as 0.99078, 0.98254, 0.99125, and 0.99005 for training, testing, validation, and all respectively in the proposed model. In addition, the optimization number of neurons in the hidden layer gave sufficient accuracy without referring to the choice of the number of neurons by using the trial-and-error method that most researchers relied.

Mass flow rate prediction of a direct-expansion ice thermal storage system using R134a based on dimensionless correlation and artificial neural network

Accurately predicting the refrigerant mass flow rate through the electronic expansion valve (EEV) is crucial for improving the system's performance and achieving intelligent control. However, the refrigerant mass flow rate model applicable to the direct-expansion ice thermal storage (DX-ITS) system for a wide range of flow rates is rare in the open literature. In this study, Buckingham-π theorem and artificial neural network (ANN) are adopted to predict the refrigerant mass flow rate through the EEV of the DX-ITS system using R134a. The dimensionless π-groups and optimal number of neurons in hidden layers of ANN model are obtained. The obtained ANN model shows good accuracy, and over 95.7 % of the predicted data are within the 15 % error band. Results indicate that the EEV outlet pressure has a significant impact on the refrigerant mass flow rate compared with the inlet pressure, the average increase in refrigerant mass flow rate is 43.76 kg/h with an outlet pressure increase of 0.05 MPa. Moreover, the refrigerant mass flow rate gently rises with the increase of superheat temperature under fixed EEV inlet and outlet pressure. On average, every 2 °C increase in superheat temperature leads to an approximately 3.98 kg/h increase in refrigerant mass flow rate.

Enhancing real-time earth–air heat exchanger outlet temperature forecasting in arid climates using artificial neural network: a case study from Bechar, Algeria

Abstract This study improves earth–air heat exchanger (EAHE) outlet temperature forecasting using artificial neural networks (ANNs) to enhance building energy efficiency. Leveraging data from Bechar, Algeria, an arid climate, a FFBPNN with one hidden layer was trained, validated, and tested. Increasing the number of neurons in the hidden layer significantly improved model accuracy. The optimal architecture, with 40 hidden neurons, demonstrated high predictive accuracy, as shown by reduced MSE and increased R2 values across datasets. This research highlights the potential of ANN-based models to optimize EAHE system performance, contributing to energy-efficient building designs, particularly in arid regions.

Bearing remaining useful life prediction with an improved CNN-LSTM network using an artificial gorilla troop optimization algorithm

To address the problem of reliance on a priori knowledge and difficult hyperparameter selection in feature fusion. The effect of different convolutional kernel sizes and filters on feature fusion is investigated firstly, based on which an artificial Gorilla Troops Optimizer (GTO) enhanced Convolutional Long-Short Term Memory Neural Network (CNN-LSTM) method for bearing lifetime prediction is suggested. The GTO algorithm was used to optimize hyperparameters such as the convolutional kernel size of CNN-LSTM, filters and pooling layer size, batch size, number of hidden layer neurons, and rate of learning with the goal of minimizing the mean squared error of the remaining useful life (RUL) prediction. From the optimized CNN-LSTM network analyze the monitored performance degradation data, construct health indicators (HI) reflecting bearing degradation, and build the remaining bearing life prediction model. Typical life cycle data has been used for the validation of the proposed method. The results indicate that the health indicators have better trending and robustness, and leading to smaller errors in life prediction outcomes.

Short-term load forecasting using an Artificial Neural Network for Battery Energy Storage System

Load levelling that use recent spotlighted the Battery Energy Storage System (BESS) saves spare electricity or low cost electricity. The saved electricity can be used for peak power demand time. In this paper, load is predicted for purpose of operating the BESS effectively. By analysing pattern of industrial load, it is classified into workdays, Saturday and holidays. Then apply ANN on workdays load pattern from classified load patterns to predict load. To increase accuracy, number of neurons in hidden layer and learning data period are changed for estimation of load. After that, error rate was calculated for comparison and analysis.

Split Retina as an Improved Flatmount Preparation for Studying Inner Nuclear Layer Neurons in Vertebrate Retina.

Bipolar cells and horizontal cells of the vertebrate retina are the first neurons to process visual information after photons are detected by photoreceptors. They perform fundamental operations such as light adaptation, contrast sensitivity, and spatial and color opponency. A complete understanding of the precise circuitry and biochemical mechanisms that govern their behavior will advance visual neuroscience research and ophthalmological medicine. However, current preparations for examining bipolar and horizontal cells (retinal whole mounts and vertical slices) are limited in their capacity to capture the anatomy and physiology of these cells. In this work, we present a method for removing photoreceptor cell bodies from live, flatmount mouse retinas, providing enhanced access to bipolar and horizontal cells for efficient patch clamping and rapid immunolabeling. Split retinas are prepared by sandwiching an isolated mouse retina between two pieces of nitrocellulose, then gently peeling them apart. The separation splits the retina just above the outer plexiform layer to yield two pieces of nitrocellulose, one containing the photoreceptor cell bodies and another containing the remaining inner retina. Unlike vertical retina slices, the split retina preparation does not sever the dendritic processes of inner retinal neurons, allowing for recordings from bipolar and horizontal cells that integrate the contributions of gap junction-coupled networks and wide-field amacrine cells. This work demonstrates the versatility of this preparation for the study of horizontal and bipolar cells in electrophysiology, immunohistochemistry, and in situ hybridization experiments.

Forecast of wind speed based on MLP network model using Levenberg Marquardt and gradient descent algorithms in Tetouan city, Northern Morocco

This study aims to find the most powerful algorithm between LM and GD, applying them to the multilayer neural network (MLP) to predict the wind speed of the city of Tetouan. To achieve this we will use the meteorological data of this city from 31/07/2017 to 31/08/2022. The MLP adopted for our study is composed of two hidden layers, 30 neurons in the first layer and 15 in the second, 7 inputs and one output. The data is divided into 80% for training and 20% for testing. The results obtained showed that the Levenberg-Marquardt (LM) algorithm is more efficient than the gradient descent (GD) algorithm with a correlation coefficient R = 0.988102 and a mean square error MSE = 0. 0458. These results will allow us to accurately predict the wind speed of August for the year 2022 in this city.

Comparative Analysis of Artificial Neural Network (ANN) and Wavelet Integrated Artificial Neural Network (W-ANN) Approaches for Rainfall Modeling of Southern Rajasthan, India

This paper addresses the challenge of predicting erratic rainfall in Rajasthan state of India, particularly in southern regions. Reliable rainfall predictions are crucial for water resource management and agriculture planning. The research involved selecting 58 stations across seven districts of southern Rajasthan and identifying the best fit computational neural (ANN) and wavelet integrated computational neural (W-ANN) architectures based on performance metrics. Different combinations of input characters, hidden layer neurons, learning algorithms, and training cycles were tested to determine optimal models. Hybrid models, combining wavelet analysis with ANN, were explored to tackle non-stationary hydrologic signals effectively. Results showed that ANN Model C with ten input layer neurons performed best for 74% of stations, followed by Model B (21% of stations) and Model A (5% of stations). Models with increased input and hidden layer neurons performed better. Among the selected stations, 81% of stations demonstrated improved performance using W-ANN models due to effective signal decomposition and information extraction. The hybrid W-ANN models outperformed simple ANN models for rainfall prediction. Both ANN and W-ANN models accurately forecasted weekly rainfall, as observed in the comparison of actual and forecasted values.

The State of Charge Estimation of LiFePO4 Batteries Performance Using Feed Forward Neural Network Model

Lithium-ion batteries like LiFePO4 become a new choice for electrical energy sources in the world and can be used on electric vehicles. Battery packs monitoring by Battery Management System in electric vehicles require accurate monitoring. The inaccuracy of monitoring such property can lead to low safety, low efficiency and battery’s life reduction. Estimating state of charge (SoC) to prevent battery damage from overcharging and over discharging. Some of the methods used to estimate SoC such as Coulomb Counting have errors during the charge and discharge process. This research proposes a counting method for measuring SoC with the artificial neural networks (ANN) to provide more precise estimation. Feed Forward Neural Network (FFNN) is an ANN model that can give an accurate estimation of SoC by learning data of the charge-discharge process performed on sample batteries. The sample batteries are tested with a battery analyzer to get its charging-discharging data consisting of variables such as voltage, current, capacity, and time with C-Rate variations. These variables data are then learned by the modeled FFNN to predict SoC value. The FFNN model consisted of 16 neurons in the first layer, 8 neurons in the second layer, and 4 neurons in the third layer. The predicted SoC value from FFNN has a similar value with its real SoC value. The relationship between SoC and battery voltage is plotted in a curve and shows an identical characteristic with how the SoC-Voltage curve of a battery should be and have a low mae value. This FFNN model can be applied further such as in electric vehicles to maintain its safety and for longer use.

Numerical investigations of the fractional order derivative-based accelerating universe in the modified gravity

In this work, a Liouville–Caputo fractional order (FO) derivative for the mathematical system based on the accelerating universe in the modified gravity (AUMG), i.e. FO-AUMG is proposed to get more accurate solutions. The nonlinear dynamics of the FO-AUMG is classified into five dynamics. The performances of the designed nonlinear FO-AUMG are numerically stimulated with the stochastic procedures of Levenberg–Marquardt backpropagated (LMB) scheme-based neural networks. The statics for FO-AUMS is used for the nonlinear FO-AUMG as 72%, 16% and 12% for training, authorization, and testing. Twenty neurons in hidden layers have been used to approximate the solution of the nonlinear FO-AUMS. The comparison of three different cases of the nonlinear FO-AUMS is performed with dataset generated by Adams method. To validate the uniformity, legitimacy, precision, and competence of LMB-based adaptive neural networks, the outcomes of the state transitions parameters, regression, correlation, error-histogram plots have been exploited.