Standard Artificial Neural Network Research Articles

Data Information integrated Neural Network (DINN) algorithm for modelling and interpretation performance analysis for energy systems

Developing a well-predictive machine learning model that also offers improved interpretability is a key challenge to widen the application of artificial intelligence in various application domains. In this work, we present a Data Information integrated Neural Network (DINN) algorithm that incorporates the correlation information present in the dataset for the model development. The predictive performance of DINN is also compared with a standard artificial neural network (ANN) model. The DINN algorithm is applied on two case studies of energy systems namely energy efficiency cooling (ENC) & energy efficiency heating (ENH) of the buildings, and power generation from a 365 MW capacity industrial gas turbine. For ENC, DINN presents lower mean RMSE for testing datasets (RMSE_test = 1.23 %) in comparison with the ANN model (RMSE_test = 1.41 %). Similarly, DINN models have presented better predictive performance to model the output variables of the two case studies. The input perturbation analysis following the Gaussian distribution for noise generation reveals the order of significance of the variables, as made by DINN, can be better explained by the domain knowledge of the power generation operation of the gas turbine. This research work demonstrates the potential advantage to integrate the information present in the data for the well-predictive model development complemented with improved interpretation performance thereby opening avenues for industry-wide inclusion and other potential applications of machine learning.

Uncertainty Quantification of Machine Learning Model Performance via Anomaly-Based Dataset Dissimilarity Measures

The use of Machine Learning (ML) models as predictive tools has increased dramatically in recent years. However, data-driven systems (such as ML models) exhibit a degree of uncertainty in their predictions. In other words, they could produce unexpectedly erroneous predictions if the uncertainty stemming from the data, choice of model and model parameters is not taken into account. In this paper, we introduce a novel method for quantifying the uncertainty of the performance levels attained by ML classifiers. In particular, we investigate and characterize the uncertainty of model accuracy when classifying out-of-distribution data that are statistically dissimilar from the data employed during training. A main element of this novel Uncertainty Quantification (UQ) method is a measure of the dissimilarity between two datasets. We introduce an innovative family of data dissimilarity measures based on anomaly detection algorithms, namely the Anomaly-based Dataset Dissimilarity (ADD) measures. These dissimilarity measures process feature representations that are derived from the activation values of neural networks when supplied with dataset items. The proposed UQ method for classification performance employs these dissimilarity measures to estimate the classifier accuracy for unseen, out-of-distribution datasets, and to give an uncertainty band for those estimates. A numerical analysis of the efficacy of the UQ method is conducted using standard Artificial Neural Network (ANN) classifiers and public domain datasets. The results obtained generally demonstrate that the amplitude of the uncertainty band associated with the estimated accuracy values tends to increase as the data dissimilarity measure increases. Overall, this research contributes to the verification and run-time performance prediction of systems composed of ML-based elements.

Utilizing neural networks to supplant chemical kinetics tabulation through mass conservation and weighting of species depletion

Artificial Neural Networks (ANNs) have emerged as a powerful tool in combustion simulations to replace memory-intensive tabulation of integrated chemical kinetics. Complex reaction mechanisms, however, present a challenge for standard ANN approaches as modeling multiple species typically suffers from inaccurate predictions on minor species. This paper presents a novel ANN approach which can be applied on complex reaction mechanisms in tabular data form, and only involves training a single ANN for a complete reaction mechanism. The approach incorporates a network architecture that automatically conserves mass and employs a particular loss weighting based on species depletion. Both modifications are used to improve the overall ANN performance and individual prediction accuracies, especially for minor species mass fractions. To validate its effectiveness, the approach is compared to standard ANNs in terms of performance and ANN complexity. Four distinct reaction mechanisms (H2, C7H16, C12H26, OME34) are used as a test cases, and results demonstrate that considerable improvements can be achieved by applying both modifications.

Deep Learning Algorithms for Sports Data Analysis and Prediction in Sports Competitions

Abstract Sports data analysis and prediction are essential for gaining a competitive advantage in today’s sports. Artificial Neural Networks (ANNs) have shown promising outcomes in several disciplines, including sports analytics. Sports data is dynamic and complex, making it difficult for standard ANNs to identify minute patterns in it. We introduce a new Puzzle-Optimized Artificial Neural Network (PO-ANN) in this work, which is intended for sports data processing and prediction. The PO-ANN is optimized using a puzzle-inspired method to enhance the network’s ability to identify and comprehend complex patterns in the data. The technique constantly modifies the weights and network topology, enabling the model to better react to the shifting dynamics of sports competitions. The Indian Premier League provided the dataset, which consists of 950 matches and 20 variables (IPL). We implemented our proposed PO-ANN and forecast accuracy in sports data analysis and prediction using Python. We performed a comparison analysis between our suggested PO-ANN approach and other existing methods, using numerous metrics, including MSE, MAE, and MAPE. The suggested POANN technique produced better outcomes than the previous approaches.

A Novel Physically Guided Data Fusion Prediction Model for Micro-EDM Drilling

Accurate prediction of Electro-Discharge Machining (EDM) results is crucial for industrial applications, aiming to achieve high-performance and cost-efficient machining. However, both the current physical model and the standard Artificial Neural Network (ANN) model exhibit inherent limitations, failing to fully meet the accurate requirements for predicting EDM machining results. In addition, Micro-EDM Drilling can lead to the distortion of the macroscopic shape of machining pits under different input conditions, rendering the use of only the volume of machining pits as the evaluation index insufficient to express the complete morphological information. In this study, we propose a novel hybrid prediction model that combines the strengths of both physical and data-driven models to simultaneously predict Material Removal Rate (MRR) and shape parameters. Our experiment demonstrates that the hybrid model achieves a maximum prediction error of 4.92% for MRR and 5.28% for shape parameters, showcasing excellent prediction accuracy and stability compared to the physical model and the standard ANN model.

A novel framework for wave power plant site selection and wave forecasting based on GIS, MCDM, and ANN methods: A case study in Hainan Island, Southern China

Wave power plants (WPPs) hold significant promise for sustainable energy generation but face complex challenges in site selection and wave forecasting. To address these challenges, this study presents an integrated methodology that combines geographic information system (GIS), multi-criteria decision making (MCDM) and artificial neural network (ANN) techniques. The primary objective of this research is to identify optimal sites for WPP deployment and enhance the accuracy of wave power density (WPD) forecasting. The study focuses on Hainan Island, the second-largest island in China, and employs both macro-scale and micro-scale site selection methods. It establishes a comprehensive criteria system that encompasses environmental, technical, economic, and social aspects. To improve the objectivity of criteria weighting, a group decision making-analytic hierarchy process (GDM-AHP) approach is applied. The findings reveal that approximately 1.36 % (1427.93 km2) of Hainan Island's area offers suitable conditions for WPP deployment, with concentrations in the southern, northern, and eastern marine regions. Among the 27 identified alternative sites covering 208.76 km2 along the eastern coast, six optimal sites are pinpointed in Wanning, Wenchang, and Qionghai. Furthermore, the optimized ANN outperforms the standard ANN, achieving a mean relative error of 9.0 %. This research contributes to the theoretical understanding of WPP site selection and wave forecasting while offering a practical and adaptable framework for stakeholders involved in renewable energy projects, particularly in coastal areas such as Hainan Island. These results and methodologies have real-world implications for the efficient and effective deployment of wave energy projects, ultimately promoting sustainable energy generation and socioeconomic development.

Effect of ultrasound‐assisted thin bed drying for retaining the quality of red bell pepper and compare the predictive ability of the mathematical model with artificial neural network

AbstractRed bell peppers (Capsicum annuum L.) are low in calories and high in nutrients, including vitamins A and C. Various factors such as weight loss, senescence, and microbial influence affect their quality during storage. To address this, the present study aims to preserve and retain the quality of red bell peppers using ultrasound‐assisted thin‐bed drying. The results were analyzed using an Artificial Neural Network (ANN) for more accurate prediction of variables involved in the process. Variations in moisture ratio and moisture content during drying were calculated and predicted. The Midilli model provided satisfactory curve fitting at an air velocity of 1.5 m/s, with R2 = 0.9993, χ2 = 0.0002, and RMSE = 0.0134. The two‐term and modified page models fit better with drying curves at air velocities of 2 and 2.5 m/s, with R2 = 0.9995, χ2 = 0.002, RMSE = 0.0016 and R2 = 0.9996, χ2 = 0.00003, RMSE = 0.00003, respectively. However, the trained standard backpropagation ANN algorithm demonstrated excellent predictive ability, outperforming the mathematical models with R2 = 0.9989 (training), MSE = 0.0001 (training), and R2 = 0.9996 (testing), MSE = 0.0002 (testing). Most importantly, the ultrasound‐assisted drying process retains the essential nutrients in red bell peppers, including vitamin C, carotenoids, polyphenols, and flavonoids, across various conditions. The antioxidant potential, as measured by DPPH and FRAP assays, remains largely unchanged compared to untreated samples. However, ABTS activity shows a significant difference at an air velocity of 1.5 m/s and temperatures of 60 and 70°C compared to the control sample.Practical applicationsIn terms of vitamins and antioxidants, red bell peppers are a great provider. Interestingly, capsaicin, the substance responsible for spiciness, is found in very little to no quantity in red bell peppers making it appealable to consumers. To achieve a certain level of processing, the quality of the dried product needs to be monitored while fulfilling the needs of consumers. Particularly, the quality‐determining parameters were vitamin C, total carotenoids, total polyphenols, total flavonoid content, DPPH, ABTS, and FRAP activity. These qualities were retained after drying with the potential novel combination of ultrasound with thin bed drying at low temperatures and air velocity. This means that the bioactive compounds responsible for improving the health of humans are readily available in dried form all year round. The drying kinetics were modeled, predicted, and compared with mathematical and ANN models.

Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing

AbstractIn financial engineering, prices of financial products are computed approximately many times each trading day with (slightly) different parameters in each calculation. In many financial models such prices can be approximated by means of Monte Carlo (MC) simulations. To obtain a good approximation the MC sample size usually needs to be considerably large resulting in a long computing time to obtain a single approximation. A natural deep learning approach to reduce the computation time when new prices need to be calculated as quickly as possible would be to train an artificial neural network (ANN) to learn the function which maps parameters of the model and of the financial product to the price of the financial product. However, empirically it turns out that this approach leads to approximations with unacceptably high errors, in particular when the error is measured in the ‐norm, and it seems that ANNs are not capable to closely approximate prices of financial products in dependence on the model and product parameters in real life applications. This is not entirely surprising given the high‐dimensional nature of the problem and the fact that it has recently been proved for a large class of algorithms, including the deep learning approach outlined above, that such methods are in general not capable to overcome the curse of dimensionality for such approximation problems in the ‐norm. In this article we introduce a new numerical approximation strategy for parametric approximation problems including the parametric financial pricing problems described above and we illustrate by means of several numerical experiments that the introduced approximation strategy achieves a very high accuracy for a variety of high‐dimensional parametric approximation problems, even in the ‐norm. A central aspect of the approximation strategy proposed in this article is to combine MC algorithms with machine learning techniques to, roughly speaking, learn the random variables (LRV) in MC simulations. In other words, we employ stochastic gradient descent (SGD) optimization methods not to train parameters of standard ANNs but instead to learn random variables appearing in MC approximations. In that sense, the proposed LRV strategy has strong links to Quasi‐Monte Carlo (QMC) methods as well as to the field of algorithm learning. Our numerical simulations strongly indicate that the LRV strategy might indeed be capable to overcome the curse of dimensionality in the ‐norm in several cases where the standard deep learning approach has been proven not to be able to do so. This is not a contradiction to the established lower bounds mentioned above because this new LRV strategy is outside of the class of algorithms for which lower bounds have been established in the scientific literature. The proposed LRV strategy is of general nature and not only restricted to the parametric financial pricing problems described above, but applicable to a large class of approximation problems. In this article we numerically test the LRV strategy in the case of the pricing of European call options in the Black‐Scholes model with one underlying asset, in the case of the pricing of European worst‐of basket put options in the Black‐Scholes model with three underlying assets, in the case of the pricing of European average put options in the Black‐Scholes model with three underlying assets and knock‐in barriers, as well as in the case of stochastic Lorentz equations. For these examples the LRV strategy produces highly convincing numerical results when compared with standard MC simulations, QMC simulations using Sobol sequences, SGD‐trained shallow ANNs, and SGD‐trained deep ANNs.

EXTRACTION OF PHENOLIC COMPOUNDS FROM FENUGREEK SEEDS: MODELLING AND ANALYSIS USING ARTIFICIAL NEURAL NETWORKS

This study introduces the modeling and analysis of the extraction process of bioactive compounds from fenugreek seeds in different solid-to-solvent ratios (0.5-60 g/L) and extraction times. Maceration was applied with agitation for the extraction processes and total phenolic compounds, total flavonoid content and antioxidant activity of the extracts were measured as experimental data. The amount of extractable phenolic compounds having antioxidant effect was increased by adjusting the solid-to-solvent ratio. According to obtained results, the highest values were determined as 12564.08±376.88 mg gallic acid/100 g dry sample, 7540.44±39.67 mg quercetin/100 g dry sample and 1904.80±17.43 mM Trolox/100 g dry sample for total phenolic compounds, total flavonoid content, and antioxidant activity, respectively. The extraction process was modeled using standard Artificial Neural Networks (ANN) and Pi-Sigma Neural-Networks (PSNN). The PSNN model had a higher prediction efficiency with lower RMSE (%) values varied between 0.94% and 1.30% for both training and testing.

DIET-SNN: A Low-Latency Spiking Neural Network With Direct Input Encoding and Leakage and Threshold Optimization.

Bioinspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding and suboptimal settings of the neuron parameters (firing threshold and membrane leak). We propose DIET-SNN, a low-latency deep spiking network trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The membrane leak and threshold of each layer are optimized with end-to-end backpropagation to achieve competitive accuracy at reduced latency. The input layer directly processes the analog pixel values of an image without converting it to spike train. The first convolutional layer converts analog inputs into spikes where leaky-integrate-and-fire (LIF) neurons integrate the weighted inputs and generate an output spike when the membrane potential crosses the trained firing threshold. The trained membrane leak selectively attenuates the membrane potential, which increases activation sparsity in the network. The reduced latency combined with high activation sparsity provides massive improvements in computational efficiency. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 69% with five timesteps (inference latency) on the ImageNet dataset with 12x less compute energy than an equivalent standard artificial neural network (ANN). In addition, DIET-SNN performs 20-500x faster inference compared to other state-of-the-art SNN models.

Physics-guided neural networks applied in rotor unbalance problems

Rotary systems are extremely important for the development of industrial production due to the large amount of work performed by these machines. However, rotating machines are prone to unbalance faults, which can reduce efficiency and, in the worst-case scenario, lead to catastrophic failure. Since artificial neural networks (ANNs) are very efficient at recognizing complex patterns, they are a useful tool to help diagnose and prevent rotor unbalance faults. Physics-Guided Machine Learning (PGML) is a class of machine learning algorithm that uses physical laws in its structure. In this paper, a method for unbalance fault identification using PGML is proposed, more specifically ANNs as machine learning—Physics-Guided Neural Networks (PGNN) is used. The first step adopts a standard ANN to locate the nodal position of the experimental fault. Afterwards, the PGNN is performed to quantify the unbalance magnitude and phase angle. Also, a comparison between the performance of the standard ANN and PGNN is accomplished. As input, the networks use simulation data of a rotor supported by hydrodynamic bearings modeled through the finite element method (FEM) and Reynolds’ equation. The results showed that the PGNN has smaller errors and better performance than the standard ANN. In addition, a small increase in the number of neurons improves the results of both networks.

A Genetic Algorithm Optimized ANN for Prediction of Exergy and Energy Analysis Parameters of a Diesel Engine Different Fueled Blends

In this research, a hybrid artificial neural network (ANN) optimized by a genetic algorithm (GA) was used to estimate energy and exergy analyses parameters. This article presents an approach for estimating energy and exergy analyses parameters with optimized ANN model based on GA (GA-ANN) for different ternary blends consisting of diesel, biodiesel and bioethanol in a single-cylinder, water-cooled diesel engine. The data used in the experiments performed at twelve different engine speeds between 1000 and 3000 rpm with 200 rpm intervals for five different fuel mixtures consisting of fuel mixtures prepared by blends biodiesel, diesel and 5% bioethanol in different volumes constitute the input data of the models. Using these input data, engine torque (ET), amount of fuel consumed depending on fuels and speed (AFC), carbon monoxide emission values (CO), carbon dioxide emission values (CO2), hydrocarbon emission values (HC), nitrogen oxides emission values (NOx), the amount of air consumed (AAC), exhaust gas temperatures (EGT) and engine coolant temperatures (ECT) were estimated with the GA-ANN. In examining the results obtained were examined, it was proved that diesel, biodiesel and bioethanol blends were effective in predicting all the results mentioned in engine studies performed at 200 rpm intervals in the 1000-3000 rpm range. A standard ANN model used in the literature was also proposed to measure the prediction performance of GA-ANN model. The predictive results of both models were compared using various performance indices. As a result, it was revealed that the proposed GA-ANN model reached higher accuracy in estimating the exergy and energy analyses parameters of the diesel engine compared to the standard ANN technique.

Predicting Cryptocurrency Fraud Using ChaosNet: The Ethereum Manifestation

Cryptocurrencies are in high demand now due to their volatile and untraceable nature. Bitcoin, Ethereum, and Dogecoin are just a few examples. This research seeks to identify deception and probable fraud in Ethereum transactional processes. We have developed this capability via ChaosNet, an Artificial Neural Network constructed using Generalized Luröth Series maps. Chaos has been objectively discovered in the brain at many spatiotemporal scales. Several synthetic neuronal simulations, including the Hindmarsh–Rose model, possess chaos, and individual brain neurons are known to display chaotic bursting phenomena. Although chaos is included in several Artificial Neural Networks (ANNs), for instance, in Recursively Generating Neural Networks, no ANNs exist for classical tasks entirely made up of chaoticity. ChaosNet uses the chaotic GLS neurons’ property of topological transitivity to perform classification problems on pools of data with cutting-edge performance, lowering the necessary training sample count. This synthetic neural network can perform categorization tasks by gathering a definite amount of training data. ChaosNet utilizes some of the best traits of networks composed of biological neurons, which derive from the strong chaotic activity of individual neurons, to solve complex classification tasks on par with or better than standard Artificial Neural Networks. It has been shown to require much fewer training samples. This ability of ChaosNet has been well exploited for the objective of our research. Further, in this article, ChaosNet has been integrated with several well-known ML algorithms to cater to the purposes of this study. The results obtained are better than the generic results.

A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients

Diabetes is a major chronic health problem affecting millions globally. Effective diabetes management can reduce the risk of hospital readmission and the associated financial losses for both the healthcare system and insurance companies. Hospital readmission is a high-priority healthcare quality measure that reflects the inadequacies in the healthcare system that also increase healthcare costs and negatively influence hospitals’ reputation. Predicting readmissions in the early stages prompts great attention to patients with a high risk of readmission. There has been some attempt in applying machine learning predictive models such as ensemble learning with Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM) and Artificial Neural Networks (ANN) to correctly identify if the readmission can happen within 30 days (< 30 days) or it may never happen or happens after 30 days ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\ge 30$ </tex-math></inline-formula> days). We are proposing a new method that is applied to ANN to guide it through its gradient descent optimizers by realizing consistent vs inconsistent data in every batch. Our results show that there are up to 1.5% improvement in classification accuracies in both 2-class and 3-class variations of the experimented benchmark dataset when using the guided optimizer to train the ANN as opposed to the standard optimizer. Guided ANN is also able to achieve better error convergence than standard ANN.

Application of augmented bat algorithm with artificial neural network in forecasting river inflow in Malaysia

Hydrologists rely extensively on anticipating river streamflow (SF) to monitor and regulate flood management and water demand for people. Only a few simulation systems, where previous techniques failed to anticipate SF data quickly, let alone cost-effectively, and took a long time to execute. The bat algorithm (BA), a meta-heuristic approach, was used in this study to optimize the weights and biases of the artificial neural network (ANN) model. The proposed hybrid work was validated in five different study areas in Malaysia. The statistical tests analysis of the preliminary results revealed that hybrid BA-ANN was superior to forecasting the SF at all five selected study areas, with average RMSE values of 0.103 m3/s for training and 0.143 m3/s for testing as compared to ANN standalone training and testing yielding 0.091 m3/s and 0.116 m3/s, respectively. This finding signifies that the implementation of BA into the ANN model resulted in a 20% improvement. In addition, with an R2 score of 0.951, the proposed model showed a better correlation than the 0.937 value of R2 of standard ANN. Nonetheless, while the proposed work outperformed the conventional ANN, the Taylor diagram, violin plot, relative error, and scatter plot findings confirmed the disparities in the proposed work’s performance throughout the research regions. The findings of these evaluations highlighted that the adaptability of the proposed works would need detailed investigation because its performance differed from case to case.

Tuning Convolutional Spiking Neural Network With Biologically Plausible Reward Propagation.

Spiking neural networks (SNNs) contain more biologically realistic structures and biologically inspired learning principles than those in standard artificial neural networks (ANNs). SNNs are considered the third generation of ANNs, powerful on the robust computation with a low computational cost. The neurons in SNNs are nondifferential, containing decayed historical states and generating event-based spikes after their states reaching the firing threshold. These dynamic characteristics of SNNs make it difficult to be directly trained with the standard backpropagation (BP), which is also considered not biologically plausible. In this article, a biologically plausible reward propagation (BRP) algorithm is proposed and applied to the SNN architecture with both spiking-convolution (with both 1-D and 2-D convolutional kernels) and full-connection layers. Unlike the standard BP that propagates error signals from postsynaptic to presynaptic neurons layer by layer, the BRP propagates target labels instead of errors directly from the output layer to all prehidden layers. This effort is more consistent with the top-down reward-guiding learning in cortical columns of the neocortex. Synaptic modifications with only local gradient differences are induced with pseudo-BP that might also be replaced with the spike-timing-dependent plasticity (STDP). The performance of the proposed BRP-SNN is further verified on the spatial (including MNIST and Cifar-10) and temporal (including TIDigits and DvsGesture) tasks, where the SNN using BRP has reached a similar accuracy compared to other state-of-the-art (SOTA) BP-based SNNs and saved 50% more computational cost than ANNs. We think that the introduction of biologically plausible learning rules to the training procedure of biologically realistic SNNs will give us more hints and inspiration toward a better understanding of the biological system's intelligent nature.

Machine Learning-Assisted Carbon Dot Synthesis: Prediction of Emission Color and Wavelength.

Carbon dots (CDs) have attracted great attention in a range of applications due to their bright photoluminescence, high photostability, and good biocompatibility. However, it is challenging to design CDs with specific emission properties because the syntheses involve many parameters, and it is not clear how each parameter influences the CD properties. To help bridge this gap, machine learning, specifically an artificial neural network, is employed in this work to characterize the impact of synthesis parameters on and make predictions for the emission color and wavelength for CDs. The machine reveals that the choice of reaction method, purification method, and solvent relate more closely to CD emission characteristics than the reaction temperature or time, which are frequently tuned in experiments. After considering multiple models, the best performing machine learning classification model achieved an accuracy of 94% in predicting relative to actual color. In addition, hybrid (two-stage) models incorporating both color classification and an artificial neural network k-ensemble model for wavelength prediction through regression performed significantly better than either a standard artificial neural network or a single-stage artificial neural network k-ensemble regression model. The accuracy of the model predictions was evaluated against CD emission wavelengths measured from experiments, and the minimum mean average error is 25.8 nm. Overall, the models developed in this work can effectively predict the photoluminescence emission of CDs and help design CDs with targeted optical properties.

Longitudinal deep truck: Deep longitudinal model with application to sim2real deep reinforcement learning for heavy‐duty truck control in the field

AbstractTo develop cooperative adaptive cruise control (CACC), the choice of control approach often influences and can limit the choice of model structure, and vice versa. For heavy‐duty trucks, practical application of CACC in the field is heavily influenced by the accuracy of the used model. Deep learning and deep reinforcement learning (deep‐RL) have recently been used to demonstrate improved modeling and control performance for vehicles such as cars and quadrotors compared to state‐of‐the‐art. The literature on the application of deep learning and deep‐RL for heavy‐duty trucks in the field, which are significantly more complex than cars, is still sparse, however. In this article, we develop a two‐layer gray‐box deep learning model to capture longitudinal dynamics of heavy‐duty trucks while abstracting their complexity and present an approach to properly break the nested feedback loops in the model for training. We compare this model with three other alternative models and show that it achieves better general performance compared to a standard artificial neural network and results in and slower steady‐state acceleration and speed error growth rates, respectively. We then present an architecture to utilize these deep learning models within the deep‐RL framework and use it to develop baseline CACC controllers that can be zero‐shot transferred to the field. To carry out the work, we present a setup of differently configured trucks along with their interface architecture and stochastic driving cycle generators for data collection. Numerical validation of the approach demonstrated stationary and bounded modeling error, and demonstrated transfer of CACC controllers with consistent overshoot bounds and a stable approximately‐zero steady‐state error. Validation from field experiments demonstrated similarly consistent results. Compared to a state‐of‐the‐art benchmark, the deep‐RL controller achieved lower speed and time‐gap error variance but higher time‐gap error offset.

A novel genetic-artificial neural network based age estimation system

Age estimation is the ability to predict the age of an individual based on facial clues. This could be put to practical use in underage voting detection, underage driving detection, and overage sportsmen detection. To date, no popular automatic age estimation system has been developed to target black faces. This study developed a novel age estimation system from the combination of a genetic algorithm and a back propagation (BP)-trained artificial neural network (ANN) and using the local binary pattern feature extraction technique (LBGANN) targeted at black faces. The system was trained with a predominantly black face database, and the result was compared against that of a standard ANN system (LBANN). The results showed that the developed system LBGANN outperformed the LBANN in terms of the correct classification rate.

Predicting the Young’s Modulus of Rock Material Based on Petrographic and Rock Index Tests Using Boosting and Bagging Intelligence Techniques

Rock deformation is considered one of the essential rock properties used in designing and constructing rock-based structures, such as tunnels and slopes. This study applied two well-established ensemble techniques, including boosting and bagging, to the artificial neural networks and decision tree methods for predicting the Young’s modulus of rock material. These techniques were applied to a dataset comprising 45 data samples from a mountain range in Malaysia. The final input variables of these models, including p-wave velocity, interlocking coarse-grained crystals of quartz, dry density, and Mica, were selected through a likelihood ratio test. In total, six models were developed: standard artificial neural networks, boosted artificial neural networks, bagged artificial neural networks, classification and regression trees, extreme gradient boosting trees (as a boosted decision tree), and random forest (as a bagging decision tree). The performance of these models was appraised utilizing correlation coefficient (R), mean absolute error (MAE), and lift chart. The findings of this study showed that, firstly, extreme gradient boosting trees outperformed all models developed in this study; secondly, boosting models outperformed the bagging models.