Search

This work reports the degradation of cellulosic material, i.e., paper, under different environmental conditions (soil and hydrolytic). Models were developed using central composite design (CCD) within the framework of response surface methodology (RSM) and artificial neural network (ANN) techniques. It is done as part of a solid waste management system to eliminate the waste produced by excessive paper usage and obtain optimized degradation conditions of paper. In view of the real environments where paper-based solid wastes are usually exposed, soil degradation and hydrolytic degradation of paper were investigated. The factors pH (4–10), compost ratio (2–5), CaCl2 (5–15 ppm), and time (7–20 days) were independent factors that varied for the study, and degradation conversion was measured as the dependent variable for soil degradation of paper. The factors pH (4–10), CaCl2 (2–5 ppm), tripotassium phosphate (TPP, 2–5 ppm), and time (6–16 days) were independent variables that varied for the study, and degradation conversion was the dependent variable for hydrolytic degradation of paper. The optimal conditions for soil degradation were determined to be a pH of 4, a compost ratio of 5, a salt (CaCl2) addition of 5 ppm, and a duration of 20 days, resulting in the highest observed conversion rate. The coefficient of regression (R2) for CCD is 87.24%, whereas it is 94.82% for ANN. The optimal conditions for achieving maximum conversion in hydrolytic degradation include a pH of 10, a CaCl2 salt concentration of 5 ppm, a TPP salt concentration of 2 ppm, and a duration of 16 days. The coefficient of regression for CCD is 75.15%, while the coefficient of regression for ANN is 93.91%. In both deterioration scenarios, the data exhibited a higher degree of fit when modeled using ANN compared to CCD (RSM). [ABSTRACT FROM AUTHOR]

This paper presents an indoor positioning strategy based on Visible Light Communication that relies on LED luminaires as transmitters, whose luminous flux is modulated at different frequencies, and a light sensor as a receiver. Then, a previously trained Artificial Neural Network (ANN) uses the illuminance signal gathered by the receiver as input to estimate the sensor's position. The main contribution of the technique is that the ANN is trained by using an illuminance estimator based on the lighting distribution of the luminaires, which is obtained through the IES file provided by the luminaire's manufacturer, without the need to collect data from the environment. In this work, the designed illuminance estimator is validated by comparing it to the well-known commercial software DIALux and Relux. The algorithm's setting and the performance evaluation of the ANN are explained. Then, the impact of the lighting uniformity and the environment's number of divisions on the accuracy of the results is analyzed. Error analyses are also made by adding uncertainty to the illuminance measurements obtained by the sensor. Finally, the work is compared to several papers in the field. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient optimization method for the stacking sequence of composite pressure vessels based on the joint application of finite element analysis (FEA), artificial neural network (ANN), and genetic algorithm (GA). The composite pressure vessel has many winding layers and varied angles, and the stacking sequence of the composite pressure vessel affects its performance. It is essential to carry out the optimal design of the stacking sequence. The experimental cost for optimal design of composite pressure vessels is high, and numerical simulation is time-consuming. ANN is used to predict the fiber direction stress of composite pressure vessels, which replaces FEA in the optimization process of GA effectively. In addition, the optimization efficiency of the optimization method proposed in this paper can be improved significantly when the neural network model is employed. The optimization results show that the peak stress in the fiber direction can be reduced by 37.3% with the design burst pressure. The burst pressure of the composite pressure vessel can be increased by 13.4% by optimizing the stacking sequence of composite pressure vessels while keeping the number of plies and the winding angle unchanged. The results imply that the work undertaken in this paper is of great significance for the improvement of the safety performance of composite pressure vessels. [ABSTRACT FROM AUTHOR]

This paper introduces a novel design for a universal DC-DC and DC-AC converter tailored for DC/AC microgrid applications using Approximate Dynamic Programming and Artificial Neural Networks (ADP-ANN). The proposed converter is engineered to operate efficiently with both low-power battery and single-phase AC supply, utilizing identical side terminals and switches for both chopper and inverter configurations. This innovation reduces component redundancy and enhances operational versatility. The converter's design emphasizes minimal switch usage while ensuring efficient conversion to meet diverse load requirements from battery or AC sources. A conceptual example illustrates the design's principles, and comprehensive analyses compare the converter's performance across various operational modes. A test bench model, rated at 3000W, demonstrates the converter's efficacy in all five operational modes with AC/DC inputs. Experimental results confirm the system's robustness and adaptability, leveraging ADP-ANN for optimal performance. The paper concludes by outlining potential applications, including microgrids, electric vehicles, and renewable energy systems, highlighting the converter's key advantages such as reduced complexity, increased efficiency, and broad applicability. [ABSTRACT FROM AUTHOR]

This paper introduces an adaptive hybrid approach to address the forward kinematics problem of a Hexa parallel robot (HPR), known for its challenge in obtaining a unique closed-form analytic solution. In the initial stage, we construct an artificial neural network (ANN) model to rapidly generate a preliminary result, effectively narrowing the search space. Subsequently, bacterial foraging optimization (BFO) is adapted to refine the result by focusing on exploration within the reduced search space. Adaptive functions adjust BFO parameters based on the error level in the preliminary result, enhancing algorithm performance. Software is developed to demonstrate the practical application of this method. Experimental results within the robot workspace indicate a significant reduction in calculation errors compared to using only the ANN model. [ABSTRACT FROM AUTHOR]

This paper reviews arrhythmia classification studies using electrocardiogram (ECG) signals. Research on automatically diagnosing arrhythmia in daily life has been actively underway for early detection and treatment of heart disease. Development of automatic arrhythmia classification using ECG signal began based on handcrafted morphological feature extraction and machine learning-based classification methods. As deep neural networks (DNN) show excellent performance in the signal processing field, studies using various types of DNN are also being conducted in ECG classification. However, these DNN-based studies have extremely high computational complexity, making it challenging to perform real-time classification, and are unsuitable for low-power environments such as wearable devices due to high power consumption. Currently, research based on spiking neural network (SNN), which mimics the low-power operation of the human nervous system, is attracting attention as a method that can dramatically reduce complexity and power consumption. The classification accuracy of the SNN-based ECG classification studies is close to that of the DNN-based studies. When combined with neuromorphic hardware, it shows ultra-low-power performance, suggesting the possibility of use in lightweight devices. In this paper, the SNN-based ECG classification studies for low-power environments are mainly reviewed, and prior to this, conventional and DNN-based ECG classification studies are also reviewed. We hope that this review will be helpful to researchers and engineers interested in the field of ECG classification. [ABSTRACT FROM AUTHOR]

In this paper, model updating for tall tower structures is discussed, a novel model variable index is proposed, and a selection method of model variables to be updated that can consider the high sensitivity of the displacement residuals and the small influence of the measurement errors is presented based on an artificial neural network (ANN). When the multi-layer perceptron architecture of the ANN obtains the optimal number of hidden layer neurons and the number of iterations, it is verified that the position and degree of the structural model defects can be detected by updating the selected model variables. Additionally, situations in which there is a large order-of-magnitude difference between the model variables are also discussed. It is found that in the proposed model variable index, the displacement residuals are more important than the measurement errors; however, as the measurement errors increase, they become more important in the model variable index. Furthermore, when the large-scale structure is damaged, the dynamic model can be transformed into an equivalent static model. Based on these results and findings, the proposed approach is expected to be used for design and analysis purposes, including structural health monitoring, safety assessment, damage identification, and structural reinforcement. [ABSTRACT FROM AUTHOR]

The retinal impulse signal is the basic carrier of visual information. It records the distribution of light on the retina. However, its direct conversion to a scene image is difficult due to the nonlinear characteristics of its distribution. Therefore, the use of artificial neural network to reconstruct the scene from retinal spikes has become an important research area. This paper proposes the architecture of a neural network based on vector quantization, where the feature vectors of spike trains are extracted, compressed, and stored using a feature extraction and compression network. During the decoding process, the nearest neighbour search method is used to find the nearest feature vector corresponding to each feature vector in the feature map. Finally, a reconstruction network is used to decode a new feature map composed of matching feature vectors to obtain a visual scene. This paper also verifies the impact of vector quantization on the characteristics of pulse signals by comparing experiments and visualizing the characteristics before and after vector quantization. The network delivers promising performance when evaluated on different datasets, demonstrating that this research is of great significance for improving relevant applications in the fields of retinal image processing and artificial intelligence. [ABSTRACT FROM AUTHOR]

Super-computing or HPC clusters are built to provide services to execute computationally complex applications. Generally, these HPC applications involve large scale IO (input/output) processing over the networked parallel file system disks. They are commonly developed on top of the C/C++ based MPI standard library. The HPC clusters MPI–IO performance significantly depends on the particular parameter value configurations, not generally considered when writing the algorithms or programs. Therefore, this leads to poor IO and overall program performance degradation. The IO is mostly left to individual practitioners to be optimised at code level. This usually leads to unexpected consequences due to IO bandwidth degradation which becomes inevitable as the file data scales in size to petabytes. To overcome the poor IO performance, this research paper presents an approach for auto-tuning of the configuration parameters by forecasting the MPI–IO bandwidth via artificial neural networks (ANNs), a machine learning (ML) technique. These parameters are related to MPI–IO library and lustre (parallel) file system. In addition to this, we have identified a number of common configurations out of numerous possibilities, selected in the auto-tuning process of READ/WRITE operations. These configurations caused an overall READ bandwidth improvement of 65.7% with almost 83% test cases improved. In addition, the overall WRITE bandwidth improved by 83% with number of test cases improved by almost 93%. This paper demonstrates that by using auto-tuning parameters via ANNs predictions, this can significantly impact overall IO bandwidth performance. [ABSTRACT FROM AUTHOR]

In numerical simulations such as computational fluid dynamics simulations or finite element analyses, mesh quality affects simulation accuracy directly and significantly. Smoothing is one of the most widely adopted methods to improve unstructured mesh quality in mesh generation practices. Compared with the optimization-based smoothing method, heuristic smoothing methods are efficient but yield lower mesh quality. The balance between smoothing efficiency and mesh quality has been pursued in previous studies. In this paper, we propose a new smoothing method that combines the advantages of the heuristic Laplacian method and the optimization-based method based on the deep reinforcement learning method under the Deep Deterministic Policy Gradient framework. Within the framework, the actor artificial neural network predicts the optimal position of each interior free node with its surrounding ring nodes. At the same time, a critic-network is established and takes the mesh quality as input and outputs the reward of the action taken by the actor-network. Training of the networks will maximize the cumulative long-term reward, which ends up maximizing the mesh quality. Training and validation of the proposed method are presented both on 2-dimensional triangular meshes and 3-dimensional surface meshes, which demonstrates the efficiency and mesh quality of the proposed method. Finally, numerical simulations on perturbed meshes and smoothed meshes are carried out and compared which prove the influence of mesh quality on the simulation accuracy. [ABSTRACT FROM AUTHOR]

The introduction of hybrid alternating current (AC)/direct current (DC) distribution networks led to several developments in smart grid and decentralized power system technology. The paper concentrates on several topics related to the operation of hybrid AC/DC networks. Such as optimization methods, control strategies, energy management, protection issues, and proposed solutions. The implementation of neural network optimization methods has great importance for the successful integration of multiple energy sources, dynamic energy management, establishment of system stability and reliability, power distribution optimization, management of energy storage, and online fault detection and diagnosis in hybrid networks like the hybrid AC–DC microgrids (MG). Taking advantage of renewable energy generation and cost-cutting through the neural network optimization technique holds the key to these progressions. Besides identifying the challenges in the operation of a hybrid system, the paper also compares this system to conventional MGs and shows the benefits of this type of system over different MG structures. This review compares the different topologies, particularly looking at the AC–DC coupled hybrid MGs, and shows the important role of the interlinking of converters that are used for efficient transmission between AC and DC MGs and generally used to implement the different control and optimization techniques. Overall, this review paper can be regarded as a reference, pointing out the pros and cons of integrating hybrid AC/DC distribution networks for future study and improvement paths in this developing area. [ABSTRACT FROM AUTHOR]

The paper presents a study on the erosion performance of stainless steel SS316L grade. The micron layers of Ni-20Al2O3 powder were sprayed on the surface SS316L by utilizing a high-velocity oxygen–fuel (HVOF) thermal spraying process. Wear experiments were performed in a slurry pot tester (Ducom TR-41) at different speeds varying from 600 to 1500 rpm. During the experiments, the sand was used to erode the coated surface of SS316L. Multi-sized slurry having a solid concentration lies in the range of 30–60% (by weight) was prepared to perform the wear experiments. A neural network technique was implemented to predict the erosion data by training 75% of the total data. Results show that the microhardness of bare and Ni-20Al2O3 HVOF coated SS316L was tested as 196 ± 21 and 393.32 ± 17 VHN respectively. The current ANN model yielded an R-value that was 0.98871 for training, 0.97209 for validation, and 0.96264 for testing accordingly. It was determined that the total R-value of the model was 0.98153. The ANN's performance evaluated based on the mean squared error (MSE) was determined as 0.0176, 0.00265, and 0.00334 respectively for the training, validation, and testing. [ABSTRACT FROM AUTHOR]

This paper presents a statistical approach based on data mining to estimate the riverine environmental water demand (EWD). A river's environmental water demand defines the quantity, timing, and quality of streamflow that are required to sustain riverine ecosystems and human activities. Genetic programming (GP), artificial neural network (ANN), and support vector regression (SVR) are herein applied to model the environmental demand. Input and output data for the use of GP, ANN, and SVR are the average monthly temperature and precipitation in 1995–2005 plus climate projections by the Canadian Land System Model (CanESM2) under the recommended concentration pathways RCPs 2.6, 4.5 and 8.5 in 2025–2035. A case study illustrates this paper's methodology using temperature and precipitation data and monthly discharge of the Karaj River, Iran. The applied data mining models were evaluated with R2, RMSE, and the NSE criteria. This work's results show that the largest values of R2 and the NSE equal respectively 0.94 and 0.95, and the smallest value of the RMSE equals 0.07, which correspond to the SVR predictions. These results establish that SVR is a suitable model for the purpose of estimating the environmental water demand in comparison to GP and ANN in the study area. The SVR projections indicate that by 2035 and under the RCPs 2.6, 4.5, and 8.5 projected changes of the environmental water demand with respect to baseline conditions would be respectively 63, 118, and 126 m3/s. It is demonstrated in this work that under climate change conditions the correlation between the EWD index and temperature was 83%, while the said value for rainfall was estimated to be 76%. [ABSTRACT FROM AUTHOR]

To address the problem that the traditional detection method for litchi sugar content is time-consuming and laborious and will destroy the tested sample, this paper proposed a non-destructive detection method for litchi sugar content based on near-infrared spectroscopy (NIR) and artificial intelligence algorithm. Firstly, to remove noise and other interference, the preprocessing methods for spectral data are studied. Nine preprocessing methods, such as moving average smoothing (MA), standard normal variate transform (SNV), and multiplicative scatter correction (MSC), are adopted to preprocess the spectral data. Then, to reduce the input dimension of the model and overcome the interference of redundant bands, the feature extraction methods for spectral data are examined. Two feature extraction methods, including Monte-Carlo uninformative variable elimination (MCUVE) and competitive adaptive reweighted sampling (CARS), are utilized to extract the features of spectral data. Finally, partial least squares regression (PLSR) and stochastic configuration network (SCN) are adopted to establish the prediction model of litchi sugar content. The experimental results show that the SNV-CARS-SCN prediction model has the highest accuracy. The coefficient of determination ( R 2 ), RMSE, and MAE of the training dataset are 0.9996, 0.1145, and 0.1154, respectively. R 2 , RMSE, and MAE of the test dataset are 0.9740, 0.4962, and 0.3818, respectively. The NIR detection system and SCN prediction model designed in this paper are of great significance for the design of litchi automatic sorting system. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) tunes modern technologies, including wireless sensors and cloud computing, to create a homogeneous and highly effective environment. Therefore, IoT has emerged in various fields of life, such as healthcare, industry, and agriculture. Agriculture is among the primary components of developing nations' financial states and is vital in maintaining human life. However, the human capacity to reproduce far exceeds the capability of our planet to secure the food required for our lives. Hence, the emergence of IoT in this industry has seen essential advancements to help boost agriculture production and quality. In addition, this emergence exposes the smart agriculture environment to considerable cyber threats. This paper presents a network intrusion detection system (NIDS) to mitigate smart agriculture security vulnerabilities. We developed our framework using radial basis functions neural networks (RBFNN) to detect and classify intrusions in the IoT network. To get our model to perform in its best form, we applied crowd wisdom tree-based machine learning (ML) techniques to select relevant features from the datasets, such as random Forrest (RF), AdaBoost (ADA), extra trees (ET), LightGBM (LGBM), and XGBoost (XGB). We implemented a single-class support vector machine (1-CSVM) to detect and remove outliers. We evaluated our model using NF-Bot-IoT and NF-ToN-IoT datasets. It scored 99.25% accuracy (ACC) and 82.97% Matthews correlation coefficient (MCC) and 90.05% MCC and 96.92% ACC on preprocessed NF-Bot-IoT and NF-ToN-IoT, respectively. Our model showed outstanding performance in overcoming the NF-Bot-IoT dataset imbalance. [ABSTRACT FROM AUTHOR]

Surface waters are essential for meeting the needs of the world. In many regions, stream water quality is a major concern due to contamination from multiple sources. Stream water is also susceptible to climatic events and land-use practices influencing its catchment. Understanding the impact of such events on stream water quality is crucial for managing and protecting aquatic ecosystems and providing safe drinking water to communities that rely on these streams. Hence, monitoring and evaluating stream water quality holds significance in identifying potential hazards and implementing suitable management strategies. In this paper, a novel effort was made to determine the relative feature importance of a set of watershed characteristics (precipitation, temperature, urban land use, agricultural land use, and forest land-use factors) on four important water quality parameters (WQPs): fecal coliforms (FC), turbidity, pH, and conductivity of the Upper Green River watershed, Kentucky, USA. Random forest (RF), an ensemble learning method, was used to predict the WQPs from the causal parameters and determine the feature importance characteristics of the four WQPs previously mentioned. This model demonstrated that precipitation and temperature are the most influential factors on FC, turbidity, and pH. Forest land use and temperature are the two most important factors for conductivity. The novel feature importance factors of the RF model have likewise been confirmed for each WQP. In modeling stream WQPs, the developed the RF model outperformed the artificial neural network (ANN) model. Using the RF model, we obtain regression coefficients of (0.93, 0.74, and 0.94) for pH in training, testing, and overall. We obtain regression coefficients of (0.60, 0.64, and 0.61) using the ANN model. ⁠⁠⁠⁠⁠⁠⁠Overall, the RF model was more effective than the ANN model in modeling stream WQPs. The model identified precipitation and temperature as the most influential factors on FC, turbidity, and pH, while forest land use and temperature were the most important factors in determining conductivity. It is also found that land use factors are important to improve the accuracy of WQPs predictions from climate variables. The results of this study can be used by authorities to better understand and control pollution at the watershed scale. [ABSTRACT FROM AUTHOR]

Sea surface gage height (SSGH) data are commonly measured at sparsely deployed tidal stations while coastal resources management requires spatially distributed SSGH data. This paper presents three different machine learning models, including a Random Forest (RF) model, an Extreme Gradient Boosting (XGBoost) model, and an Artificial Neural Network (ANN) model, for retrieving and mapping spatially distributed SSGH. The models were originally developed and independently validated using 10 years of VIIRS satellite remote sensing data and corresponding in-situ gage height (GH) data within the MATLAB ANN toolbox and RStudio. The paper made two major new contributions to the determination of SSGH, including a scientific contribution and a technical contribution. Scientifically, this paper has provided new insights into important factors affecting SSGH. The SSGH varies significantly with the location (GPS coordinates) and Julian Day with both factors affecting the tide and thus SSGH. SSGH is also affected by sea surface waves that affect the reflectance of light from different wavelengths of satellite sensors, which are described with the VIIRS remote sensing reflectance (Rrs) bands including Rrs 410, 443, 486, 551, and 671. Technically, the machine learning models, particularly the ANN model, are capable of providing the most accurate and spatially distributed SSGH data particularly for coastal waters, as characterized by the model performance metrics including the correlation coefficient R value of 0.94 for training, 0.94 for validation, and 0.93 for testing and the low root mean square error (RMSE) value of 0.113 m for training, 0.113 m for validation, and 0.118 m for testing. [ABSTRACT FROM AUTHOR]

Recent increases in global food demand have made this research and, therefore, the prediction of agricultural commodity prices, almost imperative. The aim of this paper is to build efficient artificial intelligence methods to effectively forecast commodity prices in light of these global events. Using three separate, well-structured models, the commodity prices of eleven major agricultural commodities that have recently caused crises around the world have been predicted. In achieving its objective, this paper proposes a novel forecasting model for agricultural commodity prices using the extreme learning machine technique optimized with the genetic algorithm. In predicting the eleven commodities, the proposed model, the extreme learning machine with the genetic algorithm, outperforms the model formed by the combination of long short-term memory with the genetic algorithm and the autoregressive integrated moving average model. Despite the fluctuations and changes in agricultural commodity prices in 2022, the extreme learning machine with the genetic algorithm model described in this study successfully predicts both qualitative and quantitative behavior in such a large number of commodities and over such a long period of time for the first time. It is expected that these predictions will provide benefits for the effective management, direction and, if necessary, restructuring of agricultural policies by providing food requirements that adapt to the dynamic structure of the countries. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are the future of networking. They represent one of the best technologies for automation due to their characteristics, such as cost-effectiveness and wireless nature. However, WSNs require explicit programming to perform certain tasks, lacking adaptability. To address this limitation, machine learning (ML) can be highly beneficial as it grants networks the ability to make decisions automatically. This capability can refine the accuracy and efficiency of WSNs. This paper aims to provide a detailed classification of machine learning algorithms, discussing various problems of traditional wireless sensor networks and the solutions that machine learning can offer. It also includes a brief discussion of problems associated with machine learning in WSNs. This review paper is written with the hope of being useful for researchers in a future era where the amalgamation of WSNs and machine learning algorithms will influence many aspects of human life. [ABSTRACT FROM AUTHOR]

Copyright of Low-Carbon Materials & Green Construction is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, the dispersion characteristics of slotted photonic crystal waveguides (SPCWs) have been estimated for any arbitrary set of structural parameters using machine learning-based artificial neural network (ANN). The machine learning-based technique yields faster solutions of the three-dimensional eigenvalue equations, which otherwise require substantial time using the conventional plane wave expansion (PWE)-based numerical simulations. Most importantly, the novel contribution of the work lies in estimating the structural parameters of the SPCWs from the given specifications of the dispersion characteristics through an inverse computation. A simple feed-forward neural network has been employed for both the forward and inverse estimations. The computation performances using both the ANN model and PWE simulations are analyzed and compared. The research offers significant implications for the field of photonics. By employing machine learning techniques, particularly ANNs, researchers and engineers can swiftly and efficiently analyze the dispersion properties of SPCWs, facilitating rapid prototyping and optimization of photonic devices. Additionally, the capability to infer structural parameters from desired dispersion characteristics streamlines the design process, potentially leading to the development of customized waveguides tailored to specific applications. [ABSTRACT FROM AUTHOR]

Metaheuristic algorithms with machine learning techniques have become popular because it works so well for problems like regression, classification, rule mining, and clustering in health care. This paper's primary purpose is to design a multi-disease prediction system using AI-based metaheuristic approaches. Initially, the data is collected in the form of diverse classes, which include Id, gender, date of birth, etc. The data has been preprocessed, normalized, and graphically represented to improve its quality and detect any errors. Later, machine learning models, such as decision tree, extra tree classifier, extreme gradient boosting classifier, light gradient boosting machine classifier, random forest, and artificial neural network, are initially trained without optimizing hyperparameters and then fine-tuned by integrating various hyperparameter optimizers such as grid search CV, random search, hyperband, and genetic search. During experimentation, it is found that optimizing the models using random search optimizer computed the highest accuracy of 100% as compared to the rest of the hyperparameter optimizers. In the context of 'Service Oriented Computing and Applications,' our multi-disease prediction system offers valuable innovation. It aligns with the goal of enhancing healthcare services, patient outcomes, and healthcare efficiency. Our pioneering integration of metaheuristic algorithms and machine learning introduces intelligent healthcare solutions, with the study's focus on hyperparameter optimization and achieving 100% accuracy demonstrates practical significance in SOC and its applications. [ABSTRACT FROM AUTHOR]

The rising population of millennials, coupled with Digital Assistants (DA) and online purchasing trends among consumers have gained increasing attention by global marketers. The study evaluates the influence of DA attributes on the purchasing intention (PUI) of millennials. A combined approach of PLS-SEM, Artificial Neural Network (ANN) and Fuzzy-set Qualitative Comparative Analysis (fsQCA) is used to predict the PUI of 345 millennials. Also, multi-group analysis is employed to uncover the influence of gender on the relationship between PUI and DA attributes. The findings suggest that DA attributes may amplify purchasing intention among millennials, especially through perceived interactivity and anthropomorphism. Further, the moderating role of gender was found significant on the inter-relationship of perceived interactivity and PUI. This research is a pioneer study in the area of artificial intelligence, conversational commerce, DA and AI-powered chatbots. This study will help marketers and practitioners to predict millennial purchasing intentions. An evaluation of this paper may help them to foster immersive and effective engagement through DA. [ABSTRACT FROM AUTHOR]

All-optical plasmonic switches (AOPSs) utilizing surface plasmon polaritons are well-suited for integration into photonic integrated circuits (PICs) and play a crucial role in advancing all-optical signal processing. The current AOPS design methods still rely on trial-and-error or empirical approaches. In contrast, recent deep learning (DL) advances have proven highly effective as computational tools, offering an alternative means to accelerate nanophotonics simulations. This paper proposes an innovative approach utilizing DL for spectrum prediction and inverse design of AOPS. The switches employ circular nonlinear plasmonic ring resonators (NPRRs) composed of interconnected metal–insulator–metal waveguides with a ring resonator. The NPRR switching performance is shown using the nonlinear Kerr effect. The forward model presented in this study demonstrates superior computational efficiency when compared to the finite-difference time-domain method. The model analyzes various structural parameters to predict transmission spectra with a distinctive dip. Inverse modeling enables the prediction of design parameters for desired transmission spectra. This model provides a rapid estimation of design parameters, offering a clear advantage over time-intensive conventional optimization approaches. The loss of prediction for both the forward and inverse models, when compared to simulations, is exceedingly low and on the order of 10−4. The results confirm the suitability of employing DL for forward and inverse design of AOPSs in PICs. [ABSTRACT FROM AUTHOR]

Purpose: This work designs a procedure for structural damage assessment in beams under moving loads. The proposal is based on the respective alterations of hybrid vibrational factors with respect to the structural changes, whereby matching them for accurate predictions. These hybrid factors are extracted from the vibrational responses and then are employed for an artificial neural network (ANN) to assess the structural condition. Methods: An experiment is deployed to generate a databank for evaluation as well as ANN training. The maximal overlap discrete wavelet transform (MODWT) and the fast Fourier transform (FFT) are incorporated to split original signals into several power bands, which helps to exploit characteristics of individual vibrational modes: centroids and comparative powers of allocated spectra. The extracted hybrid factors are then fed into an ANN to predict the damage condition of the beam. The training process of this ANN uses a databank of extracted features from measured signals. Results: The paper successfully finds out the damage-sensitive feature through signal processing. Alternatively, the implemented experiment provides a rich databank for the ANN training, and the training performance reaches a high accuracy. Moreover, the testing results reveal the superior generalization of the ANN because of automatic predictions with high precision. This proves the contribution of the study that the exploited features are proper for structural assessment, and the trained ANN learns the correlation of vibration features and structural state well. Conclusions: The automation and effectiveness of the proposed approach are endorsed, which has high applicability and accuracy for damage assessment in beams. The proposed method is mainly devoted to identifying, quantifying, and localizing damage. [ABSTRACT FROM AUTHOR]

The higher rate of skin diseases caused by infections, allergies, lifestyle changes, increased use of chemicals, unhealthy food habits, and hereditary reactions, among other factors demand effective diagnostic mechanisms. These mechanisms should facilitate and expedite the precise diagnosis of malignant melanoma. In addition, the existing technology-assisted tests require elaborate procedures to accurately diagnose the skin disease to be treated. The deep learning-enhanced inspection involves neural networks that diagnose skin diseases by analyzing data for skin lesions such as rashes, boils, and cancer growth. This paper proposes an automated high-precision diagnostic model with the web application to identify Malignant Melanoma Cancer. The diagnostic model framework employs a convolutional neural network (CNN) with ResNet50 for data collection, preprocessing, segmentation, enhancement, feature extraction, classification, and malignant melanoma identification to improve accuracy. The proposed model eliminates unwanted noise, enhances spectral image information, and improves classification accuracy through preprocessing and mixed hybrid pooling phases. Performance analysis shows that the proposed Malignant Melanoma Cancer detection model achieves the highest accuracy of 94% and an F1-score of 93.9%. Results from a training and testing dataset of images from the International Skin Image Collaboration (ISIC) demonstrate a significant improvement over traditional methods. Further, the web application developed for this model accelerates the precise diagnosis of Malignant Melanoma Cancer with accurate information compared to other methods in practice. The potential of applying the proposed skin cancer classification model automates the malignant and benign image classification process, speeds up diagnosis and treatment, and reduces the risk of misdiagnosis. [ABSTRACT FROM AUTHOR]

In digital communication, the transmitted data is affected due to channel distortion. In terms of Inter-Symbol Interference (ISI), the distortion is occurs due to the dispersive nature of channel. The channel equalization technique is used at the receiver end for their reliability and high-speed communication by reducing the effects of ISI. In this paper an effective equalizer based on Artificial Neural Network (ANN) is proposed. The weights of ANN are trained by proposed Battle Royale Optimization (BRO). The objective function of ANN-BRO based equalizer is to minimize Mean Square Error (MSE) values where the error value is estimated based on the transmitted signal and the equalizer output. The BRO is modified by different initialization methods like Random Number Generation (RNG), Opposition based learning (OBL), Quasi-Opposition based learning (QBL), Tent Map and chaotic methods. The experimental results of the proposed equalizer is evaluated and compared with various initialization and optimization approaches. The performance measures such as MSE, Mean Square of the Residual Error (MSRE), and Bit Error Rate (BER) are evaluated to show the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

The health development is one of the most important challenges in the world today. All human beings are affected by many diseases due to various circumstances like pollution, climate change, living habits, etc. Therefore, the improvement of predicting diseases is a very essential process in medical management. Prediction refers to the results of an algorithm after it has been trained on a dataset. It is a mathematical process that seeks to predict future outcomes by analyzing methods. Classification methods of machine learning can be used to find accurate prediction of disease by the symptoms. This paper reviews the gradient descent algorithm such as Logistic Regression and Artificial Neural Network. These models are highly applicable and deliver reliable prediction accuracy with the help of a dataset. The survey indicates that the most popular classification techniques are Artificial Neural Network and Logistic Regression. The major purpose of this study is to investigate the performance of various scaling methods, including ensemble normalization and standardization methods, for improving disease prediction. The study also presents a performance comparison of classification algorithms, with and without applying the feature scaling of the data preprocessing techniques. In the proposed system, two algorithms, Artificial Neural Network and Logistic Regression, were used for the classification. Firstly, the accuracy of Artificial Neural Network and Logistic Regression without scaling method was calculated. The results show that Artificial Neural Network produces the highest accuracy of 86.13% in predicting heart disease. Next, various scaling methods were applied with Artificial Neural Network and Logistic Regression algorithms to improve the accuracy of the prediction process. The experimental results show that the accuracy of Artificial Neural Network using Ensemble Normalization and Standardization is 98.81%, which is greater than the other accuracies. Finally, a statistical test was used to assess the significance of the difference in performance among the classifiers. [ABSTRACT FROM AUTHOR]

Recently, efficient techniques to remove indium ions from e-waste have been described due to their critical application. This paper illustrates the recovery of indium ions from an aqueous solution using a liquid membrane. CyphosIL 104 described the excellent potential for the extraction of indium ions. Evaluation of the five process parameters, such as indium concentration (10–100 mg/L), carrier concentration (0.05–0.2 mol/L), feed phase acidity (0.01–3 mol/L), chloride ion concentration (0.5–4 mol/L) and the stripping agent concentration (0.1–5 mol/L) were conducted. The interactive impacts of the various parameters on the extraction efficiency were investigated. The response surface methodology (RSM) and artificial neural network (ANN) were employed to model and compare the FS-SLM process results. RSM model with a quadratic equation (R2 = 0.9589) was the most suitable model for describing the efficiency. ANN model with six neurons showed a prediction of extraction efficiency with R2 = 0.9860. The best-optimized data were: 73.92 mg/L, 0.157 mol/L, 1.386 mol/L, 2.99 mol/L, and 3.06 mol/L for indium concentration, carrier concentration, feed phase acidity, chloride ion concentration, and stripping agent concentration. The results achieved by RSM and ANN led to an experimentally determined extraction efficiency of 93.91%, and 94.85%, respectively. It was close to the experimental data in the optimization condition (95.77%). Also, the evaluation shows that the ANN model has a better prediction and fitting ability to reach outcomes than the RSM model. [ABSTRACT FROM AUTHOR]

This paper presents the review of recent progress in photonic crystal fiber (PCF) and its applications. PCF possesses prominent potential for demonstrating various optical devices such as logic gates, combinational circuits, sensors, absorbers, etc. Recent development in PCFs incorporates the deep learning algorithms which deploy new functionalities and enhance the performance capacity in term of accuracy and optimization in comparison to conventional techniques based on Maxwell solver like finite element method (FEM), and plane wave expansion and finite difference time domain (FDTD) method. Thus, this review paper describes the overview of recent development along with historical background of PCFs and rigorous study on deep learning which incorporates neural network and machine learning algorithms like polynomial expansion method, gradient boost, and random forest. [ABSTRACT FROM AUTHOR]

Supercritical airfoils are critical components in the design of commercial wide-body aircraft wings due to their ability to enhance aerodynamic performance in transonic flow regimes. However, traditional design methods for supercritical airfoils can be time-consuming and require significant manual effort, not to mention the high cost associated with computational fluid dynamics analysis. To address these challenges, this paper introduces a highly automated approach for supercritical airfoil design, called Evolutionary Generative Design (EvoGD). The EvoGD approach is based on the framework of Evolutionary Computation and employs a series of sophisticated data-driven generative models incorporated with physical information to iteratively refine initial airfoil shapes, resulting in improved aerodynamic performances and reduced constraint violations. Moreover, to speed up the evaluation of the generated airfoils, a series of accurate and efficient data-driven predictors are utilized. The efficacy of the EvoGD approach was demonstrated through experiments on a dataset of 501 supercritical airfoils, including one baseline design and 500 randomly perturbed airfoils. On average, the generated airfoils showed improved performance in terms of buffet lift coefficient, cruise lift-to-drag ratio, and thickness by 5%, 4%, and 1%, respectively. The best generated airfoil outperformed the baseline design in terms of critical buffet lift coefficient and cruise lift-to-drag ratio by 7.1% and 6.4%, respectively. The entire design process was completed in less than an hour on a personal computer, highlighting the high efficiency and scalability of the EvoGD approach. [ABSTRACT FROM AUTHOR]

Predicting concrete strength is complex due to the high non-linearity involved in strength development, especially when using supplementary cementitious materials (SCMs) such as fly ash, silica fume, and GGBS. In this paper, an artificial neural network has been used to predict the compressive strength of concrete for four cases, namely concrete without cement replacement, and binary, ternary, and quaternary cement concretes corresponding to one, two and three different SCMs in the mix. To predict the strength accurately, a total of 1013 data were collected from 37 literature and trained using two training algorithms namely Levenberg-Marquardt (LM) and Bayesian Regularization (BR). The best predictions were achieved using one hidden layer with 14 and 15 neurons for LM and BR algorithms respectively. A high accuracy has been achieved with a correlation factor of 0.97 and 0.966 using the BR and LM algorithms respectively, with a20-index of 83%. Generally, the BR algorithm gives a better overall performance, while underestimating the compressive strength compared to LM. Sensitivity analysis has also been investigated using linear and quadratic regressions. The findings showed that the highest contributors to concrete strength were cement and water, while the lowest contributor was coarse aggregate. [ABSTRACT FROM AUTHOR]

One of the most challenging problems in cloud datacenters is the degradation of performance and energy efficiency due to the overutilization of hosts and their exposition to excessive workload. Virtual machine (VM) consolidation and migration from one host to another are strategies that have been proven to successfully bring about performance improvements and energy efficiency. These schemes help in energy optimization by moving VMs experiencing difficulty functioning on an overloaded host to another host. Similarly, by migrating VMs from an underloaded host and consolidating them, unnecessary resources have a chance to be shut down. This makes clear why the accurate detection of overloaded and underloaded hosts is of fundamental importance when energy consumption, quality of services, and service level agreements are targeted. In this paper, an energy-aware QoS-based consolidation algorithm is proposed to dynamically manage VMs in cloud datacenters. The proposed algorithm applies reinforcement learning and artificial neural networks. The first method is used to select a suitable VM for migration, while the latter helps to predict the future state of hosts and detect overloaded and underloaded hosts. We simulated the proposed algorithm using the CloudSim framework and compared it to the baselines and state-of-the-art algorithms. The results show that the proposed approach surpasses other methods in what concerns both performance and energy efficiency. [ABSTRACT FROM AUTHOR]

Numerous data centers have adopted heterogeneous computing server to accelerate the processing speed with various applications. However, as the growth of efficiency, the issue of high power consumption is increasingly becoming crucial. Traditional researchers focus on the developing strategies for power efficiency that neglects the importance of power prediction that substantially impacts on energy planning on data center. Different to the previous work, this paper utilizes the advantage of Artificial Neural Network (ANN) to design and implement an improved algorithm of power consumption prediction on heterogeneous computing server with various types of jobs. First, the impact of multi-type of jobs has been taken into account, i.e., CPU-intensive, memory-intensive, I/O-intensive and GPU-intensive. We collect the data trace from these jobs by a set of benchmarks. Then, based on the collected data trace, power prediction algorithm has been established, so that developing an improved ANN-based power consumption prediction algorithm with CNN-BiLSTM neural network and attention mechanism. Specifically, one dimensional CNN is utilized to perform local feature extraction and dimension reduction on the input, the BiLSTM network is adopted to extract high-level features from the above results. The miscellaneous features extracted are filtered out by using attention mechanism. Last, the experiment has been conducted, and the peculiarity for four types of jobs has been discussed. Compared with the latest proposed ANN-based prediction power algorithms, our proposed algorithm has better performance in prediction accuracy on power consumption. [ABSTRACT FROM AUTHOR]

Soft computational algorithms enhance the understanding, prediction, and classification of engineering and environmental problems. In Nigeria, works that have used these techniques in modeling soil erodibility are scarce. In this paper, several soft computing methods were integrated to assess and model the geotechnical and geomechanical characteristics of gully soils in Southeast Nigeria. Standard methods were employed for soil geotechnical analysis. Relationships between geotechnical parameters were estimated using R-type hierarchical clustering (HC), principal component analysis (PCA), and factor analysis (FA). Soil erodibility in the area was classified using Q-type HC and K-means clustering (KMC) algorithms. Moreover, gradient descent-optimized multilayer perceptron (GD-MLP) and multiple linear regression (MLR) models were developed to simulate and predict the soil properties, including fines %, sand %, gravel %, plasticity index, cohesion, and friction angle. This research indicated that: (1) all the analyzed soils have moderate–high erodibility characteristics, with high erodibility tendency predominant; (2) the PCA, FA, and R-type HC effectively captured the relationships of the geotechnical variables; (3) the Q-type HC and KMC models produced moderate and high erodibility clusters at 1:4 ratios; and (4) with low modeling errors, the MLR and GD-MLP accurately predicted the soil properties. However, overall, the MLR models (with R2 range of 0.976–1.000) outperformed the GD-MLP models (with R2 range of 0.924–0.998 and area under curve range of 0.900–0.948). Although high model performances were recorded in this work, future studies are encouraged to advance its findings. [ABSTRACT FROM AUTHOR]

In this era of e-commerce, many companies are moving towards subscription-based invoicing platforms to maintain their electronic invoices. Unfortunately, fraudsters are using these platforms for different types of malicious activities. Identifying fraudsters is often challenging for many companies due to the limitation of time and other resources. A fully automated fraud detection model can be useful, but it creates a risk of false-positive identification. This paper proposed a hybrid fraud detection framework when only a small set of labelled (fraud/non-fraud) data is available, and human input is required in the final decision-making step. This framework used a combination of unsupervised and supervised machine learning, red-flag prioritization, and an augmented AI approach containing a human-in-the-loop process. It also proposed a weighted center based on the feature importance scores for the fraud risk cluster and used it in the red-flag prioritization process. Finally, the approach is illustrated using a case study to identify fraudulent users in an invoicing platform. Our hybrid framework showed promising results in identifying fraudulent users and improving human performance when human input is required to make the final decision. [ABSTRACT FROM AUTHOR]

In many fields, the interpretability of machine learning models holds equal importance to their prediction accuracy. Highly accurate predictions are possible with a multilayer perceptron (MLP) neural network, but its application in high-risk fields is constrained by its lack of interpretability. To solve this issue, this paper introduces an MLP with a presingle-connection layer (SMLP). The SMLP incorporates a single-to-single connection layer with the ReLU function before the original MLP. By examining the weights of the single-connection layer after training the model, the significance of the input features can be determined. The experimental results demonstrate that this method can accurately measure the feature importance with the MLP. It offers advantages such as a straightforward theory, practical implementation, strong stability, and high reliability when compared with other widely used feature importance algorithms. Moreover, this measure effectively reveals the black box of the MLP, indicates the influence of input features on the prediction, and provides a quantitative standard for feature selection in MLP. [ABSTRACT FROM AUTHOR]

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness affecting the retina of low birth weight preterm infants. Plus disease in ROP characterised by abnormal tortuosity and dilation of posterior retinal blood vessels, is a benchmark that identifies treatment-requiring ROP cases. A Plus disease classifier with zero false negatives is a major requirement of an ROP screening system. In this paper, an efficient Artificial Neural Network (ANN) architecture with an optimal feature set is proposed which meets the above requirement. A total of 178 images with 81(45%) Plus and 97 (55%) No Plus are used for the analysis. A feature set derived from transform domain representation of retinal funds images is used along with the existing vascular features in the proposed work. Wavelet and Curvelet transforms are considered for deriving the additional feature set in the experimental analysis. The feature set containing Curvelet transform energy coefficient along with the vascular features gave an Accuracy of 96% and Specificity of 93% with 100% Sensitivity. [ABSTRACT FROM AUTHOR]

This research aims to see how well back-propagation neural network (BPNN) approaches perform in estimating peak ground acceleration in the Himalayan region using various forms of input data (i.e., magnitude, focal depth, hypocentre and S-wave avg. velocity). These criteria were derived from the Himalayan Earthquake Catalogue, which includes all minor and significant earthquakes and their aftershock sequences in prior years. The analysis of high-quality seismological recorded data is important for earthquake prediction. The BPNN is employed for predicting the strong ground motion parameters such as peak ground acceleration, peak ground velocity and peak ground displacement using different activation functions at different layers. This research paper focuses on the model's training to analyze the dataset, including a few parameters to estimate the acceleration of the ground. Translated data into seismicity indicators, which are mathematically derived parameters. These seismicity indicators were utilized for the training of the BPNN to improve decision-making and for peak ground acceleration estimation. Artificial neural network models were used to predict the ground motion intensity measures for future events. The predictive parameters' contributions to the prediction of the considered intensity measurements are finally explored via sensitivity analysis. This study uses the multi-layer BPNN model to discover components in the Himalayan region, using the actual incidence of earthquake seismicity indicators as input and goal vectors. Finally, the BPNN model produces a good estimate for the peak ground acceleration of earthquakes. [ABSTRACT FROM AUTHOR]

This paper proposes a solution to enhance and compare different neural network (NN)-based side-slip angle estimators. The feed-forward neural networks (FFNNs), recurrent neural networks, long short-term memory units (LSTMs), and gated recurrent units are investigated. However, there is a lack in the selection criteria of the architectures' hyper-parameters. Therefore, the genetic algorithm is integrated with the NN-based estimators to find the optimal hyper-parameters for the studied architectures. The tuned hyper-parameters in this work include the number of neurons, number of layers, activation function, optimizer type, and learning rate. The objective function of the optimization problem is minimizing the root-mean-square error (RMSE) on multiple testing data. The optimal models are further included in the design of a hybrid NN estimator with Kalman filter. In the hybrid estimators, the optimal NN estimators are used as virtual sensors to correct the prediction of the side-slip angle resulting from the mathematical lateral vehicle model. Eventually, the performance of the best selected model is evaluated in terms of different metrics; mean RMSE, mean error variance, mean training time, and mean estimation time. LSTMs are found to achieve the lowest mean RMSE while being tested on highly generalized data yielding the highest training and estimation time. However, FFNNs achieve the lowest RMSE while being tested on low generalized data and the lowest training and estimation time. Meanwhile, it is observed that the hybrid estimators achieved lower RMSE with great enhancement compared to the non-hybridized ones proving the effectiveness of the proposed approach and increasing the side-slip estimation generalization ability in unknown environments with high uncertainties, which are not covered by the training dataset for the NNs estimators. [ABSTRACT FROM AUTHOR]

This paper introduces a novel hybrid approach for predicting the rainfall-runoff (r-r) phenomenon across different data division scenarios (50%-50%, 60%-40%, and 75%-25%) within two distinct watersheds, encompassing both monthly and daily scales. Additionally, the effectiveness of this newly proposed hybrid method is evaluated in multi-step ahead prediction (MSAP) scenarios. The proposed method comprises three primary steps. Initially, to address the non-stationarity of the runoff and rainfall time series, these series are decomposed into multiple sub-time series using the wavelet (WT) decomposition method. Subsequently, in the second step, the decomposed sub-series are utilized as input data for the M5 model tree, a decision tree-based model. The M5 model tree classifies the samples of decomposed runoff and rainfall time series into distinct classes. Finally, each class is modeled using an artificial neural network (ANN). The results demonstrate the superior efficiency of the proposed WT-M5-ANN method compared to other available hybrid methods. Specifically, the calculated R2 was 0.93 for the proposed WT-M5-ANN method, whereas it was 0.89 and 0.81 for the WT-ANN (WANN) and WT-M5 methods, respectively, for the Lobbs Hole Creek watershed at the daily scale. [ABSTRACT FROM AUTHOR]

The evaluation of uterine contraction offers significant information regarding the progression of labour. The occurrence of deliveries before the expected dates leads to undesirable consequences for the mother and fetus. Electrohysterography (EHG) is a non-invasive monitoring scheme generally preferred to detect preterm delivery and reduce the hostile consequences. This paper proposed a novel term and preterm prediction method for predicting preterm deliveries by employing EHG signals. The proposed scheme involves three phases: pre-processing, feature extraction and prediction. Initially, the acquired EHG signals are pre-processed using a band pass filter and wavelet transform to remove noise and artefacts from the EHG signal. The second stage is feature extraction, where the representative features, including Shannon energy, median frequency, time-varying centroid frequency, etc., are extracted. At last, the prediction is carried out using an enhanced sheep flock optimized hybrid extreme artificial neural learning network (ESFHEANL). ESFHEANL is the combination of a hybrid extreme artificial neural learning network (HEANL) and enhanced sheep flock optimization (ESFO) algorithm. It assists in diagnosing the term and preterm birth more accurately. The proposed scheme is implemented in the Python platform and assessed the performance in terms of accuracy, recall, specificity and f-measure using the term-preterm EHG (TPEHG) database. Finally, the experimental outcomes evidenced that the proposed scheme achieved better performance and was employed to diagnose term and preterm births accurately. [ABSTRACT FROM AUTHOR]

Flow lines are often used to perform assembly operations in multi-stage processes. During these assembly operations, components that are relatively small, compared to the work pieces travelling down the flow line, are mounted to the work pieces at a given stage. Those components, or more generally, any kind of auxiliary material, are provisioned to the corresponding production stage in a repetitive but not necessarily deterministic manner using a certain delivery frequency, each time filling the local storage up to a predetermined order-up-to level. Just like random processing times, machine failures, and repairs, the randomness of the provisioning process can impact the long-term throughput of such a flow line. In this paper, we develop a fast and accurate analytical performance evaluation method to estimate the long-term throughput of a Markovian flow line of this type for the practically important case of limited buffer capacities between the production stages. We first give an exact characterization of a two-machine line of that type and show how to determine system state probabilities and aggregate performance measures. Furthermore, we show how to use this two-machine model as the building block of an approximate decomposition approach for longer flow lines. As opposed to previous decomposition approaches, even the state space of the two-machine lines can become so large that an exact solution of the Markov chains can become impractical. We hence show how to set up, train, and use an artificial neural network to replace the Markov chain solver embedded in the decomposition approach, which then leads to an accurate and extremely fast flow line evaluation tool. The proposed methodology is evaluated by a comparison with simulation results and used to characterize the structural patterns describing the behaviour of flow lines of this type. The method can be used to systematically consider the combined impact of the delivery frequency and the local order-up-to levels for the auxiliary material when designing a flow line of this type. [ABSTRACT FROM AUTHOR]

The thermal efficiency for the pelletizing process is intrinsically linked to the diameter and humidity of the iron ore pellets, so that the sensing of the granulometric range in the formation of the pellets becomes essential to the flow of the pelletizing process in the steel industry; this paper presents the assembly of a computer vision system for the detection and segmentation of pellets aiming at the automation of the granulometric measurement, following its formation in the pelletizing disk, using the instance segmentation method to verify whether the particle granulometric distribution (PSD) is adequate for "real-time" applications. The system calculates the normal distribution of the diameter in millimeters, evaluating the normal curve and the standard deviation of the segmented pellets, using a deep neural network based on the You Only Look At CoefficienTs (YOLACT) network, adding speed and precision in the granulometric analysis. In the sample sets, the need for adjustment factors inherent to the pelletizing process became evident. This led to the establishment of the computer vision system, termed the Volumetric Correction Factor (VCF) and Visual Overlay Factor (VOF). The VCF is utilized to estimate the volume of pellets within the pelletizing disk during operation, while the VOF adjusts the millimeter-per-pixel (mpp) ratio. The results of the measurement system proved to be efficient in real-time granulometric measurement. [ABSTRACT FROM AUTHOR]

In rubber extrusion, precise temperature control is critical due to the process's sensitivity to fluctuating parameters like compound behavior and batch-specific material variations. Rapid adjustments to temperature deviations are essential to ensure stable throughput and extrudate surface integrity. Based on our previous research, which initiated the development of a feedforward neural network (FNN) without real-world empirical application, we now present a real-time control system using artificial neural networks (ANNs) for dynamic temperature regulation. The underlying FNN was trained on a dataset comprising different ethylene propylene diene monomer (EPDM) rubber compounds, totaling 14,923 measurement points for each temperature value. After training, the FNN achieves remarkable precision, evidenced by a mean absolute percentage error (MAPE) of 0.68% and a mean squared error (MSE) of 0.63°C2 in predicting temperature variations. Its integration into the control system enables real-time responsiveness, allowing for adjustments to temperature deviations within an average timeframe of 68 ms. A key advantage over proportional-integral-derivative (PID) controllers is the ability to continuously learn and adjust to complex, non-linear, and batch-specific process dynamics. This adaptability results in enhanced process stability, as evidenced by inline manufacturing validation. Our paper presents the first ANN-based rubber extrusion control, demonstrating how machine learning techniques can be effectively leveraged for real-time, adaptive temperature control. Beyond rubber extrusion, this strategy has potential applications in various polymer processing and other industries requiring precise temperature control. Future trends may involve the integration of online learning techniques and the expansion of interconnected manufacturing processes. [ABSTRACT FROM AUTHOR]

Bubble point oil formation volume factor (Bob) and solution gas–oil ratio (Rs) are two crucial PVT parameters used for modeling and volumetric calculations in petroleum industry. They are usually determined in laboratory or estimated using empirical correlations. Experimental methods are time-consuming and expensive where empirical correlations have limitations. Artificial intelligence can be sued overcome these limitations to develop more accurate, robust, and quick predictive tools. In this paper, we used three artificial neural network algorithms to develop intelligent models to predict Bob and Rest using 465 experimental data. Application of the Elman neural network (ENN) for this purpose is being reported for the first time. A variety of input parameters were selected based on a sensitivity analysis which include reservoir temperature (T), oil API gravity (°API), bubble point pressure (Pb), gas-specific gravity (γg), and Rs was used to predict the Bob. T, °API, Pb, γg, and Bob was used to predict the Rs. The ENN model was found superior to the other developed smart models and the empirical correlations with coefficient of determination (R2) of 0.993, root mean square error (RMSE) of 0.0093, and average absolute percent relative error (AAPRE) of 0.93% for the Bob and 0.999, 0.016, and 6.72% for the Rs, respectively. The ENN network has fewer adjustable parameters and provides faster training capabilities using fewer neurons and hidden layers compared to other ANN algorithms. The developed smart predictive tools can be safely used instead of laboratory methods and empirical correlations for a much wider ranges of input parameters and with higher accuracy and confidence. [ABSTRACT FROM AUTHOR]

In 2022, the World Health Organization declared an outbreak of monkeypox, a viral zoonotic disease. With time, the number of infections with this disease began to increase in most countries. A human can contract monkeypox by direct contact with an infected human, or even by contact with animals. In this paper, a diagnostic model for early detection of monkeypox infection based on artificial intelligence methods is proposed. The proposed method is based on training the artificial neural network (ANN) with the adaptive artificial bee colony algorithm for the classification problem. In the study, the ABC algorithm was preferred instead of classical training algorithms for ANN because of its effectiveness in numerical optimization problem solutions. The ABC algorithm consists of food and limit parameters and three procedures: employed, onlooker and scout bee. In the algorithm standard, artificial onlooker bees are produced as much as the number of artificially employed bees and an equal number of limit values are assigned for all food sources. In the advanced adaptive design, different numbers of artificial onlooker bees are used in each cycle, and the limit numbers are updated. For effective exploitation, onlooker bees tend toward more successful solutions than the average fitness value of the solutions, and limit numbers are updated according to the fitness values of the solutions for efficient exploration. The performance of the proposed method was investigated on CEC 2019 test suites as examples of numerical optimization problems. Then, the system was trained and tested on a dataset representing the clinical symptoms of monkeypox infection. The dataset consists of 240 suspected cases, 120 of which are infected and 120 typical cases. The proposed model's results were compared with those of ten other machine learning models trained on the same dataset. The deep learning model achieved the best result with an accuracy of 75%. It was followed by the random forest model with an accuracy of 71.1%, while the proposed model came third with an accuracy of 71%. [ABSTRACT FROM AUTHOR]

Current challenges in the field of luminescent materials are concerned with designing efficient material to meet the rapidly rising demands of industry. Luminescent material excitation and emission are highly complex phenomena driven by the combination of atomic-level properties such as valence electron, inter-atomic radius, ionic radius, etc., and physical properties such as crystal structure, symmetry, etc. The current research paper focuses on the development of a machine-learning algorithm based on simple luminescent materials to predict the excitation to the closest possible accuracy using easily accessible key attributes by the CatBoost regressor, multiple linear regression (MLR), and an artificial neural network (ANN) approach. These selected features likely correlate with the excitation of the material. In comparison, the ANN and MLR algorithms have higher mean absolute error values in both the training and test datasets. The CatBoost algorithm outperforms the other algorithms in terms of mean of the absolute percentage difference, achieving a value of 0.302136% in the training dataset. The CatBoost algorithm exhibits the lowest root mean squared error value of 1.680768 nm in the training dataset, indicating that its predictions have a smaller average deviation from the actual values. The style for studying the material property has the potential to reduce the cost and time involved in an Edisonian approach to the lengthy laboratory experiment to identify excitation. [ABSTRACT FROM AUTHOR]

Phononic crystals as manufactured materials have particular property called bandgap to control elastic wave propagation. The geometric and material parameters have considerable effects on bandgap, but the sensitivities of these parameters to the starting and ending frequencies, and width of bandgap are not yet clear, especially for three-dimensional and three-component PCs. Thus, in this paper, the generation mechanism of bandgap, the influences and sensitivities of geometric and material features on bandgap characteristics are fully investigated according to the improved plane wave expansion method, Sobol's sensitivity method, and artificial neural network. The results demonstrate that the artificial neural network prediction model with multiple hidden layers has good fitness, of which the coefficients of determination for the starting and ending frequencies are 0.9981 and 0.9982, respectively. The radius of the scatterer and the radius of the coating layer have the greatest influence, followed by the elastic modulus and Poisson's ratio of the coating layer on the starting and ending frequencies. The radius of the scatterer and lattice constant have the biggest effect, followed by the elastic modulus and radius of the coating layer on the bandgap width. [ABSTRACT FROM AUTHOR]

Despite the high efficiency of remote sensing methods for rapid and large-scale detection of subsidence phenomena, this technique has limitations such as atmospheric impact and temporal and spatial decorrelation that affect the accuracy of the results. This paper proposes a method based on an artificial neural network to improve the results of monitoring land subsidence due to groundwater overexploitation by radar interferometry in the Aliabad plain (Central Iran). In this regard, vertical ground deformations were monitored over 18 months using the Sentinel-1A SAR images. To model the land subsidence by a multilayer perceptron (MLP) artificial neural network, four parameters, including groundwater level, alluvial thickness, elastic modulus, and transmissivity have been applied. The model's generalizability was assessed using data derived for 144 days. According to the results, the neural network estimates the land subsidence at each ground point with an accuracy of 6.8 mm. A comparison between the predicted and actual values indicated a significant agreement. The MLP model can be used to improve the results of subsidence detection in the study area or other areas with similar characteristics. [ABSTRACT FROM AUTHOR]