Search

This investigation presents a paradigm-shifting Human Resource (HR) Assessment and Recommendation Framework, leveraging progressed huge information mining procedures. Drawing bits of knowledge from cybersecurity, healthcare, education, and further detecting spaces, our framework utilizes a different cluster of calculations, counting Arbitrary Forests, Support Vector Machines, K-Means Clustering, and a Feedforward Neural Organize. The comparative investigation uncovers the Feedforward Neural Network as the standout entertainer, emphasizing its various levels including learning for complicated design acknowledgement inside HR measurements. Uniquely, this framework draws on methodologies and insights from varied domains such as cybersecurity, healthcare, and education, applying these rich, interdisciplinary perspectives to HR analytics. This cross-pollination of ideas enables the framework to adopt sophisticated data mining and pattern recognition techniques that are not traditionally utilized within HR, offering new avenues for detecting and interpreting complex employee data patterns. Result values illustrate the system's adequacy, with a precision of 88%, an accuracy of 90%, a review of 87%, and an F1 score of 88%. These measurements emphasize the system's capacity to comprehensively assess worker execution, giving exact suggestions for key HR decision-making. Ethical contemplations, innovation acknowledgement, and custom-fitted proposal frameworks, propelled by related works, are coordinates to guarantee the system's reasonability over assorted organizational settings. This research contributes to the advancing scene of HR administration, offering a spearheading arrangement for organizations looking for data-driven, comprehensive, and morally sound approaches to workforce optimization. [ABSTRACT FROM AUTHOR]

AbstractIn this paper, we develop a novel efficient and robust nonparametric regression estimator under a framework of a feedforward neural network (FNN). There are several interesting characteristics for the proposed estimator. First, the loss function is built upon an estimated maximum likelihood function, which integrates the information from observed data as well as the information from the data distribution. Consequently, the resulting estimator has desirable optimal properties, such as efficiency. Second, different from the traditional maximum likelihood estimation (MLE), the proposed method avoids the specification of the distribution, making it adaptable to various distributions such as heavy tails and multimodal or heterogeneous distributions. Third, the proposed loss function relies on probabilities rather than direct observations as in least square loss, contributing to the robustness of the proposed estimator. Finally, the proposed loss function involves a nonparametric regression function only. This enables the direct application of the existing packages, simplifying the computational and programming requirements. We establish the large sample property of the proposed estimator in terms of its excess risk and minimax near-optimal rate. The theoretical results demonstrate that the proposed estimator is equivalent to the true MLE where the density function is known in terms of excess risk. Our simulation studies show that the proposed estimator outperforms the existing methods based on prediction accuracy, efficiency and robustness. Particularly, it is comparable to the MLE with the known density and even gets slightly better as the sample size increases. This implies that the adaptive and data-driven loss function from the estimated density may offer an additional avenue for capturing valuable information. We further apply the proposed method to four real data examples, resulting in significantly reduced out-of-sample prediction errors compared to existing methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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.)

This paper focuses on the emerging branch of the deep learning technique that is employed in the various simple and nonlinear mathematical models of one and two-dimension. This numerical technique takes advantage of the backpropagation algorithm and computational graph of deep learning. A computational ability of a feedforward neural network (FNN) has been further employed, which utilized the randomly or uniformly sampled collocation points over the physical domain and different boundary conditions. Furthermore, a loss function is formulated based on the mathematical model and boundary conditions which is further enforced to minimize the unlabeled sampled points. The minimization process of the loss function is achieved through the various optimizer during the backpropagation algorithm. Eventually, the training process of FNN completes after getting an admissible error for the solution. Multiple examples are tested and cross-validated with the exact solutions for the problem. Furthermore, the DL-based solutions have a good agreement with the solution obtained from finite element approach, indicating that the DL-based numerical techniques can be considered an alternate numerical technique for solving various mathematical models. [ABSTRACT FROM AUTHOR]

Harini Sriraman, Saleena Badarudeen, Saransh Vats, Prakash Balasubramanian School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, IndiaCorrespondence: Prakash Balasubramanian, School of Computer Science Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu, India, Tel +91-044-39931228, Fax +91-044-39932555, Email Prakash.bala@vit.ac.inAbstract: Deep Learning (DL) drives academics to create models for cancer diagnosis using medical image processing because of its innate ability to recognize difficult-to-detect patterns in complex, noisy, and massive data. The use of deep learning algorithms for real-time cancer diagnosis is explored in depth in this work. Real-time medical diagnosis determines the illness or condition that accounts for a patient’s symptoms and outward physical manifestations within a predetermined time frame. With a waiting period of anywhere between 5 days and 30 days, there are currently several ways, including screening tests, biopsies, and other prospective methods, that can assist in discovering a problem, particularly cancer. This article conducts a thorough literature review to understand how DL affects the length of this waiting period. In addition, the accuracy and turnaround time of different imaging modalities is evaluated with DL-based cancer diagnosis. Convolutional neural networks are critical for real-time cancer diagnosis, with models achieving up to 99.3% accuracy. The effectiveness and cost of the infrastructure required for real-time image-based medical diagnostics are evaluated. According to the report, generalization problems, data variability, and explainable DL are some of the most significant barriers to using DL in clinical trials. Making DL applicable for cancer diagnosis will be made possible by explainable DL.Keywords: artificial intelligence, AI, machine learning, DL, CNN, healthcare, real-time diagnosis, classification, image processing, elastography, feedforward neural network

AbstractAdvanced reactor designers are looking to maximize the system capacity factor to make advanced reactors more economically competitive and meet the projected energy demand. To achieve this goal, we propose a Dynamic Operation and Maintenance Optimization (DyOMO) framework to perform system-level predictive maintenance (PdM) using a dynamic Bayesian network and component-specific PdM using deep neural networks. At the system level, DyOMO detects the presence of anomalous phenomena, determines the most influential degradation mode, and estimates the remaining useful life (RUL) distribution for the system. At the component level, DyOMO summarizes the health state of key system components, determines the presence of an anomaly using a feedforward neural network, and predicts component RUL using a Bayesian neural network. To evaluate the overall performance of DyOMO, normal operations of a Pebble-Bed High-Temperature Gas-cooled Reactor (PB-HTGR) were simulated with realistic component degradation for the steam turbine and steam generator. Across the 20 independent reactor life simulations, it was found that maintenance was always performed before any safety limits were violated and before a component failed. Specifically, the system-level PdM suggested maintenance on the steam generator once the steam pressure approached its safety limit, and the component-specific PdM suggested maintenance on the steam turbine once the turbine blade hardness degraded. The results indicate that through the continuous monitoring of the system and individual components, the DyOMO framework improves safety and increases the availability of the reactor when compared to traditional maintenance philosophies. [ABSTRACT FROM AUTHOR]

Aiming at the design problem of aviation swarm combat course of action (COA), considering the influence of stochastic parameters in the causal relationship model and optimization problem model, according to the dynamic influence net (DIN) theory, stochastic simulation technique, feedforward neural network (FNN) function approximation technique and multi-objective artificial fish school algorithm (MOAFSA), this paper proposed a COA optimized method based on DIN and multi-objective stochastic chance constraint optimization for aviation swarm combat. First, on the basis of establishing the overall framework of the model and defining the elements of causal relationship modeling, the static and dynamic causal relationship modeling and optimization problem modeling were carried out respectively. Second, the probability propagation mechanism of DIN was established, which mainly included two aspects, i.e., the overall process and the specific algorithm. Then, input and output data were generated based on stochastic simulation. According to these data, FNN was adopted for function approximation, and MOAFSA was adopted for iterative optimization. Finally, the rationality of the model, and the effectiveness and superiority of the algorithm were verified through multiple sets of simulation cases. [ABSTRACT FROM AUTHOR]

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

Purpose Methods Results Conclusions The purpose of this study is to compare the reconstructed corneal power (RCP) by working backwards from the post‐implantation spectacle refraction and toric intraocular lens power and to develop the models for mapping preoperative keratometry and total corneal power to RCP.Retrospective single‐centre study involving 442 eyes treated with a monofocal and trifocal toric IOL (Zeiss TORBI and LISA). Keratometry and total corneal power were measured preoperatively and postoperatively using IOLMaster 700. Feedforward neural network and multilinear regression models were derived to map keratometry and total corneal power vector components (equivalent power EQ and astigmatism components C0 and C45) to the respective RCP components.Mean preoperative/postoperative C0 for keratometry and total corneal power was −0.14/−0.08 dioptres and −0.30/−0.24 dioptres. All mean C45 components ranged between −0.11 and −0.20 dioptres. With crossvalidation, the neural network and regression models showed comparable results on the test data with a mean squared prediction error of 0.20/0.18 and 0.22/0.22 dioptres2 and on the training data the neural network models outperformed the regression models with 0.11/0.12 and 0.22/0.22 dioptres2 for predicting RCP from preoperative keratometry/total corneal power.Based on our dataset, both the feedforward neural network and multilinear regression models showed good precision in predicting the power vector components of RCP from preoperative keratometry or total corneal power. With a similar performance in crossvalidation and a simple implementation in consumer software, we recommend implementation of regression models in clinical practice. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) 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.)

The selection of weight initialization in an artificial neural network is one of the key aspects and affects the learning speed, convergence rate and correctness of classification by an artificial neural network. In this paper, we investigate the effects of weight initialization in an artificial neural network. Nguyen-Widrow weight initialization, random initialization, and Xavier initialization method are paired with five different activation functions. This paper deals with a feedforward neural network, consisting of an input layer, a hidden layer, and an output layer. The paired combination of weight initialization methods with activation functions are examined and tested and compared based on their best achieved loss rate in training. This work aims to better understand how weight initialization methods in neural networks, in combination with activation functions, affect the learning speed in comparison after a fixed number of training epochs. [ABSTRACT FROM AUTHOR]

Abstract Suspended sediment concentration prediction is critical for the design of reservoirs, dams, rivers ecosystems, various operations of aquatic resource structure, environmental safety, and water management. In this study, two different machine models, namely the cascade correlation neural network (CCNN) and feedforward neural network (FFNN) were applied to predict daily-suspended sediment concentration (SSC) at Simga and Jondhara stations in Sheonath basin, India. Daily-suspended sediment concentration and discharge data from 2010 to 2015 were collected and used to develop the model to predict suspended sediment concentration. The developed models were evaluated using statistical indices like Nash and Sutcliffe efficiency coefficient (NES), root mean square error (RMSE), Willmott’s index of agreement (WI), and Legates–McCabe’s index (LM), supplemented by a scatter plot, density plots, histograms and Taylor diagram for graphical representation. The developed model was evaluated and compared with CCNN and FFNN. Nine input combinations were explored using different lag-times for discharge (Qt-n) and suspended sediment concentration (St-n) as input variables, with the current suspended sediment concentration as the desired output, to develop CCNN and FFNN models. The CCNN4 model with 4 lagged inputs (St-1, St-2, St-3, St-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest NES = 0.0.662, WI = 0.890 and LM = 0.668 for the Jondhara Station while the same CCNN4 model secure as the best with the lowest RMSE = 53.71 mg/l and the highest NES = 0.785, WI = 0.936 and LM = 0.788 for the Simga Station. The result shows the CCNN model was better than the FFNN model for predicting daily-suspended sediment at both stations in the Sheonath basin, India. Overall, CCNN showed better forecasting potential for suspended sediment concentration compared to FFNN at both stations, demonstrating their applicability for hydrological forecasting with complex relationships.

Photonic neural networks (PNNs), utilizing light-based technologies, show immense potential in artificial intelligence (AI) and computing. Compared to traditional electronic neural networks, they offer faster processing speeds, lower energy usage, and improved parallelism. Leveraging light's properties for information processing could revolutionize diverse applications, including complex calculations and advanced machine learning (ML). Furthermore, these networks could address scalability and efficiency challenges in large-scale AI systems, potentially reshaping the future of computing and AI research. In this comprehensive review, we provide current, cutting-edge insights into diverse types of PNNs crafted for both imaging and computing purposes. Additionally, we delve into the intricate challenges they encounter during implementation, while also illuminating the promising perspectives they introduce to the field. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV), specifically a quadcopter is publicly popular which it provides services in different applications such as aerial delivery, aerial photography, military, weather forecasting and more examples to date. A Proportional-Integral-Derivative (PID) controller is one of the control techniques that can provide stabilization and reliable trajectory tracking. However, proper PID gains are needed to ensure a stable flight and it should be hybridized or improved to increase the robustness, reliability, and stabilization during flight. In this paper, an intelligent PID controller using neural network is proposed based on Levenberg-Marquardt feedforward neural network training method. The PID gains are initialized using different ranges according to the optimal gains generated by Particle Swarm Optimization, and this contributes towards a good training performance using Mean Square Error (MSE) evaluation. The trained network takes desired output and references as input data to calculate the required combination of PID gains as the output. The including of the response characteristics as the input data for the network, together with reference, error, and control input is the significance of the work. The performance of this work is presented using MSE performances, attitudes and altitude stabilization, and trajectory tracking reliability through error index performances. The simulation results graphically prove that the proposed controller provides better stability with reduced overshoot and settling times. Disturbance rejection is also enhanced by 1.7% compared to manual tuned PID controller. The reliability of the proposed controller highlights avenues for further exploration in AI-driven control strategies for quadcopter systems. [ABSTRACT FROM AUTHOR]

Background: Intraocular lenses (IOLs) require proper positioning in the eye to provide good imaging performance. This is especially important for premium IOLs. The purpose of this study was to develop prediction models for estimating IOL decentration, tilt and the axial IOL equator position (IOLEQ) based on preoperative biometric and tomographic measures. Methods: Based on a dataset (N = 250) containing preoperative IOLMaster 700 and pre-/postoperative Casia2 measurements from a cataractous population, we implemented shallow feedforward neural networks and multilinear regression models to predict the IOL decentration, tilt and IOLEQ from the preoperative biometric and tomography measures. After identifying the relevant predictors using a stepwise linear regression approach and training of the models (150 training and 50 validation data points), the performance was evaluated using an N = 50 subset of test data. Results: In general, all models performed well. Prediction of IOL decentration shows the lowest performance, whereas prediction of IOL tilt and especially IOLEQ showed superior performance. According to the 95% confidence intervals, decentration/tilt/IOLEQ could be predicted within 0.3 mm/1.5°/0.3 mm. The neural network performed slightly better compared to the regression, but without significance for decentration and tilt. Conclusion: Neural network or linear regression-based prediction models for IOL decentration, tilt and axial lens position could be used for modern IOL power calculation schemes dealing with 'real' IOL positions and for indications for premium lenses, for which misplacement is known to induce photic effects and image distortion. [ABSTRACT FROM AUTHOR]

Atrial Fibrillation (AFib) and its associated symptoms are significant problems that doctors and several studies have attempted to solve throughout the years. It is diagnosed by analyzing a patient’s electrocardiogram (ECG) data. However, continuous efforts have been made to develop an algorithm that detects AFib with optimal efficiency and cost-effectiveness. In this study, a sequential model was used based on feedforward neural network as this is arguably the simplest algorithm developed and requires minimal computing power. The results showed that training the algorithm for 1000 epochs yielded the best results. Further studies showed that using a combination of 10-fold cross-validation and blindfold validation proved an ideal way to determine the model's capabilities in distinguishing patients with AFib from those without. In conclusion, the developed model successfully distinguished between AFib and non-AFib patients with a 96.67% sensitivity, 94.61% specificity, and 95.64% accuracy.

The precise ascertainment of stellar ages is pivotal for astrophysical research into stellar characteristics and galactic dynamics. To address the prevalent challenges of suboptimal accuracy in stellar age determination and limited proficiency in apprehending nonlinear dynamics, this study introduces an enhanced model for stellar age determination, amalgamating the Feedforward Neural Network (FFNN) with TabNet (termed FFNN–TabNet). The methodology commences with the acquisition of a stellar dataset via meticulous cross-matching. Subsequent advancements encompass refinements to the activation functions within TabNet, coupled with augmentations to the Attentive transformer module by incorporating an FFNN module. These enhancements substantially boost training efficiency and precision in age estimation while amplifying the model's capability to decode complex nonlinear interactions. Leveraging Bayesian Optimization Algorithm (BOA) for hyperparameter fine-tuning further elevates the model's efficiency. Comprehensive ablation and comparative analyses validate the model's superior performance in stellar age determination, demonstrating marked enhancements in accuracy. The experiment also demonstrates an enhanced ability of the model to capture nonlinear relationships between features. [ABSTRACT FROM AUTHOR]

A path-following control method based on dual heuristic programming (DHP) is proposed to address the problem whereby unmanned articulated vehicles need to set different controller parameters to track complex routes and cannot adapt to complex routes. First, the path-following control system structure is designed based on the articulated vehicle experimental platform, and the error model is derived based on the kinematic model of the articulated vehicle. Second, the payoff function is designed considering the error and stability indices, and the actor and critic of the path-following control method based on the DHP algorithm are approximated using a multilayer feedforward neural network. Finally, the path-following quality of the method is verified using simulations and real vehicle tests and compared with the conventional pure tracking and linear-quadratic regulator methods. The results show that the DHP-based method is able to follow complex reference paths and obtain better control results than the traditional methods without iterative tuning of the controller parameters, which improves the adaptiveness of the articulated vehicle path-following control method to complex environments. [ABSTRACT FROM AUTHOR]

This article proposes the use of a feedforward neural network (FNN) to select the starting point for the first iteration in well-known iterative location estimation algorithms, with the research objective of finding the minimum size of a neural network that allows iterative position estimation algorithms to converge in an example positioning network. The selected algorithms for iterative position estimation, the structure of the neural network and how the FNN is used in 2D and 3D position estimation process are presented. The most important results of the work are the parameters of various FNN network structures that resulted in a 100% probability of convergence of iterative position estimation algorithms in the exemplary TDoA positioning network, as well as the average and maximum number of iterations, which can give a general idea about the effectiveness of using neural networks to support the position estimation process. In all simulated scenarios, simple networks with a single hidden layer containing a dozen non-linear neurons turned out to be sufficient to solve the convergence problem. [ABSTRACT FROM AUTHOR]

The existing smog-haze forecast methods less consider about the influence of precipitable water vapor, and most of the prediction methods do not effectively handle the model regression residuals, so the prediction accuracy is not very high. For these issues, the PM2. 5 daily mean value data of four cities in Guangxi (Nanning, Guilin, Wuzhou and Baise) in 2017 combining with the factors of air pollutants, meteorological factors and precipitable water vapor (PWV), ARIMA models of the whole year and each quarter are respectively established to make short-term prediction of daily average PM2. 5 concentration in this region. The forecast residuals of ARIMA model are respectively fitted with the feedforward neural network radical basis function (RBF) and multi-layer perceptron (MLP) in order to optimize ARIMA model. The results show, except Guilin, the prediction effect of quarterly ARIMA model is better than the annual ARIMA model, and the quarterly ARIMA-MLP neural network prediction accuracy is better than the quarterly ARIMA model, indicating that this kind of model can be used for regional PM2. 5 concentration prediction. [ABSTRACT FROM AUTHOR]

The investigation of neural network convergence represents a pivotal and indispensable area of research, as it plays a crucial role in unraveling the universal approximation capability and the intricate structural complexity inherent in these systems. In this study, we delve into an innovative and generalized convex incremental iteration method, which surpasses previous studies by offering a more expansive formulation capable of encompassing a broader range of weight parameters. Moreover, we rigorously and systematically demonstrate the convergence rate of this convex iteration technique, shedding light on its reliability and effectiveness. Furthermore, we adopt a discrete statistical perspective to effectively tackle the challenges arising from the non-compactness of input data and the inherent unknowability of the objective function in practical settings, thereby enhancing the robustness and applicability of our research. To support our conclusions, we introduce two implementation algorithms, namely back propagation and random search. The latter algorithm plays a vital role in preventing the neural network from becoming entrapped in suboptimal local minima during the training process. Finally, we present comprehensive results obtained from a variety of regression problems, which not only serve as empirical evidence of the superior performance of our algorithms but also validate their alignment with our theoretical predictions. These results contribute significantly to the advancement of our understanding of neural network convergence and its profound implications for the universal approximation capability inherent in these complex systems. [ABSTRACT FROM AUTHOR]

Least squares estimate that can directly obtain the analytical solution to minimize the mean square error (MSE) is one of the most effective regression tools. It has also been applied to many classification tasks due to its simplicity, clear physical and tractability. However, there is a fundamental contradiction between regression with continuous samples and classification with discrete category labels, i.e., the output metric spaces are different. Considering this contradiction in regression-based classification, this paper presents a new linear classifier, termed penalized least squares classifier (PLSC), which gradually adds the penalty on the distance between misclassified samples and decision boundary to the loss function. Fundamentally, the decision boundary is obtained by minimizing MSE with iterative cost-sensitive learning. Then, an enhanced nonlinear neural network classifier, PLSC-BP is formulated, in which the penalized least squares mechanism is applied to tune the learning strategy of the conventional neural network by adjusting the cost factor for each sample. Extensive experiments on six synthetic datasets and eleven publicly available datasets show that classification, which cannot be realized by traditional least squares, can be conducted using a regression algorithm with iterative cost-sensitive learning. The proposed enhanced algorithm outperforms the traditional neural network classifiers and other classifiers in terms of classification. [ABSTRACT FROM AUTHOR]

Corrugated board is an environmentally friendly, commonly used packing material. Its basic structure consists of two liners and a flute between them. The mechanical properties and strength of the corrugated board depend not only on the constituent papers but also its geometry, which can be distorted, however, due to various factors related to its manufacturing process or use. The greatest distortion occurs in the corrugated layer, which, due to crushing, significantly deteriorates the functional properties of cardboard. In this work, two algorithms for the automatic classification of corrugated board types based on images of deformed corrugated boards using artificial intelligence methods are presented. A prototype of a corrugated board sample image acquisition device was designed and manufactured. It allowed for the collection of an extensive database of images with corrugated board cross-sections of various types. Based on this database, two approaches for processing and classifying them were developed. The first method is based on the identification of the geometric parameters of the corrugated board cross-section using a genetic algorithm. After this stage, a simple feedforward neural network was applied to classify the corrugated board type correctly. In the second approach, the use of a convolutional neural network for corrugated board cross-section classification was proposed. The results obtained using both methods were compared, and the influence of various imperfections in the corrugated board cross-section was examined. [ABSTRACT FROM AUTHOR]

Stock prediction has garnered considerable attention among investors, with a recent focus on the application of machine learning techniques to enhance predictive accuracy. Prior research has established the effectiveness of machine learning in forecasting stock market trends, irrespective of the analytical approach employed, be it technical, fundamental, or sentiment analysis. In the context of fiscal year-end selection, the decision may initially seem straightforward, with December 31 being the apparent choice, as discussed by B. Kamp in 2002. The primary argument for a uniform fiscal year-end centers around comparability. When assessing the financial performance of two firms with differing fiscal year-ends, substantial shifts in the business environment during non-overlapping periods can impede meaningful comparisons. Moreover, when two firms merge, the need to synchronize their annual reporting often results in shorter or longer fiscal years, complicating time series analysis. In the US S&P stock market, misaligned fiscal years lead to variations in report publication dates across different industries and market segments. Since the financial reporting dates of US S&P companies are determined independently by each listed entity, relying solely on these dates for investment decisions may prove less than entirely reliable and impact the accuracy of return prediction models. Hence, our interest lies in the synchronized fiscal year of the TW stock market, leveraging machine learning models for fundamental analysis to forecast returns. We employed four machine learning models: Random Forest (RF), Feedforward Neural Network (FNN), Gated Recurrent Unit (GRU), and Financial Graph Attention Network (FinGAT). We crafted portfolios by selecting stocks with higher predicted returns using these machine learning models. These portfolios outperformed the TW50 index benchmarks in the Taiwan stock market, demonstrating superior returns and portfolio scores. Our study's findings underscore the advantages of using aligned financial ratios for predicting the top 20 high-return stocks in a mid-to-long-term investment context, delivering over 50% excess returns across the four models while maintaining lower risk profiles. Using the top 10 high-return stocks produced over 100% relative returns with an acceptable level of risk, highlighting the effectiveness of employing machine learning techniques based on financial ratios for stock prediction. [ABSTRACT FROM AUTHOR]

Feedforward neural network (FNN) models with strong learning ability and prediction accuracy are crucial for optimization. This paper investigates the effects of the number of training samples and the hidden layers on the accuracy of the FNN model. Meanwhile, under the premise of a high space-fillingness degree, a sample expansion strategy based on the max--min distance criterion is proposed, which ensures that the expanded sample set completely contains the pre-expanded. The strategy can eliminate the interference of sample differences. Furthermore, the multi-objective optimization on the train nose shape is accomplished by minimizing the aerodynamic lift force of the tail car (LT), as well as the aerodynamic drag force of the head (DH) and tail car (DT) using the FNN model. The results indicate that the number of training samples has a greater impact on the prediction error of the FNN model than the number of hidden layers does. Prediction errors decrease as the number of training samples increases and then stabilise, the most accurate one is chosen for nose shape optimization. The DH, DT, and LT all have prediction errors of less than 2%. Compared with the original high-speed train, the DH, DT, and LT of the optimal model are reduced by 5.24%, 3.74%, and 2.61%, respectively. Meanwhile, the correlation analysis reveals that the height of the cab window and the horizontal profile have a significant impact on the aerodynamic characteristics of the high-speed train. [ABSTRACT FROM AUTHOR]

In agricultural and hydrological applications, daily reference evapotranspiration (ET) is a key parameter. Based on one, two, and three-day antecedent meteorological parameters including average air temperature (T), sunshine hours (S), average relative humidity (RH), average wind speed (W), and reference evapotranspiration (ET), this study develops a new model framework for estimating daily ET magnitudes. The Long Short-Term Memory (LSTM) model was combined with the Feedforward Neural Network (FFNN) model in order to develop the hybrid approach, which was used to estimate daily ET values at two stations, Babolsar and Bandar Anzali, Iran, between 1990 and 2022. Additionally, 70% of the data in the present study were used for training purposes and 30% for testing purposes. Based on the statistical metrics, the proposed LSTM-FFNN model was benchmarked against the standalone LSTM model. Results from the comparison at Babolsar station indicated that the LSTM-FFNN model performed better than all scenarios with an error of approximately 1 millimeter per day in scenarios 12, 15, and 16. According to the standalone LSTM model, scenarios 5, 8, 11, 15, and 16 had a 1.57 mm/day error rate, and likewise, for the Bandar Anzali station, the combined LSTM-FFNN model performed the best in scenarios 14 and 15 with the lowest error rates (RMSE=0.96 mm/day), while the standalone LSTM model performed better in scenarios 15 and 16. It was found, however, that the proposed LSTM-FFNN model outperformed the standalone LSTM model at both sites. These results suggest that the proposed LSTM-FFNN model is capable of accurately estimating daily ET magnitudes, which may assist in the optimal management of water resources within agriculture. [ABSTRACT FROM AUTHOR]

Atrial Fibrillation (AFib) and its associated symptoms are significant problems that doctors and several studies have attempted to solve throughout the years. It is diagnosed by analyzing a patient's electrocardiogram (ECG) data. However, continuous efforts have been made to develop an algorithm that detects AFib with optimal efficiency and cost-effectiveness. In this study, a sequential model was used based on feedforward neural network as this is arguably the simplest algorithm developed and requires minimal computing power. The results showed that training the algorithm for 1000 epochs yielded the best results. Further studies showed that using a combination of 10-fold cross-validation and blindfold validation proved an ideal way to determine the model's capabilities in distinguishing patients with AFib from those without. In conclusion, the developed model successfully distinguished between AFib and non-AFib patients with a 96.67% sensitivity, 94.61% specificity, and 95.64% accuracy. [ABSTRACT FROM AUTHOR]

Assessing the training process of artificial neural networks (ANNs) is vital for enhancing their performance and broadening their applicability. This paper employs the Monte Carlo simulation (MCS) technique, integrated with a stopping criterion, to construct the probability distribution of the learning error of an ANN designed for short-term forecasting. The training and validation processes were conducted multiple times, each time considering a unique random starting point, and the subsequent forecasting error was calculated one step ahead. From this, we ascertained the probability of having obtained all the local optima. Our extensive computational analysis involved training a shallow feedforward neural network (FFNN) using wind power and load demand data from the transmission systems of the Netherlands and Germany. Furthermore, the analysis was expanded to include wind speed prediction using a long short-term memory (LSTM) network at a site in Spain. The improvement gained from the FFNN, which has a high probability of being the global optimum, ranges from 0.7% to 8.6%, depending on the forecasting variable. This solution outperforms the persistent model by between 5.5% and 20.3%. For wind speed predictions using an LSTM, the improvement over an average-trained network stands at 9.5%, and is 6% superior to the persistent approach. These outcomes suggest that the advantages of exhaustive search vary based on the problem being analyzed and the type of network in use. The MCS method we implemented, which estimates the probability of identifying all local optima, can act as a foundational step for other techniques like Bayesian model selection, which assumes that the global optimum is encompassed within the available hypotheses.

With the growth in network usage, there has been a corresponding growth in the nefarious exploitation of this technology. A wide array of techniques is now available that can be used to deal with cyberattacks, and one of them is network intrusion detection. Artificial Intelligence (AI) and Machine Learning (ML) techniques have extensively been employed to identify network anomalies. This paper provides an effective technique to evaluate the classification performance of a deep-learning-based Feedforward Neural Network (FFNN) classifier. A small feature vector is used to detect network traffic anomalies in the UNSW-NB15 and NSL-KDD datasets. The results show that a large feature set can have redundant and unuseful features, and it requires high computation power. The proposed technique exploits a small feature vector and achieves better classification accuracy.

Conductivity change in skin layers has been classified by source indicator ok (k=1: Stratum corneum, k=2: Epidermis, k=3: Dermis, k=4: Fat, and k=5: Stratum corneum + Epidermis) trained from feedforward neural network (FNN) in bioelectrical impedance spectroscopy (BIS). In BIS studies, treating the skin as a bulk, limits the differentiation of conductivity changes in individual skin layers, however skin layer classification using FNN shows promise in accurately categorizing skin layers, which is essential for predicting source indicators ok and initiating skin dielectric characteristics diagnosis. The ok is trained by three main conceptual points which are (i) implementing FNN for predicting k in conductivity change, (ii) profiling four impedance inputs αξ consisting of magnitude input α|z|, phase angle input αθ, resistance input αR, and reactance input αx for filtering nonessential input, and (iii) selecting low and high frequency pair (frlh)$$(f_{r}^{lh})$$ by distribution of relaxation time (DRT) for eliminating parasitic noise effect. The training data set of FNN is generated to obtain the αξ ∈ R10×17×10 by 10,200 cases by simulation under configuration and measurement parameters. The trained skin layer classification is validated through experiments with porcine skin under various sodium chloride (NaCl) solutions CNaCl = {15, 20, 25, 30, 35}[mM] in the dermis layer. FNN successfully classified conductivity change in the dermis layer from experiment with accuracy of 90.6% for the bipolar set-up at f6lh=10 &100 [kHz]$$f_{6}^{lh}=10\,\And 100\,{\rm{[kHz]}}$$ and with the same accuracy for the tetrapolar at f8lh=35 &100 [kHz]$$f_{8}^{lh}=35\,\And 100\,{\rm{[kHz]}}$$. The measurement noise and systematic error in the experimental results are minimized by the proposed method using the feature extraction based on αξ at frlh$$f_{r}^{lh}$$.

Background and Objectives: Education is one of the main parts of knowledge and science production in which teachers contribute to the scientific and cultural progress of any country. Inefficiency in education and training can lead to challenges and widespread problems of social, cultural, scientific, political, religious dimensions in society. Therefore, it seems necessary to assess the competence of student teachers in terms of knowledge, skills, and attitudes especially before entering the professional field of teaching. In this research, the competency of student teachers before entering education and training was evaluated using artificial intelligence neural network as a precise computing tool.Methods: In the present study, the research method is applied and quantitative. The statistical population consisted of students of Farhangian University, and the sample included 91 teacher students who were selected via cluster sampling in 2015-2016 in the field of Biology Education of Shahid Beheshti Higher Education Center of Farhangian University. A corpus of 500 data (80% training and 20% test) was formed based on the scores of general, educational, specialized educational, theoretical, research, internship, and total average courses. The findings were assessed using the feedforward neural network method. According to the investigations carried out on the layers and the number of neurons on the data of the algorithm, a three-layer neural network was designed with two hidden layers with a number of 300 neurons and an output layer with a number of 1 neuron.Findings: The results of the examination of professional competence are based on the scores of student teachers and the extraction of new data of the seven dimensions of theoretic- specialization, education- specialization, education- practice, general, internship, research, and total average, which show the highest average with a score of 19.8 in the educational courses and the lowest average with a score of 16.67 was in theory-specialized courses. The analysis of the findings according to the educational data of the graduates and the labeling of experts showed the level of competence as 17.77.Conclusion: These results indicate that curriculum planners should pay more attention to specialized-theory courses because teachers must have the appropriate and sufficient knowledge and scientific level to present scientific materials to students in addition to learning educational lessons. Besides, it is suggested to evaluate the competence coefficient in other studies by using special questionnaires based on students' attitudes toward the teaching profession. On the other hand, the student's handwriting can be examined and studied as another indicator. Also, the neural network model of artificial intelligence should be used to determine the competence of student teachers in other fields of basic sciences and humanities.