Search

This document is a summary of a journal article titled "Artificial Intelligence in Modeling and Simulation." The article discusses the integration of artificial intelligence (AI) into modeling and simulation (M&S) processes. It highlights the various applications of AI in fields such as engineering, physics, social sciences, and biology. The article also provides an overview of 11 selected papers from a special issue on AI and M&S, covering topics such as AI techniques for simulation and optimization, AI in agent-based modeling, AI for data processing and classification models, and artificial neural network (ANN) methods for improved M&S. The papers explore different methodologies and approaches to enhance the efficiency and validity of modeling and simulation using AI. The article concludes by emphasizing the progress and diverse uses of AI in M&S and expressing gratitude to the authors, reviewers, and editorial team involved in the special issue. [Extracted from the article]

Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms. Adversarial training is one of the methods used to defend against the threat of adversarial attacks. It is a training schema that utilizes an alternative objective function to provide model generalization for both adversarial data and clean data. In this systematic review, we focus particularly on adversarial training as a method of improving the defensive capacities and robustness of machine learning models. Specifically, we focus on adversarial sample accessibility through adversarial sample generation methods. The purpose of this systematic review is to survey state-of-the-art adversarial training and robust optimization methods to identify the research gaps within this field of applications. The literature search was conducted using Engineering Village (Engineering Village is an engineering literature search tool, which provides access to 14 engineering literature and patent databases), where we collected 238 related papers. The papers were filtered according to defined inclusion and exclusion criteria, and information was extracted from these papers according to a defined strategy. A total of 78 papers published between 2016 and 2021 were selected. Data were extracted and categorized using a defined strategy, and bar plots and comparison tables were used to show the data distribution. The findings of this review indicate that there are limitations to adversarial training methods and robust optimization. The most common problems are related to data generalization and overfitting. [ABSTRACT FROM AUTHOR]

The research on baggage flow plays a pivotal role in achieving the efficient and intelligent allocation and scheduling of airport service resources, as well as serving as a fundamental element in determining the design, development, and process optimization of airport baggage handling systems. This paper examines baggage checked in by departing passengers at airports. The crrent state of the research on baggage flow demand is first reviewed and analyzed. Then, using examples of objective data, it is concluded that while there is a significant correlation between airport passenger flow and baggage flow, an increase in passenger flow does not necessarily result in a proportional increase in baggage flow. According to the existing research results on the influencing factors of baggage flow sorting and classification, the main influencing factors of baggage flow are divided into two categories: macro-influencing factors and micro-influencing factors. When studying the relationship between the economy and baggage flow, it is recommended to use a comprehensive analysis that includes multiple economic indicators, rather than relying solely on GDP. This paper provides a brief overview of prevalent transportation flow prediction methods, categorizing algorithmic models into three groups: based on mathematical and statistical models, intelligent algorithmic-based models, and combined algorithmic models utilizing artificial neural networks. The structures, strengths, and weaknesses of various transportation flow prediction algorithms are analyzed, as well as their application scenarios. The potential advantages of using artificial neural network-based combined prediction models for baggage flow forecasting are explained. It concludes with an outlook on research regarding the demand for baggage flow. This review may provide further research assistance to scholars in airport management and baggage handling system development. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction is widely applied in prognostic and health management (PHM) of turbofan engines. Although some of the existing deep learning-based models for RUL prediction of turbofan engines have achieved satisfactory results, there are still some challenges. For example, the spatial features and importance differences hidden in the raw monitoring data are not sufficiently addressed or highlighted. In this paper, a novel multi-head self-Attention fully convolutional network (MSA-FCN) is proposed for predicting the RUL of turbofan engines. MSA-FCN combines a fully convolutional network and multi-head structure, focusing on the degradation correlation among various components of the engine and extracting spatially characteristic degradation representations. Furthermore, by introducing dual multi-head self-attention modules, MSA-FCN can capture the differential contributions of sensor data and extracted degradation representations to RUL prediction, emphasizing key data and representations. The experimental results on the C-MAPSS dataset demonstrate that, under various operating conditions and failure modes, MSA-FCN can effectively predict the RUL of turbofan engines. Compared with 11 mainstream deep neural networks, MSA-FCN achieves competitive advantages in terms of both accuracy and timeliness for RUL prediction, delivering more accurate and reliable forecasts. [ABSTRACT FROM AUTHOR]

This document provides an overview of a special issue of the journal "Algorithms" focused on "Deep Neural Networks and Optimization Algorithms." The issue includes seven papers that address theoretical and practical issues in this area. The papers cover a range of topics, including preprocessing pregnancy examination data, sampling in neural network training, neural network boosting for logistic regression, generating artificial EEG data, enhancing QR code source printer identification, gas tracking in chemical industry parks, and developing a graph neural network-based surrogate model. The document concludes by noting the increasing use of AI in cybersecurity and the three main directions of research in this field. The authors of the document express their gratitude to the authors, referees, and the editorial office of Algorithms. [Extracted from the article]

Predicting the price gap between the day-ahead Market (DAM) and the real-time Market (RTM) plays a vital role in the convergence bidding mechanism of Independent System Operators (ISOs) in wholesale electricity markets. This paper presents a model to predict the values of the price gap between the DAM and RTM using statistical machine learning algorithms and deep neural networks. In this paper, we seek to answer these questions: What will be the impact of predicting the DAM and RTM price gap directly on the prediction performance of learning methods? How can exogenous weather data affect the price gap prediction? In this paper, several exogenous features are collected, and the impacts of these features are examined to capture the best relations between the features and the target variable. An ensemble learning algorithm, namely the Random Forest (RF), is used to select the most important features. A Long Short-Term Memory (LSTM) network is used to capture long-term dependencies in predicting direct gap values between the markets stated. Moreover, the advantages of directly predicting the gap price rather than subtracting the price predictions of the DAM and RTM are shown. The presented results are based on the California Independent System Operator (CAISO)'s electricity market data for two years. The results show that direct gap prediction using exogenous weather features decreases the error of learning methods by 46 % . Therefore, the presented method mitigates the prediction error of the price gap between the DAM and RTM. Thus, the convergence bidders can increase their profit, and the ISOs can tune their mechanism accordingly. [ABSTRACT FROM AUTHOR]

Traffic forecasting is an important research topic in intelligent transportation systems and smart cities. This Special Issue aims to collect the state-of-the-art results of applying neural networks for traffic forecasting. A collection of five papers are accepted and included in this Special Issue, covering the latest methods such as Artificial Neural Networks (ANN), Physics-Informed Neural Networks (PINNs), spatio-temporal attention-boosted autoencoder and Deep Reinforcement Learning (DRL). [Extracted from the article]

The increasing growth in knowledge about the functioning of the nervous system of mammals and humans, as well as the significant neuromorphic technology developments in recent decades, has led to the emergence of a large number of brain–computer interfaces and neuroprosthetics for regenerative medicine tasks. Neurotechnologies have traditionally been developed for therapeutic purposes to help or replace motor, sensory or cognitive abilities damaged by injury or disease. They also have significant potential for memory enhancement. However, there are still no fully developed neurotechnologies and neural interfaces capable of restoring or expanding cognitive functions, in particular memory, in mammals or humans. In this regard, the search for new technologies in the field of the restoration of cognitive functions is an urgent task of modern neurophysiology, neurotechnology and artificial intelligence. The hippocampus is an important brain structure connected to memory and information processing in the brain. The aim of this paper is to propose an approach based on deep neural networks for the prediction of hippocampal signals in the CA1 region based on received biological input in the CA3 region. We compare the results of prediction for two widely used deep architectures: reservoir computing (RC) and long short-term memory (LSTM) networks. The proposed study can be viewed as a first step in the complex task of the development of a neurohybrid chip, which allows one to restore memory functions in the damaged rodent hippocampus. [ABSTRACT FROM AUTHOR]

This paper presents various machine learning methods with different text features that are explored and evaluated to determine the authorship of the texts in the example of the Azerbaijani language. We consider techniques like artificial neural network, convolutional neural network, random forest, and support vector machine. These techniques are used with different text features like word length, sentence length, combined word length and sentence length, n-grams, and word frequencies. The models were trained and tested on the works of many famous Azerbaijani writers. The results of computer experiments obtained by utilizing a comparison of various techniques and text features were analyzed. The cases where the usage of text features allowed better results were determined. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have gained prominence in various applications, but remain vulnerable to adversarial attacks that manipulate data to mislead a DNN. This paper aims to challenge the efficacy and transferability of two contemporary defense mechanisms against adversarial attacks: (a) robust training and (b) adversarial training. The former suggests that training a DNN on a data set consisting solely of robust features should produce a model resistant to adversarial attacks. The latter creates an adversarially trained model that learns to minimise an expected training loss over a distribution of bounded adversarial perturbations. We reveal a significant lack in the transferability of these defense mechanisms and provide insight into the potential dangers posed by L ∞ -norm attacks previously underestimated by the research community. Such conclusions are based on extensive experiments involving (1) different model architectures, (2) the use of canonical correlation analysis, (3) visual and quantitative analysis of the neural network's latent representations, (4) an analysis of networks' decision boundaries and (5) the use of equivalence of L 2 and L ∞ perturbation norm theories. [ABSTRACT FROM AUTHOR]

Brain tumors are one of the deadliest types of cancer. Rapid and accurate identification of brain tumors, followed by appropriate surgical intervention or chemotherapy, increases the probability of survival. Accurate determination of brain tumors in MRI scans determines the exact location of surgical intervention or chemotherapy. However, this accurate segmentation of brain tumors, due to their diverse morphologies in MRI scans, poses challenges that require significant expertise and accuracy in image interpretation. Despite significant advances in this field, there are several barriers to proper data collection, particularly in the medical sciences, due to concerns about the confidentiality of patient information. However, research papers for learning systems and proposed networks often rely on standardized datasets because a specific approach is unavailable. This system combines unsupervised learning in the adversarial generative network component with supervised learning in segmentation networks. The system is fully automated and can be applied to tumor segmentation on various datasets, including those with sparse data. In order to improve the learning process, the brain MRI segmentation network is trained using a generative adversarial network to increase the number of images. The U-Net model was employed during the segmentation step to combine the remaining blocks efficiently. Contourlet transform produces the ground truth for each MRI image obtained from the adversarial generator network and the original images in the processing and mask preparation phase. On the part of the adversarial generator network, high-quality images are produced, the results of which are similar to the histogram of the original images. Finally, this system improves the image segmentation performance by combining the remaining blocks with the U-net network. Segmentation is evaluated using brain magnetic resonance images obtained from Istanbul Medipol Hospital. The results show that the proposed method and image segmentation network, which incorporates several criteria, such as the DICE criterion of 0.9434, can be effectively used in any dataset as a fully automatic system for segmenting different brain MRI images. [ABSTRACT FROM AUTHOR]

This paper reviews the application of artificial neural network (ANN) models to time series prediction tasks. We begin by briefly introducing some basic concepts and terms related to time series analysis, and by outlining some of the most popular ANN architectures considered in the literature for time series forecasting purposes: feedforward neural networks, radial basis function networks, recurrent neural networks, and self-organizing maps. We analyze the strengths and weaknesses of these architectures in the context of time series modeling. We then summarize some recent time series ANN modeling applications found in the literature, focusing mainly on the previously outlined architectures. In our opinion, these summarized techniques constitute a representative sample of the research and development efforts made in this field. We aim to provide the general reader with a good perspective on how ANNs have been employed for time series modeling and forecasting tasks. Finally, we comment on possible new research directions in this area. [ABSTRACT FROM AUTHOR]

Traffic breakdown is the transition of traffic flow from an uncongested state to a congested state. During peak hours, when a large number of on-ramp vehicles merge with mainline traffic, it can cause a significant drop in speed and subsequently lead to traffic breakdown. Therefore, ramp meters have been used to regulate the traffic flow from the ramps to maintain stable traffic flow on the mainline. However, existing traffic breakdown prediction models do not consider on-ramp traffic flow. In this paper, an algorithm based on artificial neural networks (ANN) is developed to predict the probability of a traffic breakdown occurrence on freeway segments with merging traffic, considering temporal and spatial correlations of the traffic conditions from the location of interest, the ramp, and the upstream and downstream segments. The feature selection analysis reveals that the traffic condition of the ramps has a significant impact on the occurrence of traffic breakdown on the mainline. Therefore, the traffic flow characteristics of the on-ramp, along with other significant features, are used to build the ANN model. The proposed ANN algorithm can predict the occurrence of traffic breakdowns on freeway segments with merging traffic with an accuracy of 96%. Furthermore, the model has been deployed at a different location, which yields a predictive accuracy of 97%. In traffic operations, the high probability of the occurrence of a traffic breakdown can be used as a trigger for the ramp meters. [ABSTRACT FROM AUTHOR]

The performance of optimization algorithms, and consequently of AI/machine learning solutions, is strongly influenced by the setting of their hyperparameters. Over the last decades, a rich literature has developed proposing methods to automatically determine the parameter setting for a problem of interest, aiming at either robust or instance-specific settings. Robust setting optimization is already a mature area of research, while instance-level setting is still in its infancy, with contributions mainly dealing with algorithm selection. The work reported in this paper belongs to the latter category, exploiting the learning and generalization capabilities of artificial neural networks to adapt a general setting generated by state-of-the-art automatic configurators. Our approach differs significantly from analogous ones in the literature, both because we rely on neural systems to suggest the settings, and because we propose a novel learning scheme in which different outputs are proposed for each input, in order to support generalization from examples. The approach was validated on two different algorithms that optimized instances of two different problems. We used an algorithm that is very sensitive to parameter settings, applied to generalized assignment problem instances, and a robust tabu search that is purportedly little sensitive to its settings, applied to quadratic assignment problem instances. The computational results in both cases attest to the effectiveness of the approach, especially when applied to instances that are structurally very different from those previously encountered. [ABSTRACT FROM AUTHOR]

Maintenance processes are of high importance for industrial plants. They have to be performed regularly and uninterruptedly. To assist maintenance personnel, industrial sensors monitored by distributed control systems observe and collect several machinery parameters in the cloud. Then, machine learning algorithms try to match patterns and classify abnormal behaviors. This paper presents a new deep learning model called stranded-NN. This model uses a set of NN models of variable layer depths depending on the input. This way, the proposed model can classify different types of emergencies occurring in different time intervals; real-time, close-to-real-time, or periodic. The proposed stranded-NN model has been compared against existing fixed-depth MLPs and LSTM networks used by the industry. Experimentation has shown that the stranded-NN model can outperform fixed depth MLPs 15–21% more in terms of accuracy for real-time events and at least 10–14% more for close-to-real-time events. Regarding LSTMs of the same memory depth as the NN strand input, the stranded NN presents similar results in terms of accuracy for a specific number of strands. Nevertheless, the stranded-NN model's ability to maintain multiple trained strands makes it a superior and more flexible classification and prediction solution than its LSTM counterpart, as well as being faster at training and classification. [ABSTRACT FROM AUTHOR]

In this paper, we describe a model for the automatic generation of literary sentences in French. Although there has been much recent effort directed towards automatic text generation in general, the generation of creative, literary sentences that is not restricted to a specific genre, which we approached in this work, is a difficult task that is not commonly treated in the scientific literature. In particular, our present model has not been previously applied to the generation of sentences in the French language. Our model was based on algorithms that we previously used to generate sentences in Spanish and Portuguese and on a new corpus, which we constructed and present here, consisting of literary texts in French, called MegaLitefr. Our automatic text generation algorithm combines language models, shallow parsing, the canned text method, and deep learning artificial neural networks. We also present a manual evaluation protocol that we propose and implemented to assess the quality of the artificial sentences generated by our algorithm, by testing if they fulfil four simple criteria. We obtained encouraging results from the evaluators for most of the desired features of our artificially generated sentences. [ABSTRACT FROM AUTHOR]

The adoption of deep neural networks for profiling side-channel attacks opened new perspectives for leakage detection. Recent publications showed that cryptographic implementations featuring different countermeasures could be broken without feature selection or trace preprocessing. This success comes with a high price: an extensive hyperparameter search to find optimal deep learning models. As deep learning models usually suffer from overfitting due to their high fitting capacity, it is crucial to avoid over-training regimes, which require a correct number of epochs. For that, early stopping is employed as an efficient regularization method that requires a consistent validation metric. Although guessing entropy is a highly informative metric for profiling side-channel attacks, it is time-consuming, especially if computed for all epochs during training, and the number of validation traces is significantly large. This paper shows that guessing entropy can be efficiently computed during training by reducing the number of validation traces without affecting the efficiency of early stopping decisions. Our solution significantly speeds up the process, impacting the performance of the hyperparameter search and overall profiling attack. Our fast guessing entropy calculation is up to 16× faster, resulting in more hyperparameter tuning experiments and allowing security evaluators to find more efficient deep learning models. [ABSTRACT FROM AUTHOR]

Numerical methods based on finite element (FE) have proven their efficiency for many years in the thermomechanical simulation of forming processes. Nevertheless, the application of these methods to new materials requires the identification and implementation of constitutive and flow laws within FE codes, which sometimes pose problems, particularly because of the strongly non-linear character of the behavior of these materials. Computational techniques based on machine learning and artificial neural networks are becoming more and more important in the development of these models and help the FE codes to integrate more complex behavior. In this paper, we present the development, implementation and use of an artificial neural network (ANN) based flow law for a GrC15 alloy under high temperature thermomechanical solicitations. The flow law modeling by ANN shows a significant superiority in terms of model prediction quality compared to classical approaches based on widely used Johnson–Cook or Arrhenius models. Once the ANN parameters have been identified on the base of experiments, the implementation of this flow law in a finite element code shows promising results in terms of solution quality and respect of the material behavior. [ABSTRACT FROM AUTHOR]

It is well known that biomedical imaging analysis plays a crucial role in the healthcare sector and produces a huge quantity of data. These data can be exploited to study diseases and their evolution in a deeper way or to predict their onsets. In particular, image classification represents one of the main problems in the biomedical imaging context. Due to the data complexity, biomedical image classification can be carried out by trainable mathematical models, such as artificial neural networks. When employing a neural network, one of the main challenges is to determine the optimal duration of the training phase to achieve the best performance. This paper introduces a new adaptive early stopping technique to set the optimal training time based on dynamic selection strategies to fix the learning rate and the mini-batch size of the stochastic gradient method exploited as the optimizer. The numerical experiments, carried out on different artificial neural networks for image classification, show that the developed adaptive early stopping procedure leads to the same literature performance while finalizing the training in fewer epochs. The numerical examples have been performed on the CIFAR100 dataset and on two distinct MedMNIST2D datasets which are the large-scale lightweight benchmark for biomedical image classification. [ABSTRACT FROM AUTHOR]

This paper presents and analyzes a programming tool that implements a method for classification and function regression problems. This method builds new features from existing ones with the assistance of a hybrid algorithm that makes use of artificial neural networks and grammatical evolution. The implemented software exploits modern multi-core computing units for faster execution. The method has been applied to a variety of classification and function regression problems, and an extensive comparison with other methods of computational intelligence is made. [ABSTRACT FROM AUTHOR]

Explainability is one of the key factors in Natural Language Processing (NLP) specially for legal documents, medical diagnosis, and clinical text. Attention mechanism has been a popular choice for such explainability recently by estimating the relative importance of input units. Recent research has revealed, however, that such processes tend to misidentify irrelevant input units when explaining them. This is due to the fact that language representation layers are initialized by pre-trained word embedding that is not context-dependent. Such a lack of context-dependent knowledge in the initial layer makes it difficult for the model to concentrate on the important aspects of input. Usually, this does not impact the performance of the model, but the explainability differs from human understanding. Hence, in this paper, we propose an ensemble method to use logic-based information from the Tsetlin Machine to embed it into the initial representation layer in the neural network to enhance the model in terms of explainability. We obtain the global clause score for each word in the vocabulary and feed it into the neural network layer as context-dependent information. Our experiments show that the ensemble method enhances the explainability of the attention layer without sacrificing any performance of the model and even outperforming in some datasets. [ABSTRACT FROM AUTHOR]

Deep learning, with increasingly large datasets and complex neural networks, is widely used in computer vision and natural language processing. A resulting trend is to split and train large-scale neural network models across multiple devices in parallel, known as parallel model training. Existing parallel methods are mainly based on expert design, which is inefficient and requires specialized knowledge. Although automatically implemented parallel methods have been proposed to solve these problems, these methods only consider a single optimization aspect of run time. In this paper, we present Trinity, an adaptive distributed parallel training method based on reinforcement learning, to automate the search and tuning of parallel strategies. We build a multidimensional performance evaluation model and use proximal policy optimization to co-optimize multiple optimization aspects. Our experiment used the CIFAR10 and PTB datasets based on InceptionV3, NMT, NASNet and PNASNet models. Compared with Google's Hierarchical method, Trinity achieves up to 5% reductions in runtime, communication, and memory overhead, and up to a 40% increase in parallel strategy search speeds. [ABSTRACT FROM AUTHOR]

In the paper, the author deals with modeling the stochastic behavior of ordinary patch antennas in terms of the mean and standard deviation of their reflection coefficient |S11| under the geometrical uncertainty associated with their manufacturing process. The Artificial Neural Network is used to model the stochastic reflection coefficient of the antennas. The Polynomial Chaos Expansion and FDTD computations are used to obtain the training and testing data for the Artificial Neural Network. For the first time, the author uses his analytical transformations to reduce the required number of highly time-consuming FDTD simulations for a given set of nominal values of the design parameters of the ordinary patch antenna. An analysis is performed for n257 and n258 frequency bands (24.5–28.7 GHz). The probability distributions of the design parameters are extracted from the measurement results obtained for a series of manufactured patch antenna arrays for three different frequencies in the C, X, and Ka bands. Patch antennas are chosen as the subject of the scientific analysis in this paper because of the popularity of the patch antennas in the scientific literature concerning antennas, as well as because of a simple form of these antennas that is reflected in the time required for computation of training and testing data for the Artificial Neural Network. [ABSTRACT FROM AUTHOR]

Aiming at the pitting fault of deep groove ball bearing during service, this paper uses the vibration signal of five different states of deep groove ball bearing and extracts the relevant features, then uses a neural network to model the degradation for identifying and classifying the fault type. By comparing the effects of training samples with different capacities through performance indexes such as the accuracy and convergence speed, it is proven that an increase in the sample size can improve the performance of the model. Based on the polynomial fitting principle and Pearson correlation coefficient, fusion features based on the skewness index are proposed, and the performance improvement of the model after incorporating the fusion features is also validated. A comparison of the performance of the support vector machine (SVM) model and the neural network model on this dataset is given. The research shows that neural networks have more potential for complex and high-volume datasets [ABSTRACT FROM AUTHOR]

Traffic sign detection is an important task in traffic sign recognition systems. Chinese traffic signs have their unique features compared with traffic signs of other countries. Convolutional neural networks (CNNs) have achieved a breakthrough in computer vision tasks and made great success in traffic sign classification. In this paper, we present a Chinese traffic sign detection algorithm based on a deep convolutional network. To achieve real-time Chinese traffic sign detection, we propose an end-to-end convolutional network inspired by YOLOv2. In view of the characteristics of traffic signs, we take the multiple 1 × 1 convolutional layers in intermediate layers of the network and decrease the convolutional layers in top layers to reduce the computational complexity. For effectively detecting small traffic signs, we divide the input images into dense grids to obtain finer feature maps. Moreover, we expand the Chinese traffic sign dataset (CTSD) and improve the marker information, which is available online. All experimental results evaluated according to our expanded CTSD and German Traffic Sign Detection Benchmark (GTSDB) indicate that the proposed method is the faster and more robust. The fastest detection speed achieved was 0.017 s per image. [ABSTRACT FROM AUTHOR]

Network analysis aids management in reducing overall expenditures and maintenance workload. Social media platforms frequently use neural networks to suggest material that corresponds with user preferences. Machine learning is one of many methods for social network analysis. Machine learning algorithms operate on a collection of observable features that are taken from user data. Machine learning and neural network-based systems represent a topic of study that spans several fields. Computers can now recognize the emotions behind particular content uploaded by users to social media networks thanks to machine learning. This study examines research on machine learning and neural networks, with an emphasis on social analysis in the context of the current literature. [ABSTRACT FROM AUTHOR]

This topic is strictly related to that addressed in the fifth article [[5]] of this Special Issue, wherein, to create a process that is easier to operate, a supermarket refrigeration system's integrated design is adopted. The article [[5]] has two goals, that is, to demonstrate the benefit of considering integrated design and adapting the Surface Response Method (SRM) to optimize problems without experimental variability, such as that used in the computational campaign proposed by the authors. The first article [[1]] of this Special Issue investigates some of the drawbacks that might have prevented this performance measure from being adopted, wherein the quantitative Knowles and Corne measure is analyzed based on attainment surfaces. [Extracted from the article]

Skin cancer is a prevalent and perilous form of cancer and presents significant diagnostic challenges due to its high costs, dependence on medical experts, and time-consuming procedures. The existing diagnostic process is inefficient and expensive, requiring extensive medical expertise and time. To tackle these issues, researchers have explored the application of artificial intelligence (AI) tools, particularly machine learning techniques such as shallow and deep learning, to enhance the diagnostic process for skin cancer. These tools employ computer algorithms and deep neural networks to identify and categorize skin cancer. However, accurately distinguishing between skin cancer and benign tumors remains challenging, necessitating the extraction of pertinent features from image data for classification. This study addresses these challenges by employing Principal Component Analysis (PCA), a dimensionality-reduction approach, to extract relevant features from skin images. Additionally, accurately classifying skin images into malignant and benign categories presents another obstacle. To improve accuracy, the AdaBoost algorithm is utilized, which amalgamates weak classification models into a robust classifier with high accuracy. This research introduces a novel approach to skin cancer diagnosis by integrating Principal Component Analysis (PCA), AdaBoost, and EfficientNet B0, leveraging artificial intelligence (AI) tools. The novelty lies in the combination of these techniques to develop a robust and accurate system for skin cancer classification. The advantage of this approach is its ability to significantly reduce costs, minimize reliance on medical experts, and expedite the diagnostic process. The developed model achieved an accuracy of 93.00% using the DermIS dataset and demonstrated excellent precision, recall, and F1-score values, confirming its ability to correctly classify skin lesions as malignant or benign. Additionally, the model achieved an accuracy of 91.00% using the ISIC dataset, which is widely recognized for its comprehensive collection of annotated dermoscopic images, providing a robust foundation for training and validation. These advancements have the potential to significantly enhance the efficiency and accuracy of skin cancer diagnosis and classification. Ultimately, the integration of AI tools and techniques in skin cancer diagnosis can lead to cost reduction and improved patient outcomes, benefiting both patients and healthcare providers. [ABSTRACT FROM AUTHOR]

Color distortion in an image presents a challenge for machine learning classification and regression when the input data consists of pictures. As a result, a new algorithm for color standardization of photos is proposed, forming the foundation for a deep neural network regression model. This approach utilizes a self-designed color template that was developed based on an initial series of studies and digital imaging. Using the equalized histogram of the R, G, B channels of the digital template and its photo, a color mapping strategy was computed. By applying this approach, the histograms were adjusted and the colors of photos taken with a smartphone were standardized. The proposed algorithm was developed for a series of images where the entire surface roughly maintained a uniform color and the differences in color between the photographs of individual objects were minor. This optimized approach was validated in the colorimetric determination procedure of vitamin C. The dataset for the deep neural network in the regression variant was formed from photos of samples under two separate lighting conditions. For the vitamin C concentration range from 0 to 87.72 µg·mL−1, the RMSE for the test set ranged between 0.75 and 1.95 µg·mL−1, in comparison to the non-standardized variant, where this indicator was at the level of 1.48–2.29 µg·mL−1. The consistency of the predicted concentration results with actual data, expressed as R2, ranged between 0.9956 and 0.9999 for each of the standardized variants. This approach allows for the removal of light reflections on the shiny surfaces of solutions, which is a common problem in liquid samples. This color-matching algorithm has universal character, and its scope of application is not limited. [ABSTRACT FROM AUTHOR]

Deep learning is crucial in marine logistics and container crane error detection, diagnosis, and prediction. A novel deep learning technique using Long Short-Term Memory (LSTM) detected and anticipated errors in a system with imbalanced data. The LSTM model was trained on real operational error data from container cranes. The custom algorithm employs the Synthetic Minority Oversampling TEchnique (SMOTE) to balance the imbalanced data for operational data errors (i.e., too few minority class samples). Python was used to program. Pearson, Spearman, and Kendall correlation matrices and covariance matrices are presented. The model's training and validation loss is shown, and the remaining data are predicted. The test set (30% of actual data) and forecasted data had RMSEs of 0.065. A heatmap of a confusion matrix was created using Matplotlib and Seaborn. Additionally, the error outputs for the time series for the next n seconds were projected, with the n seconds input by the user. Accuracy was 0.996, precision was 1.00, recall was 0.500, and f1 score was 0.667, according to the evaluation criteria that were produced. Experiments demonstrated that the technique is capable of identifying critical elements. Thus, future attempts will improve the model's structure to forecast industrial big data errors. However, the advantage is that it can handle imbalanced data, which is usually what most industries have. With additional data, the model can be further improved. [ABSTRACT FROM AUTHOR]

Public authorities and private companies have used video cameras as part of surveillance systems, and one of their objectives is the rapid detection of physically violent actions. This task is usually performed by human visual inspection, which is labor-intensive. For this reason, different deep learning models have been implemented to remove the human eye from this task, yielding positive results. One of the main problems in detecting physical violence in videos is the variety of scenarios that can exist, which leads to different models being trained on datasets, leading them to detect physical violence in only one or a few types of videos. In this work, we present an approach for physical violence detection on images obtained from video based on threshold active learning, that increases the classifier's robustness in environments where it was not trained. The proposed approach consists of two stages: In the first stage, pre-trained neural network models are trained on initial datasets, and we use a threshold (μ) to identify those images that the classifier considers ambiguous or hard to classify. Then, they are included in the training dataset, and the model is retrained to improve its classification performance. In the second stage, we test the model with video images from other environments, and we again employ (μ) to detect ambiguous images that a human expert analyzes to determine the real class or delete the ambiguity on them. After that, the ambiguous images are added to the original training set and the classifier is retrained; this process is repeated while ambiguous images exist. The model is a hybrid neural network that uses transfer learning and a threshold μ to detect physical violence on images obtained from video files successfully. In this active learning process, the classifier can detect physical violence in different environments, where the main contribution is the method used to obtain a threshold μ (which is based on the neural network output) that allows human experts to contribute to the classification process to obtain more robust neural networks and high-quality datasets. The experimental results show the proposed approach's effectiveness in detecting physical violence, where it is trained using an initial dataset, and new images are added to improve its robustness in diverse environments. [ABSTRACT FROM AUTHOR]

This study briefly describes the concept of guided training of deep neural networks (DNNs) to learn physically reasonable solutions. The proposed method does not need the gradients of the physical equations, although the conventional physics-informed models need the gradients. DNNs are widely used to predict phenomena in physics and mechanics. One of the issues with DNNs is that their output does not always satisfy physical equations. One approach to consider with physical equations is adding a residual of the equations into the loss function; this is called physics-informed neural network (PINN). One feature of PINNs is that the physical equations and corresponding residuals must be implemented as part of a neural network model. In addition, the residual does not always converge to a small value. The proposed model is a physics-guided generative adversarial network (PG-GAN) that uses a GAN architecture, in which physical equations are used to judge whether the neural network's output is consistent with physics. The proposed method was applied to a simple problem to assess its potential usability. [ABSTRACT FROM AUTHOR]

This paper studies a novel intelligent motion control algorithm for Autonomous Underwater Vehicles (AUV) and develops a virtual reality system for a new interactive experimental platform. The paper designs a robust neuro-fuzzy controller to tackle system uncertainties and external disturbances. Fuzzy control can solve the uncertainty problem of control systems. The neural network model self-tunes the controller parameters to improve the anti-interference ability. The designed control algorithm is verified using a MATLAB implementation and a virtual reality system. The virtual reality system developed in this paper can be used to debug the control algorithm, simulate the marine environment, and establish an ocean current interference model. The paper uses the MATLAB engine to realize the data communication between the MATLAB and the AUV virtual reality system. This allows the output order of the controller in MATLAB to drive the AUV in a virtual simulation system to simulate the 3D space motion. [ABSTRACT FROM AUTHOR]

Deep learning uses artificial neural networks to recognize patterns and learn from them to make decisions. Deep learning is a type of machine learning that uses artificial neural networks to mimic the human brain. It uses machine learning methods such as supervised, semi-supervised, or unsupervised learning strategies to learn automatically in deep architectures and has gained much popularity due to its superior ability to learn from huge amounts of data. It was found that deep learning approaches can be used for big data analysis successfully. Applications include virtual assistants such as Alexa and Siri, facial recognition, personalization, natural language processing, autonomous cars, automatic handwriting generation, news aggregation, the colorization of black and white images, the addition of sound to silent films, pixel restoration, and deep dreaming. As a review, this paper aims to categorically cover several widely used deep learning algorithms along with their architectures and their practical applications: backpropagation, autoencoders, variational autoencoders, restricted Boltzmann machines, deep belief networks, convolutional neural networks, recurrent neural networks, generative adversarial networks, capsnets, transformer, embeddings from language models, bidirectional encoder representations from transformers, and attention in natural language processing. In addition, challenges of deep learning are also presented in this paper, such as AutoML-Zero, neural architecture search, evolutionary deep learning, and others. The pros and cons of these algorithms and their applications in healthcare are explored, alongside the future direction of this domain. This paper presents a review and a checkpoint to systemize the popular algorithms and to encourage further innovation regarding their applications. For new researchers in the field of deep learning, this review can help them to obtain many details about the advantages, disadvantages, applications, and working mechanisms of a number of deep learning algorithms. In addition, we introduce detailed information on how to apply several deep learning algorithms in healthcare, such as in relation to the COVID-19 pandemic. By presenting many challenges of deep learning in one section, we hope to increase awareness of these challenges, and how they can be dealt with. This could also motivate researchers to find solutions for these challenges. [ABSTRACT FROM AUTHOR]

Recently, inspired by the power of deep learning, convolution neural networks can produce fantastic images at the pixel level. However, a significant limiting factor for previous approaches is that they focus on some simple datasets such as faces and bedrooms. In this paper, we propose a multiscale deep neural network to transform sketches into Chinese paintings. To synthesize more realistic imagery, we train the generative network by using both L1 loss and adversarial loss. Additionally, users can control the process of the synthesis since the generative network is feed-forward. This network can also be treated as neural style transfer by adding an edge detector. Furthermore, additional experiments on image colorization and image super-resolution demonstrate the universality of our proposed approach. [ABSTRACT FROM AUTHOR]

Embedding social network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification, node clustering, link prediction and network visualization. However, the information contained in these vector embeddings remains abstract and hard to interpret. Methods for inspecting embeddings usually rely on visualization methods, which do not work on a larger scale and do not give concrete interpretations of vector embeddings in terms of preserved network properties (e.g., centrality or betweenness measures). In this paper, we study and investigate network properties preserved by recent random walk-based embedding procedures like node2vec, DeepWalk or LINE. We propose a method that applies learning to rank in order to relate embeddings to network centralities. We evaluate our approach with extensive experiments on real-world and artificial social networks. Experiments show that each embedding method learns different network properties. In addition, we show that our graph embeddings in combination with neural networks provide a computationally efficient way to approximate the Closeness Centrality measure in social networks. [ABSTRACT FROM AUTHOR]

First-order algorithms have long dominated the training of deep neural networks, excelling in tasks like image classification and natural language processing. Now there is a compelling opportunity to explore alternatives that could outperform current state-of-the-art results. From the estimation theory, the Extended Kalman Filter (EKF) arose as a viable alternative and has shown advantages over backpropagation methods. Current computational advances offer the opportunity to review algorithms derived from the EKF, almost excluded from the training of convolutional neural networks. This article revisits an approach of the EKF with decoupling and it brings the Fully Decoupled Extended Kalman Filter (FDEKF) for training convolutional neural networks in image classification tasks. The FDEKF is a second-order algorithm with some advantages over the first-order algorithms, so it can lead to faster convergence and higher accuracy, due to a higher probability of finding the global optimum. In this research, experiments are conducted on well-known datasets that include Fashion, Sports, and Handwritten Digits images. The FDEKF shows faster convergence compared to other algorithms such as the popular Adam optimizer, the sKAdam algorithm, and the reduced extended Kalman filter. Finally, motivated by the finding of the highest accuracy of FDEKF with images of natural scenes, we show its effectiveness in another experiment focused on outdoor terrain recognition. [ABSTRACT FROM AUTHOR]

The adequacy and efficacy of simple and hybrid machine learning and Computational Intelligence algorithms were evaluated for the classification of potential prostate cancer patients in two distinct categories, the high- and the low-risk group for PCa. The evaluation is based on randomly generated surrogate data for the biomarker PSA, considering that reported epidemiological data indicated that PSA values follow a lognormal distribution. In addition, four more biomarkers were considered, namely, PSAD (PSA density), PSAV (PSA velocity), PSA ratio, and Digital Rectal Exam evaluation (DRE), as well as patient age. Seven simple classification algorithms, namely, Decision Trees, Random Forests, Support Vector Machines, K-Nearest Neighbors, Logistic Regression, Naïve Bayes, and Artificial Neural Networks, were evaluated in terms of classification accuracy. In addition, three hybrid algorithms were developed and introduced in the present work, where Genetic Algorithms were utilized as a metaheuristic searching technique in order to optimize the training set, in terms of minimizing its size, to give optimal classification accuracy for the simple algorithms including K-Nearest Neighbors, a K-means clustering algorithm, and a genetic clustering algorithm. Results indicated that prostate cancer cases can be classified with high accuracy, even by the use of small training sets, with sizes that could be even smaller than 30% of the dataset. Numerous computer experiments indicated that the proposed training set minimization does not cause overfitting of the hybrid algorithms. Finally, an easy-to-use Graphical User Interface (GUI) was implemented, incorporating all the evaluated algorithms and the decision-making procedure. [ABSTRACT FROM AUTHOR]

The accurate classification of brain tumors is an important step for early intervention. Artificial intelligence (AI)-based diagnostic systems have been utilized in recent years to help automate the process and provide more objective and faster diagnosis. This work introduces an enhanced AI-based architecture for improved brain tumor classification. We introduce a hybrid architecture that integrates vision transformer (ViT) and deep neural networks to create an ensemble classifier, resulting in a more robust brain tumor classification framework. The analysis pipeline begins with preprocessing and data normalization, followed by extracting three types of MRI-derived information-rich features. The latter included higher-order texture and structural feature sets to harness the spatial interactions between image intensities, which were derived using Haralick features and local binary patterns. Additionally, local deeper features of the brain images are extracted using an optimized convolutional neural networks (CNN) architecture. Finally, ViT-derived features are also integrated due to their ability to handle dependencies across larger distances while being less sensitive to data augmentation. The extracted features are then weighted, fused, and fed to a machine learning classifier for the final classification of brain MRIs. The proposed weighted ensemble architecture has been evaluated on publicly available and locally collected brain MRIs of four classes using various metrics. The results showed that leveraging the benefits of individual components of the proposed architecture leads to improved performance using ablation studies. [ABSTRACT FROM AUTHOR]

Cyclic air braking is a key element for ensuring safe train operation when running on a long and steep downhill railway section. In reality, the cyclic braking performance of a train is affected by its operating environment, speed and air-refilling time. Existing optimization algorithms have the problem of low learning efficiency. To solve this problem, an intelligent control method based on the deep Q-network (DQN) algorithm for heavy-haul trains running on long and steep downhill railway sections is proposed. Firstly, the environment of heavy-haul train operation is designed by considering the line characteristics, speed limits and constraints of the train pipe's air-refilling time. Secondly, the control process of heavy-haul trains running on long and steep downhill sections is described as the reinforcement learning (RL) of a Markov decision process. By designing the critical elements of RL, a cyclic braking strategy for heavy-haul trains is established based on the reinforcement learning algorithm. Thirdly, the deep neural network and Q-learning are combined to design a neural network for approximating the action value function so that the algorithm can achieve the optimal action value function faster. Finally, simulation experiments are conducted on the actual track data pertaining to the Shuozhou–Huanghua line in China to compare the performance of the Q-learning algorithm against the DQN algorithm. Our findings revealed that the DQN-based intelligent control strategy decreased the air braking distance by 2.1% and enhanced the overall average speed by more than 7%. These experiments unequivocally demonstrate the efficacy and superiority of the DQN-based intelligent control strategy. [ABSTRACT FROM AUTHOR]

Despite medical advancements in recent years, cardiovascular diseases (CVDs) remain a major factor in rising mortality rates, challenging predictions despite extensive expertise. The healthcare sector is poised to benefit significantly from harnessing massive data and the insights we can derive from it, underscoring the importance of integrating machine learning (ML) to improve CVD prevention strategies. In this study, we addressed the major issue of class imbalance in the Behavioral Risk Factor Surveillance System (BRFSS) 2021 heart disease dataset, including personal lifestyle factors, by exploring several resampling techniques, such as the Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), SMOTE-Tomek, and SMOTE-Edited Nearest Neighbor (SMOTE-ENN). Subsequently, we trained, tested, and evaluated multiple classifiers, including logistic regression (LR), decision trees (DTs), random forest (RF), gradient boosting (GB), XGBoost (XGB), CatBoost, and artificial neural networks (ANNs), comparing their performance with a primary focus on maximizing sensitivity for CVD risk prediction. Based on our findings, the hybrid resampling techniques outperformed the alternative sampling techniques, and our proposed implementation includes SMOTE-ENN coupled with CatBoost optimized through Optuna, achieving a remarkable 88% rate for recall and 82% for the area under the receiver operating characteristic (ROC) curve (AUC) metric. [ABSTRACT FROM AUTHOR]

We develop decision support and automation for the task of ultrasonic non-destructive evaluation data analysis. First, we develop a probabilistic model for the task and then implement the model as a series of neural networks based on Conditional Score-Based Diffusion and Denoising Diffusion Probabilistic Model architectures. We use the neural networks to generate estimates for peak amplitude response time of flight and perform a series of tests probing their behavior, capacity, and characteristics in terms of the probabilistic model. We train the neural networks on a series of datasets constructed from ultrasonic non-destructive evaluation data acquired during an inspection at a nuclear power generation facility. We modulate the partition classifying nominal and anomalous data in the dataset and observe that the probabilistic model predicts trends in neural network model performance, thereby demonstrating a principled basis for explainability. We improve on previous related work as our methods are self-supervised and require no data annotation or pre-processing, and we train on a per-dataset basis, meaning we do not rely on out-of-distribution generalization. The capacity of the probabilistic model to predict trends in neural network performance, as well as the quality of the estimates sampled from the neural networks, support the development of a technical justification for usage of the method in safety-critical contexts such as nuclear applications. The method may provide a basis or template for extension into similar non-destructive evaluation tasks in other industrial contexts. [ABSTRACT FROM AUTHOR]

Background. Brain–machine interfaces (BMIs) offer users the ability to directly communicate with digital devices through neural signals decoded with machine learning (ML)-based algorithms. Spiking Neural Networks (SNNs) are a type of Artificial Neural Network (ANN) that operate on neural spikes instead of continuous scalar outputs. Compared to traditional ANNs, SNNs perform fewer computations, use less memory, and mimic biological neurons better. However, SNNs only retain information for short durations, limiting their ability to capture long-term dependencies in time-variant data. Here, we propose a novel spike-weighted SNN with spiking long short-term memory (swSNN-SLSTM) for a regression problem. Spike-weighting captures neuronal firing rate instead of membrane potential, and the SLSTM layer captures long-term dependencies. Methods. We compared the performance of various ML algorithms during decoding directional movements, using a dataset of microelectrode recordings from a macaque during a directional joystick task, and also an open-source dataset. We thus quantified how swSNN-SLSTM performed compared to existing ML models: an unscented Kalman filter, LSTM-based ANN, and membrane-based SNN techniques. Result. The proposed swSNN-SLSTM outperforms both the unscented Kalman filter, the LSTM-based ANN, and the membrane based SNN technique. This shows that incorporating SLSTM can better capture long-term dependencies within neural data. Also, our proposed swSNN-SLSTM algorithm shows promise in reducing power consumption and lowering heat dissipation in implanted BMIs. [ABSTRACT FROM AUTHOR]

Zero-crossing point detection is necessary to establish a consistent performance in various power system applications, such as grid synchronization, power conversion and switch-gear protection. In this paper, zero-crossing points of a sinusoidal signal are detected using deep neural networks. In order to train and evaluate the deep neural network model, new datasets for sinusoidal signals having noise levels from 5% to 50% and harmonic distortion from 10% to 50% are developed. This complete study is implemented in Google Colab using deep learning framework Keras. Results shows that the proposed deep learning model is able to detect zero-crossing points in a distorted sinusoidal signal with good accuracy. [ABSTRACT FROM AUTHOR]

The main goal of this paper is to improve the performance of the Fireworks Algorithm (FWA). To improve the performance of the FWA we propose three modifications: the first modification is to change the stopping criteria, this is to say, previously, the number of function evaluations was utilized as a stopping criteria, and we decided to change this to specify a particular number of iterations; the second and third modifications consist on introducing a dispersion metric (dispersion percent), and both modifications were made with the goal of achieving dynamic adaptation of the two parameters in the algorithm. The parameters that were controlled are the explosion amplitude and the number of sparks, and it is worth mentioning that the control of these parameters is based on a fuzzy logic approach. To measure the impact of these modifications, we perform experiments with 14 benchmark functions and a comparative study shows the advantage of the proposed approach. We decided to call the proposed algorithms Iterative Fireworks Algorithm (IFWA) and two variants of the Dispersion Percent Iterative Fuzzy Fireworks Algorithm (DPIFWA-I and DPIFWA-II, respectively). [ABSTRACT FROM AUTHOR]

The literature contains several reports evaluating the abilities of deep neural networks in text transfer learning. To our knowledge, however, there have been few efforts to fully realize the potential of deep neural networks in cross-domain product review sentiment classification. In this paper, we propose a two-layer convolutional neural network (CNN) for cross-domain product review sentiment classification (LM-CNN-LB). Transfer learning research into product review sentiment classification based on deep neural networks has been limited by the lack of a large-scale corpus; we sought to remedy this problem using a large-scale auxiliary cross-domain dataset collected from Amazon product reviews. Our proposed framework exhibits the dramatic transferability of deep neural networks for cross-domain product review sentiment classification and achieves state-of-the-art performance. The framework also outperforms complex engineered features used with a non-deep neural network method. The experiments demonstrate that introducing large-scale data from similar domains is an effective way to resolve the lack of training data. The LM-CNN-LB trained on the multi-source related domain dataset outperformed the one trained on a single similar domain. [ABSTRACT FROM AUTHOR]

This paper presents a novel diagonal recurrent neural network hybrid controller based on the shared memory of real-time database structure. The controller uses Data Engine (DE) technology, through the establishment of a unified and standardized software architecture and real-time database in different control stations, effectively solves many problems caused by technical standard, communication protocol, and programming language in actual industrial application: the advanced control algorithm and control system co-debugging difficulties, algorithm implementation and update inefficiency, and high development and operation and maintenance costs effectively fill the current technical gap. More importantly, the control algorithm development uses a unified visual graphics configuration programming environment, effectively solving the problem of integrated control of heterogeneous devices; and has the advantages of intuitive configuration and transparent data processing process, reducing the difficulty of the advanced control algorithms debugging in engineering applications. In this paper, the application of a neural network hybrid controller based on DE in motor speed measurement and control system shows that the system has excellent control characteristics and anti-disturbance ability, and provides an integrated method for neural network control algorithm in a practical industrial control system, which is the major contribution of this article. [ABSTRACT FROM AUTHOR]

The Delta robot is an over-actuated parallel robot with highly nonlinear kinematics and dynamics. Designing the control for a Delta robot to carry out various operations is a challenging task. Various advanced control algorithms, such as adaptive control, sliding mode control, and model predictive control, have been investigated for trajectory tracking of the Delta robot. However, these control algorithms require a reliable input–output model of the Delta robot. To address this issue, we have created a control-affine neural network model of the Delta robot with stepper motors. This is a completely data-driven model intended for control design consideration and is not derivable from Newton's law or Lagrange's equation. The neural networks are trained with randomly sampled data in a sufficiently large workspace. The sliding mode control for trajectory tracking is then designed with the help of the neural network model. Extensive numerical results are obtained to show that the neural network model together with the sliding mode control exhibits outstanding performance, achieving a trajectory tracking error below 5 cm on average for the Delta robot. Future work will include experimental validation of the proposed neural network input–output model for control design for the Delta robot. Furthermore, transfer learnings can be conducted to further refine the neural network input–output model and the sliding mode control when new experimental data become available. [ABSTRACT FROM AUTHOR]

The Recurrent Neural Networks (RNNs) are an essential class of supervised learning algorithms. Complex tasks like speech recognition, machine translation, sentiment classification, weather prediction, etc., are now performed by well-trained RNNs. Local or cloud-based GPU machines are used to train them. However, inference is now shifting to miniature, mobile, IoT devices and even micro-controllers. Due to their colossal memory and computing requirements, mapping RNNs directly onto resource-constrained platforms is arcane and challenging. The efficacy of edge-intelligent RNNs (EI-RNNs) must satisfy both performance and memory-fitting requirements at the same time without compromising one for the other. This study's aim was to provide an empirical evaluation and optimization of historic as well as recent RNN architectures for high-performance and low-memory footprint goals. We focused on Human Activity Recognition (HAR) tasks based on wearable sensor data for embedded healthcare applications. We evaluated and optimized six different recurrent units, namely Vanilla RNNs, Long Short-Term Memory (LSTM) units, Gated Recurrent Units (GRUs), Fast Gated Recurrent Neural Networks (FGRNNs), Fast Recurrent Neural Networks (FRNNs), and Unitary Gated Recurrent Neural Networks (UGRNNs) on eight publicly available time-series HAR datasets. We used the hold-out and cross-validation protocols for training the RNNs. We used low-rank parameterization, iterative hard thresholding, and spare retraining compression for RNNs. We found that efficient training (i.e., dataset handling and preprocessing procedures, hyperparameter tuning, and so on, and suitable compression methods (like low-rank parameterization and iterative pruning) are critical in optimizing RNNs for performance and memory efficiency. We implemented the inference of the optimized models on Raspberry Pi. [ABSTRACT FROM AUTHOR]

Background: The development and application of machine learning (ML) methods have become so fast that almost nobody can follow their developments in every detail. It is no wonder that numerous errors and inconsistencies in their usage have also spread with a similar speed independently from the tasks: regression and classification. This work summarizes frequent errors committed by certain authors with the aim of helping scientists to avoid them. Methods: The principle of parsimony governs the train of thought. Fair method comparison can be completed with multicriteria decision-making techniques, preferably by the sum of ranking differences (SRD). Its coupling with analysis of variance (ANOVA) decomposes the effects of several factors. Earlier findings are summarized in a review-like manner: the abuse of the correlation coefficient and proper practices for model discrimination are also outlined. Results: Using an illustrative example, the correct practice and the methodology are summarized as guidelines for model discrimination, and for minimizing the prediction errors. The following factors are all prerequisites for successful modeling: proper data preprocessing, statistical tests, suitable performance parameters, appropriate degrees of freedom, fair comparison of models, and outlier detection, just to name a few. A checklist is provided in a tutorial manner on how to present ML modeling properly. The advocated practices are reviewed shortly in the discussion. Conclusions: Many of the errors can easily be filtered out with careful reviewing. Every authors' responsibility is to adhere to the rules of modeling and validation. A representative sampling of recent literature outlines correct practices and emphasizes that no error-free publication exists. [ABSTRACT FROM AUTHOR]