Search

With the development of computer technology, automatic test paper generation systems have gradually become an effective tool for detecting and maintaining national machine security and protecting the rights and interests of workers. This article achieved multi-level oral scores for different types of questions through online scoring using artificial neural networks in recent years. Based on its specific situation and evaluation index requirements, an analysis module that is reasonable, efficient, and in line with the hierarchical structure and module requirements of national conditions has been designed to complete the research on automatic test paper generation technology, in order to help better manage and allocate human resources and improve production efficiency. Afterwards, this article conducted functional testing on the technical module. The test results showed that the scalability of the system was over 82%. [ABSTRACT FROM AUTHOR]

To enhance solution accuracy and training efficiency in neural network approximation to partial differential equations, partitioned neural networks can be used as a solution surrogate instead of a single large and deep neural network defined on the whole problem domain. In such a partitioned neural network approach, suitable interface conditions or subdomain boundary conditions are combined to obtain a convergent approximate solution. However, there has been no rigorous study on the convergence and parallel computing enhancement on the partitioned neural network approach. In this paper, iterative algorithms are proposed to enhance parallel computation performance in the partitioned neural network approximation. Our iterative algorithms are based on classical additive Schwarz domain decomposition methods. For the proposed iterative algorithms, their convergence is analyzed under an error assumption on the local and coarse neural network solutions. Numerical results are also included to show the performance of the proposed iterative algorithms. [ABSTRACT FROM AUTHOR]

Neural network ensembling is a common and robust way to increase model efficiency. In this paper, we propose a new neural network ensemble algorithm based on Audibert's empirical star algorithm. We provide optimal theoretical minimax bound on the excess squared risk. Additionally, we empirically study this algorithm on regression and classification tasks and compare it to most popular ensembling methods. [ABSTRACT FROM AUTHOR]

• A novel water transparency calculation algorithm is introduced, employing deep neural network and image processing technology. This algorithm obviates the need for a water gauge, allowing the calculation of water transparency solely through the analysisof Secchi disk videos. Notably, it demonstrates heightened detection efficiency and success rates. • An enhanced Siamese tracker, termed SiamDCFF (Siamese tracker based on dual correlation feature fusion), is proposed for Secchi disk recognition. Distinguishing features of SiamDCFF include a dual correlation module and a feature fusion module. On the Secchi disk dataset, SiamDCFF achieves the highest success rate, outperforming other methods detailed in this paper. • The simplified 3D-ResNet [41] is leveraged to assess the state of the Secchi disk, transforming the critical position determination problem into an optimization challenge. The objective function involves maximizing the number of visible and invisible Secchi disk images on both sides of the critical position. This method facilitates adaptive critical position determination. • A novel Gated Recurrent Unit based on auto-regression (ARGRU) is proposed, taking into account the motion characteristics of the Secchi disk. ARGRU achieves a higher success detection rate for water transparency compared to the water gauge recognition method. Notably, ARGRU outperforms RNN [42], GRU, and LSTM [43] on the dataset presented in this paper. Water transparency is traditionally assessed through visual inspection using a lowered Secchi disk (SD) into the water, with the disappearance depth of the SD recorded as the measure of transparency. However, manual and visually-dependent frequency measurements of the SD render this process labor-intensive and time-consuming. This paper presents a comprehensive machine-vision-based algorithm designed for the automatic computation of water transparency using Secchi disk videos. The algorithm leverages multiple deep neural networks, including an enhanced Siamese tracking model, a 3D-ResNet, and an improved GRU network. Trained models directly identify the SD in the video, calculating water transparency by processing pixel information. Experimental results demonstrate the algorithm's efficacy in estimating water transparency across diverse natural environments, achieving commendable accuracy (MAE = 3.6 cm MSE = 21.5 cm RMSE = 4.6 cm), rapid processing speed (average 6.87 s), and robust stability. In comparison with the former water-gauge-based algorithm, our proposed algorithm exhibits heightened efficiency and a superior detection success rate. [ABSTRACT FROM AUTHOR]

This paper presents a novel natural gradient and Hessian-free (NGHF) optimisation framework for neural network training that can operate efficiently in a distributed manner. It relies on the linear conjugate gradient (CG) algorithm to combine the natural gradient (NG) method with local curvature information from Hessian-free (HF). A solution to a numerical issue in CG allows effective parameter updates to be generated with far fewer CG iterations than usually used (e.g. 5-8 instead of 200). This work also presents a novel preconditioning approach to improve the progress made by individual CG iterations for models with shared parameters. Although applicable to other training losses and model structures, NGHF is investigated in this paper for lattice-based discriminative sequence training for hybrid hidden Markov model acoustic models using a standard recurrent neural network, long short-term memory, and time delay neural network models for output probability calculation. Automatic speech recognition experiments are reported on the multi-genre broadcast data set for a range of different acoustic model types. These experiments show that NGHF achieves larger word error rate reductions than standard stochastic gradient descent or Adam, while requiring orders of magnitude fewer parameter updates. • Large batch optimisation: NGHF. Combines natural gradient (NG) & Hessian-free (HF). • Faster convergence of each update estimated via improved conjugate gradient. • Applied NG, HF & NGHF to discriminative sequence training for speech recognition. • NG, HF, and NGHF require orders of magnitude fewer parameter updates than Adam & SGD. • MPE training with NGHF achieves lower word error rates than with NG, HF, Adam & SGD. [ABSTRACT FROM AUTHOR]

This paper discusses the estimation of zonal geomagnetic indices of two super geomagnetic activities of 2015 in the 24th solar cycle. It estimates the zonal geomagnetic indices (Dst, ap, AE) of 17 March and 22 June 2015 super storms with an artificial neural network model. The activities that happened in March and June are considered on the solar wind parameters (B z , E, P, N, v, T) and zonal geomagnetic indices obtained from NASA coordinated data analysis web. Descriptive values of the variables are indicated, binary correlations of the data are shown with the covariance matrix and the hierarchical cluster of the data are presented by the dendrogram. In the paper, the physical principles govern the artificial neural network model. The model utilizes solar wind parameters as inputs and zonal geomagnetic indices as outputs. The causality principle shapes the models by cause-effect relationship. Back propagation algorithm is specified as Levenberg–Marquardt (trainlm) and 30 neural numbers are used in the artificial neural network. The neural network model estimates the Dst, ap, and AE indices of 17 March and 22 June activities with reliable accuracy. The geomagnetic activity estimation can support interplanetary studies. [ABSTRACT FROM AUTHOR]

Despite the existence of evidence-based rehabilitation strategies that address biomechanical deficits, the persistence of recurrent ankle problems in 70% of patients with acute ankle sprains highlights the unresolved nature of this issue. Artificial intelligence (AI) emerges as a promising tool to identify definitive predictors for ankle sprains. This paper aims to summarize the use of AI in investigating the ankle biomechanics of healthy and subjects with ankle sprains. Articles published between 2010 and 2023 were searched from five electronic databases. 59 papers were included for analysis with regards to: i). types of motion tested (functional vs. purposeful ankle movement); ii) types of biomechanical parameters measured (kinetic vs kinematic); iii) types of sensor systems used (lab-based vs field-based); and, iv) AI techniques used. Most studies (83.1%) examined biomechanics during functional motion. Single kinematic parameter, specifically ankle range of motion, could obtain accuracy up to 100% in identifying injury status. Wearable sensor exhibited high reliability for use in both laboratory and on-field/clinical settings. AI algorithms primarily utilized electromyography and joint angle information as input data. Support vector machine was the most used supervised learning algorithm (18.64%), while artificial neural network demonstrated the highest accuracy in eight studies. The potential for remote patient monitoring is evident with the adoption of field-based devices. Nevertheless, AI-based sensors are underutilized in detecting ankle motions at risk of sprain. We identify three key challenges: sensor designs, the controllability of AI models, and the integration of AI-sensor models, providing valuable insights for future research. [Display omitted] • Application of sensors and artificial intelligence to analyse ankle biomechanics. • Lab sensors predict parameters, paving the way for post-modern rehabilitation. • Field devices show potential for ankle injury prediction. • Focus on streamlined smart sensors and effective data management in the future. [ABSTRACT FROM AUTHOR]

• This paper suggests a grating Moiré fringe-based error correction approach that uses an artificial neural network (ANN) and the quartile method (QM). • The approach uses QM for data cleaning operations to eliminate outliers and creates the ANN model with a structure of fully connected layer-normalization layer-fully connected layer for regression training in order to achieve lightweight and stability. • The proposed QM-ANN error correction model's mean absolute error (MAE) can reach 3.3 nm once the QM data has been cleaned and the ANN model has been trained. Many interference factors of the complex and changeable working environment of the grating sensor are the main factors affecting the accuracy; a grating Moiré fringe error correction model based on the quartile method (QM) and artificial neural network (ANN) is proposed in this paper. Firstly, the grating sensor's signals in the working process are collected, and three kinds of interference signals (temperature, humidity and vibration) from the grating sensor working environment are collected simultaneously. Secondly, the QM is used to detect outliers from the collected data and delete data outliers directly. Subsequently, the processed data are input into the ANN model for training. The model is lightweight and stable, because it adopts the cascaded structure of full connection layer-normalization layer-full connection layer, which does not need deploy the complex convolution layer module etc. Finally, the corrected data are output after being processed by the QM-ANN error correction model. The experimental results show that the mean absolute error (MAE) of the proposed QM-ANN error correction model is better than QM-convolutional neural network (CNN), QM-long short-term memory (LSTM) and ANN, CNN, LSTM models without QM. It shows that the proposed model has better robustness and practicability. [ABSTRACT FROM AUTHOR]

In this paper, a novel control scheme is developed to solve an optimal containment control problem of unknown continuous-time multi-agent systems. Different from traditional adaptive dynamic programming (ADP) algorithms, this paper proposes an internal reinforcement ADP algorithm (IR-ADP), in which the internal reinforcement signals are added in order to facilitate the learning process. Then a distributed containment control law is designed for each agent with the internal reinforcement signal. The convergence of this IR-ADP algorithm and the stability of the closed-loop multi-agent system are analyzed theoretically. For the implementation of the optimal controllers, three neural networks (NNs), namely internal reinforcement NNs, critic NNs and actor NNs, are utilized to approximate the internal reinforcement signals, the performance indices and optimal control laws, respectively. Finally, some simulation results are provided to demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Approaching to the biological neural network, small-world neural networks have been demonstrated to improve the generalization performance of artificial neural networks. However, the architecture of small-world neural networks is typically large and predefined. This may cause the problems of overfitting and time consuming, and cannot obtain an optimal network structure automatically for a given problem. To solve the above problems, this paper proposes a pruning feedforward small-world neural network (PFSWNN), and applies it to nonlinear system modeling. Firstly, a feedforward small-world neural network (FSWNN) is constructed according to the rewiring rule of Watts–Strogatz. Secondly, the importance of each hidden neuron is evaluated based on its Katz centrality. If the Katz centrality of a hidden neuron is below the predefined threshold, this neuron is considered to be an unimportant node and then merged with its most correlated neuron in the same hidden layer. The connection weights are trained using the gradient-based algorithm, and the convergence of the proposed PFSWNN is theoretically analyzed in this paper. Finally, the PFSWNN model is tested on some problems for nonlinear system modeling, including the approximation for a rapidly changing function, CATS missing time-series prediction, four benchmark problems of UCI public datasets and a practical problem for wastewater treatment process. Experimental results demonstrate that PFSWNN exhibits superior generalization performance by small-world property as well as the pruning algorithm, and the training time of PFSWNN is shortened owning to a compact structure. • The importance of the hidden nodes is measured using Katz centrality. • The small-worldness property and pruning improve the generalization performance of PFSWNN. • PFSWNN can self-adjust to a compact structure by the pruning algorithm. • The convergence of PFSWNN can be guaranteed. [ABSTRACT FROM AUTHOR]

Matrix completion is extensively studied due to its wide applications in science and technology. In this paper, we concentrate our study on the matrix completion problem for image analysis tasks due to their immense importance and pervasive use in many fields. A rich collection of models has been proposed to capture both linear and nonlinear relationships latent in a matrix. Even though nonlinear models possess more powerful matrix completion capabilities than their linear counterparts, these models generally carry higher model complexity and tuning difficulties. To take advantage of the superior discriminative power offered by nonlinear models while curbing its deployment overheads, this paper proposes a novel nonlinear matrix completion model utilizing a deep learning-based approach. In contrast to existing nonlinear models, the new model carefully explores and exploits spatial locality among adjacent matrix elements exhibited in patches of various sizes and locations in a target matrix. Building upon this idea, a new patch-based nonlinear matrix completion algorithm is designed. The algorithm leverages a convolutional neural network to learn the predictive relationship between a matrix element and its surrounding elements through an end-to-end trainable fashion, leading to a capable and easy-to-deploy nonlinear matrix completion solution. To identify an optimal patch size suited for tackling a given matrix completion task without exhaustively enumerating all candidate patch sizes, the new algorithm is coupled with a fast stochastic search procedure, yielding a good trade-off between computational efficiency and accuracy. Extensive experiments are conducted to validate the effectiveness and advantages of the proposed algorithm for nonlinear matrix completion problem in comparison with a series of state-of-the-art algorithms. Experimental results consistently demonstrate the superiority of the new algorithm in completing images with a variety of random and textual noises. [ABSTRACT FROM AUTHOR]

The integration of Spiking Neural Networks (Maass, 1997) and Transformers (Vaswani et al., 2017) has significantly enhanced performance in the field, achieving substantial improvements while ensuring energy efficiency. This amalgamation bears significant exploratory significance. This paper aims to enhance the network's capacity for extracting temporal information from neuromorphic datasets. By leveraging the Spikformer (Zhou et al., 2023b) architecture, we introduce a novel network named TE-Spikformer. Through thorough analysis, we identified an imbalance in the Average Firing Rates(AFR) of neurons in the layer preceding the classification head across temporal steps. We thoroughly investigate the root cause of this issue, attributing it to the limitations of the network's use of Batch Normalization (BN) (Ioffe and Szegedy, 2015) layer. To address these challenges, we propose a Batch Group Normalization (BGN) layer. While maintaining the stability of temporal characteristics in the data, we also introduce the Spike Spatio-Temporal Attention(SSTA) module to enhance the network's ability to capture temporal information. To validate the effectiveness of our approach, we conducted multiple experiments using neuromorphic datasets, including DVS-CIFAR10, DVS128 Gesture, and N-Caltech101. The experimental results demonstrate that our algorithm consistently outperforms baseline methods, achieving accuracy rates of 99.30%, 89.60%, and 87.42%, respectively, thereby attaining state-of-the-art performance in the field. • Proposed imbalanced average firing rate across time steps. • Analyzed BN layer inadequacy, proposed BGN layer. • Introduced Spike Spatio-Temporal Attention (SSTA) module. • Achieved SOTA results on three popular neuromorphic datasets. [ABSTRACT FROM AUTHOR]

In recent years, the research on transferable feature-level adversarial attack has become a hot spot due to attacking unknown deep neural networks successfully. But the following problems limit its transferability. Existing feature disruption methods often focus on computing feature weights precisely, while overlooking the noise influence of feature maps, which results in disturbing non-critical features. Meanwhile, geometric augmentation algorithms are used to enhance image diversity but compromise information integrity, which hamper models from capturing comprehensive features. Furthermore, current feature perturbation could not pay attention to the density distribution of object-relevant key features, which mainly concentrate in salient region and fewer in the most distributed background region, and get limited transferability. To tackle these challenges, a feature distribution-aware transferable adversarial attack method, called FDAA, is proposed to implement distinct strategies for different image regions in the paper. A novel Aggregated Feature Map Attack (AFMA) is presented to significantly denoise feature maps, and an input transformation strategy, called Smixup, is introduced to help feature disruption algorithms to capture comprehensive features. Extensive experiments demonstrate that scheme proposed achieves better transferability with an average success rate of 78.6% on adversarially trained models. [ABSTRACT FROM AUTHOR]

• Formulation of a chance-constrained model for optimal power-water flow. • Recasting the model as a tractable problem using uncertain margins and convex relaxation. • Development of a novel iterative algorithm integrating two deep neural networks. • Achievement of a solution error under 0.03 % with a speedup over 200. The optimal power-water flow (OPWF) is a fundamental tool for operating integrated power and water networks. To address uncertainties in renewable energy and load demands, researchers have used chance-constrained models to investigate OPWF under uncertainty. However, existing work has limitations, such as oversimplified network representations, intractable problem formulations, and high computational burdens. This paper presents a chance-constrained OPWF formulation that incorporates detailed network constraints and stochastic uncertainties from wind speeds and electricity/water demands. By leveraging the concept of quantiles of stochastic variables and convexification techniques, the model is recast into a deterministic mixed-integer second-order cone programming (MISOCP) problem with uncertain margins. To efficiently solve this problem, we propose a novel iterative algorithm assisted by deep neural networks (DNNs). The algorithm integrates two DNNs: one designed to solve power and water flow equations, accelerating the probabilistic evaluation of uncertain margins; and the other to predict pipeline flows and refine variable ranges, facilitating a warm-start approach to the MISOCP model. Case studies conducted on the IEEE 123-node feeder coupled with a 67-node water distribution network validate the two DNNs and the overall iterative algorithm. The findings demonstrate that the proposed DNN-assisted approach effectively balances system security and economy. Compared to existing algorithms, the relative error of the optimization solution is less than 0.03%, with a speedup ratio exceeding 200. [ABSTRACT FROM AUTHOR]

As the deployment of artificial intelligence (AI) algorithms at edge devices becomes increasingly prevalent, enhancing the robustness and reliability of autonomous AI-based perception and decision systems is becoming as relevant as precision and performance, especially in applications areas considered safety-critical such as autonomous driving and aerospace. This paper delves into the robustness assessment in embedded Deep Neural Networks (DNNs), particularly focusing on the impact of parameter perturbations produced by single event upsets (SEUs) on convolutional neural networks (CNN) for image semantic segmentation. By scrutinizing the layer-by-layer and bit-by-bit sensitivity of various encoder–decoder models to soft errors, this study thoroughly investigates the vulnerability of segmentation DNNs to SEUs and evaluates the consequences of techniques like model pruning and parameter quantization on the robustness of compressed models aimed at embedded implementations. The findings offer valuable insights into the mechanisms underlying SEU-induced failures that allow for evaluating the robustness of DNNs once trained in advance. Moreover, based on the collected data, we propose a set of practical lightweight error mitigation techniques with no memory or computational cost suitable for resource-constrained deployments. The code used to perform the fault injection (FI) campaign is available at https://github.com/jonGuti13/TensorFI2 , while the code to implement proposed techniques is available at https://github.com/jonGuti13/parameterProtection. [ABSTRACT FROM AUTHOR]

In recent years, the application of deep neural networks in the field of image classification has become increasingly widespread. However, existing researches have exposed the inherent vulnerabilities and opacity of these network models, rendering them susceptible to carefully crafted adversarial attacks. This poses significant security risks to their practical deployment. Given that the majority of models in real-world applications operate in a black-box manner, current research on black-box attacks targeting classification models remains inadequate, facing significant challenges such as incomplete robustness evaluations, low success rates of black-box attacks, and excessive resource consumption during the attack process. To address these challenges, this paper innovatively proposes a black-box attack algorithm based on a cycle-consistent generative network. This algorithm directly generates adversarial perturbations through a generative network that integrates an attention mechanism, deeply learning the complex relationship between adversarial samples and clean sample data. It supports both targeted and untargeted attack modes. Experimental validation on the SAT dataset demonstrates that our method achieves an average white-box attack success rate exceeding 96% in classification tasks and an average success rate of up to 69.4% in black-box transfer attacks, exhibiting excellent transferability across different models. This research contributes significantly to enhancing the effectiveness of black-box attacks, reducing attack costs, and providing novel ideas and methods for enhancing the security of deep learning models. • We proposed an optimized cycle-consistent generative network for adversarial attacks, ultimately enhancing the success rate against other diverse black-box models. • Our algorithm offers support for both targeted and non-targeted attacks. Our targeted approach confers directionality to the generated perturbations, enabling purposeful attacks tailored to the attacker's intentions. • A transformation distribution module is incorporated into our model. We introduce a distance loss function to our overall loss computation. • Our approach enables migration attacks across different models, achieving a black-box attack success rate superior to current methods, exceeding 69.4%. [ABSTRACT FROM AUTHOR]

Even though the demand for utilizing geopolymers is growing, the need for current standard guidelines to regulate compliance to address the complexity of the mix design could be one of the major hurdles of utilizing geopolymers vastly in construction. There is no straightforward standard that addresses the complexity of the mix design of geopolymers. Thus, this work addresses main factors affecting the compressive strength of slag based geopolymers and provide a tool for predicting it. This article includes experimental work to evaluate the properties of slag-based geopolymer binders and the development of a model using Artificial Neural Network (ANN) algorithms for predicting the performance of these slag-based geopolymer binders. In this paper, we have utilized and developed ANN models for optimizing slag-based geopolymer mixes based on precursor materials' physiochemical properties and activation solutions constituents that can enhance performance compressive strength prediction in construction applications. • A high-accuracy DOE model was developed and used to characterize the Geopolymeric paste. • A developed ANN model was superior in forecasting the compressive strength of AAS systems. • The choice of the alkali activator has minimal impact on the compressive strength. • The optimal water-to-slag ratio is approximately 0.28. • The optimal alkali oxide concentration is 6 %. [ABSTRACT FROM AUTHOR]

Abstract In the last 20 years, and in particular in the last decade, the availability of propagation data for GNSS has increased substantially. In this sense, the ionosphere has been sounded with a large number of receivers that provide an enormous amount of ionospheric data. Moreover, the maturity of the models has also been increased in the same period of time. As an example, IGS has ionospheric maps from GNSS data back to 1998, which would allow for the correlation of these data with other quantities relevant for the user and space weather (such as Solar Flux and Kp). These large datasets would account for almost half a billion points to be analyzed. With the advent and explosion of Big Data algorithms to analyze large databases and find correlations with different kinds of data, and the availability of open source code libraries (for example, the TensorFlow libraries from Google that are used in this paper), the possibility of merging these two worlds has been widely opened. In this paper, a proof of concept for a single frequency correction algorithm based in GNSS GIM vTEC and Fully Connected Neural Networks is provided. Different Neural Network architectures have been tested, including shallow (one hidden layer) and deep (up to five hidden layers) Neural Network models. The error in training data of such models ranges from 50% to 1% depending on the architecture used. Moreover, it is shown that by adjusting a Neural Network with data from 2005 to 2009 but tested with data from 2016 to 2017, Neural Network models could be suitable for the forecast of vTEC for single frequency users. The results indicate that this kind of model can be used in combination with the Galileo Signal-in-Space (SiS) NeQuick G parameters. This combination provides a broadcast model with equivalent performances to NeQuick G and better than GPS ICA for the years 2016 and 2017, showing a 3D position Root Mean Squared (RMS) error of approximately 2 m. [ABSTRACT FROM AUTHOR]

Abstract With the rapid development of high-through technology, vast amounts of protein molecular data has been generated, which is crucial to advance our understanding of biological organisms. An increasing number of protein post translation modification sites identification approaches have been designed and developed to detect such modification sites among the protein sequences. Nevertheless, these methods are merely suitable for one type of modification site, their performance deteriorate rapidly when applied to other types of modification sites' prediction. In this paper, with the method of different types of neural network algorithm ensemble, a novel method, named CMSENN (http://121.250.173.184/) Computational Modification Sites with Ensemble Neural Network, was proposed to detect protein modification. The algorithm mainly consists of several steps: First, the predicted peptide sequences translate to the feature vectors. Second, the three types of employed amino acid residues properties should be normalized. Finally, various combination of features and classification model have been compared the performances with several current typical algorithms. The results demonstrate that the proposed model have well performance at the sensitivity, specificity, F1 score and Matthews correlation coefficient (MCC) value in the identification modification with the approach of the selected features and algorithm combination. Highlights • This paper proposed CMSENN to detect protein modification sites. • The predicted peptide sequences translate to the feature vectors. • And three types of employed amino acid residues properties should be normalized. • The results demonstrate that the proposed model have well performance. [ABSTRACT FROM AUTHOR]

Highlights • We provide computational intelligence method for different levels of the system. • We describe the development direction of the intelligent system. • We introduce the basic state-of-the-art concepts of data mining. • We validate the performance of the model with discussions on applications. Abstract The integration of intelligent system mainly includes the application of intelligent technology, such as artificial intelligence and computational intelligence method, which is used in different levels of the system. This paper introduces the application and technology of several intelligent system integrations, the advantages and disadvantages of learning theory and expert system. Neural network is applied in intelligent systems and we use scope reviewed several new development of intelligent technology, plus this paper describes the development direction of the intelligent system. This paper introduces the basic concepts of data mining, including data mining technology, artificial intelligence, machine learning, statistical analysis, fuzzy logic, pattern recognition and artificial neural networks and other technologies. We analyze the structure of the general algorithm of data mining, and classify the data mining technology in details, including more than 10 techniques of decision tree technology, neural network technology, rough set and fuzzy set. Finally, the research directions of data mining in artificial intelligence, e-commerce applications and mobile communication computing are discussed. [ABSTRACT FROM AUTHOR]

• We are the first to propose QSNN: a quantum algorithm to speed up the classic spiking neural network. • We give the proof for minimum success probability and calculation accuracy of QSNN. • We verify the complexity of QSNN is log-polynomial, and better than the complexity of SNN. • We validate the feasibility and robustness of QSNN on real-world datasets. Spiking neural networks (SNNs) are a kind of neuromorphic computing which meticulously imitates the operations of biological nervous systems. Thus, the SNN is seen as a promising approach to further improve the level of intelligence that the legacy artificial neural networks achieved. In a spiking neuron of an SNN, it is a key step with the highest computing complexity to find out the moment when the output stimuli occur. Classic computer (i.e., electrical computer) based acceleration cannot reduce the computational complexity of the operations in the spiking neurons. As a result, the SNN suffers from scaling and deeper emulation problems. Considering these, in this paper, we propose a quantum algorithm to reduce the complexity of the key steps in the SNN and use this algorithm to build a quantum spiking neuron network (QSNN). More specifically, first, we give mathematical proof that the problem of finding the output stimuli is approximately equal to the problem of calculating the unsigned vector inner products, which can transfer to a quantum operation. Second, we design a scalable quantum circuit of QSNN for data of any dimension and evaluate its basic success probability and calculation accuracy. Third, to improve the QSNN performance, we propose a method to improve the minimum success probability to 99.8%, by repeatedly performing the quantum circuit only 11 times. Fourth, we prove that the computational complexity of the QSNN is a log-polynomial relationship with the data dimension, which is much lower than that of the linear complexity of the classic SNN. Finally, we apply the QSNN to solve classification tasks on two real-world datasets, i.e., MNIST and fashion MNIST which both have two noise levels (i.e., no noise and 50% of the noise). The experiment results show that in addition to the acceleration, QSNN and SNN have equal classification accuracy, which suggests the feasibility and robustness of the QSNN. [ABSTRACT FROM AUTHOR]

Abstract Learning of convolutional neural networks (CNNs) to perform a face recognition task requires a large set of facial images each annotated with a label to be predicted. In this paper we propose a method for learning CNNs from weakly annotated images. The weak annotation in our setting means that a pair of an attribute label and a person identity label is assigned to a set of faces automatically detected in the image. The challenge is to link the annotation with the correct face. The weakly annotated images of this type can be collected by an automated process not requiring a human labor. We formulate learning from weakly annotated images as a maximum likelihood (ML) estimation of a parametric distribution describing the weakly annotated images. The ML problem is solved by an instance of the EM algorithm which in its inner loop learns a CNN to predict attribute label from facial images. Experiments on age and gender estimation problem show that the proposed algorithm significantly outperforms the existing heuristic approach for dealing with this type of data. A practical outcome of our paper is a new annotation of the IMDB database [26] containing 300 k faces each one annotated by biological age, gender and identity labels. Highlights • Celebrity images can be automatically annotated by age, gender and identity. • New database of 300 k face images annotated by age, gender and identity • Algorithm for learning convolutional networks from weakly annotated images [ABSTRACT FROM AUTHOR]

In this paper, the application of Artificial Neural Networks to perform the thermal calibration of bias for Micro Electro-Mechanical gyros that are installed in Inertial Measurement Units is discussed. In recent years, the interest in using these systems to perform integrated inertial navigation has increased. Several new applications, related to the use of autonomous systems and personal navigation systems in GPS-challenging environments, have been developed. Thermal calibration of bias is a key issue to be assessed to achieve the best performance of a Micro Electro-Mechanical gyro. It can reduce sensor bias to one order of magnitude lower than non-calibrated conditions. Usually, thermal calibration is performed by exploiting polynomial fitting, i.e. finding the least-square polynomial that fits experimental data collected during laboratory tests in a climatic chamber. Polynomials have some drawbacks when they are applied to Micro Electro-Mechanical gyro calibration. They are not adequate to model abrupt change of bias trend in small temperature intervals and sensor hysteresis. For this reason, in the present paper, the use of Back Propagation Artificial Neural Networks is suggested as an improvement of polynomial fitting. Indeed, Neural Networks have intrinsic adaptive configurations and standard training and testing techniques, so that they can be adequately adopted for mapping thermal bias variations. In this paper, the polynomial fitting and Neural Network compensation algorithms are compared on selected testing points where the two techniques have the largest difference. Results highlight that the proposed method has better performance on these points. Therefore, the time in which the flight attitude accuracy meets the requirements imposed by the current regulations is improved by 20%. [ABSTRACT FROM AUTHOR]

Today, the Structural Health Monitorin (SHM) methodology is the main way to deal with the detection and identification of damages in a range of engineering sectors, mainly in the military and civil aerospace industry. The need to monitor damages and failures in increasingly complex structures has led to the development of various detection techniques. Identification of damages through intelligent signal processing and optimization algorithms are particularly emphasized. The methods discussed here are mainly elaborated by the evaluation of modal data due to the great potential of their application. Moreover, the optimization of damage identification is approached through methods of optimal positioning of sensors for the acquisition of the data that must be evaluated so that conclusions can be made. This article discusses the use of computational and intelligent techniques for structural monitoring in the form of a review with emphasis on composite materials. Despite the excellent mechanical performance already known about composite materials, they have a weak point. While damages, in a metallic material are easily visible (in some cases), composite materials often have the superficial appearance as if in perfect condition, when, inside, there are serious damages. This paper can be seen as a guideline or a starting point for developing and improving SHM systems. The contents of this paper aim to help engineers and researchers find a starting point in developing a better solution to their specific structural monitoring problems, either by inverse methods, pattern recognition, and intelligent signal processing. [ABSTRACT FROM AUTHOR]

The primary purpose of this paper is to realize robust place recognition algorithms towards simultaneous viewpoint and condition changes, and provide satisfactory computational efficiency. In this paper, we significantly improve the viewpoint invariance of the SeqSLAM algorithm by using state-of-the-art deep learning techniques to generate robust feature representations of images and develop the SeqCNNSLAM . Experimental results show that SeqCNNSLAM outperforms state-of-the-art place recognition systems in most cases, such as, when precision is maintained at 100%, the maximum recall obtained by SeqCNNSLAM is 50% higher than SeqSLAM on the Norland dataset with simultaneous condition change and 12.5% viewpoint change. Besides, we develop an acceleration method called A-SeqCNNSLAM , which exploits the location relationship between the matching images of adjacent images to reduce the matching range of the current image. Experimental results demonstrate that an acceleration of  ∼  5 times is achieved with minimal accuracy degradation of  ∼  5%. Finally, to enable A-SeqCNNSLAM adaptability in new environments, O-SeqCNNSLAM is devised for the online parameter adjustment in A-SeqCNNSLAM. [ABSTRACT FROM AUTHOR]

An algorithm that generates an exponential number of stable states for the very well-known Hopfield Neural Network (HNN) is introduced in this paper. We show that the quantity of stable states depends on the dimension and number of components of the input pattern supporting noise. Extensive tests verify that the states generated by our algorithm are stable states and show the exponential storage capacity of a HNN. This paper opens the possibility of designing improved HNNs able to achieve exponential storage, and thus find their applicability in complex real-world problems. [ABSTRACT FROM AUTHOR]

In this paper, a hierarchical method for human body segmentation in static images is proposed. Based on the face detection, a torso model is developed to locate the torso to provide the foreground seeds for torso segmentation with graph cuts. Similarly, an upper leg model is designed for lower body segmentation based on the segmented torso. Besides, a general method which combines shape information into graph cuts is presented, which can make the segmentation more accurate. The main contributions of this paper include two models and a new method of integrating shape information into graph cuts. Experiments on our collected real world images show that our method can accurately recover human body from static images with a variety of individuals, poses, backgrounds and clothing. [ABSTRACT FROM AUTHOR]

The problem of subspace clustering which refers to segmenting a collection of data samples approximately drawn from a union of linear subspaces is considered in this paper. Among existing subspace clustering algorithms, low rank representation (LRR) based subspace clustering is a very powerful method and has demonstrated that its performance is good. Latent low rank representation (LLRR) subspace clustering algorithm is an improvement of the original LRR algorithm when the observed data samples are insufficient. The clustering accuracy of LLRR is higher than that of LRR. Recently, Frobenius norm minimization based LRR algorithm has been proposed and its clustering accuracy is higher than that of LRR demonstrating the effectiveness of Frobenius norm as another convex surrogate of the rank function. Combining LLRR and Frobenius norm, a new low rank representation subspace clustering algorithm is proposed in this paper. The nuclear norm in the LLRR algorithm is replaced by the Frobenius norm. The resulting optimization problem is solved via alternating direction method of multipliers (ADMM). Experimental results show that compared with LRR, LLRR and several other state-of-the-art subspace clustering algorithms, the proposed algorithm can get higher clustering accuracy. Compared with LLRR, the running time of the proposed algorithm is reduced significantly. [ABSTRACT FROM AUTHOR]

Metastatic femoral tumors may lead to pathological fractures during daily activities. A CT-based finite element analysis of a patient's femurs was shown to assist orthopedic surgeons in making informed decisions about the risk of fracture and the need for a prophylactic fixation. Improving the accuracy of such analyses ruqires an automatic and accurate segmentation of the tumors and their automatic inclusion in the finite element model. We present herein a deep learning algorithm (nnU-Net) to automatically segment lytic tumors within the femur. A dataset consisting of fifty CT scans of patients with manually annotated femoral tumors was created. Forty of them, chosen randomly, were used for training the nnU-Net, while the remaining ten CT scans were used for testing. The deep learning model's performance was compared to two experienced radiologists. The proposed algorithm outperformed the current state-of-the-art solutions, achieving dice similarity scores of 0.67 and 0.68 on the test data when compared to two experienced radiologists, while the dice similarity score for inter-individual variability between the radiologists was 0.73. The automatic algorithm may segment lytic femoral tumors in CT scans as accurately as experienced radiologists with similar dice similarity scores. The influence of the realistic tumors inclusion in an autonomous finite element algorithm is presented in (Rachmil et al., "The Influence of Femoral Lytic Tumors Segmentation on Autonomous Finite Element Analyses", Clinical Biomechanics, 112, paper 106192, (2024)). • A deep learning algorithm for automatic segmentation of lytic femoral tumors is developed. • The deep learning dice similarity score of ∼0.67 is obtained, higher than any former study. • Inter-individual dice similarity score variability between two radiologists was 0.73. • The automatic segmentation of lytic tumors is as good as a radiologist. [ABSTRACT FROM AUTHOR]

Gradient-based algorithms are commonly used for training radial basis function neural network (RBFNN). However, it is still difficult to avoid vanishing gradient to improve the learning performance in the training process. For this reason, in this paper, an accelerated second-order learning (ASOL) algorithm is developed to train RBFNN. First, an adaptive expansion and pruning mechanism (AEPM) of gradient space, based on the integrity and orthogonality of hidden neurons, is designed. Then, the effective gradient information is constantly added to gradient space and the redundant gradient information is eliminated from gradient space. Second, with AEPM, the neurons are generated or pruned accordingly. In this way, a self-organizing RBFNN (SORBFNN) which reduces the structure complexity and improves the generalization ability is obtained. Then, the structure and parameters in the learning process can be optimized by the proposed ASOL-based SORBFNN (ASOL-SORBFNN). Third, some theoretical analyses including the efficiency of the proposed AEPM on avoiding the vanishing gradient and the stability of SORBFNN in the process of structural adjustment are given, then the successful application of the proposed ASOL-SORBFNN is guaranteed. Finally, to illustrate the advantages of the proposed ASOL-SORBFNN, several experimental studies are examined. By comparing with other existing approaches, the results show that ASOL-SORBFNN performs well in terms of both learning speed and prediction accuracy. [ABSTRACT FROM AUTHOR]

[Display omitted] • A novel polar representation is introduced for video object segmentation. • An asymmetric Siamese network is developed using similar backbones with different depths. • We design the repeated cross correlation and semi-FPN based on peeling convolutions. Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. Besides the accuracy metric, the real-time speed is very important for the algorithms of autonomous vehicles. In this paper, we propose a semi-supervised real-time method based on the Siamese network using a new polar representation. The input of bounding boxes are initialized rather than the object masks, which are applied to the video object detection tasks. The polar representation could reduce the parameters for encoding masks with subtle accuracy loss, so that the algorithm speed can be improved significantly. An asymmetric siamese network is also developed to extract the features from different spatial scales. Moreover, the peeling convolution is proposed to reduce the antagonism among the branches of the polar head. The repeated cross-correlation and semi-FPN are designed based on this idea. The experimental results on the DAVIS-2016 dataset and other public datasets demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In the artificial neural networks domain, the Levenberg-Marquardt technique is novel with convergent stability and generates a numerical solution of the wire coating system for Sisko fluid flow (WCS-SFF) through regression plots, histogram representations, state transition measures, and means squared errors. In this paper, the analysis of fluid flow problem based on WCS-SFF is studied with a new application of intelligent computing system via supervised learning mechanism using the efficacy of neural networks trained by Levenberg-Marquardt algorithm (NN-TLMA). The original mathematical formulation in terms of PDEs for WCS-SFF is converted into dimensionless nonlinear ODEs. The data collection for the projected NN-TLMA is produced for parameters associated with the system model WCS-SFF influencing the velocity using the explicit Runge-Kutta technique. The training, validation, and testing processes of NN-TLMA are utilized to evaluate the obtained results of WCS-SFF for various cases, and a comparison of the obtained results is performed with reference data set to check the accuracy and effectiveness of the proposed algorithm NN-TLMA for the analysis of non-Newtonian fluid problem-related WCS-SFF. The proposed NN-TLMA for solving the WCS-SFF is effectively confirmed through state transition dynamics, mean square error, regression analyses, and error histogram studies. The powerful consistency of suggested outcomes with reference solutions indicates the validity of the framework, and the accuracy of 10 - 8 to 10 - 6 is also achieved. [ABSTRACT FROM AUTHOR]

We use a recently developed synchronous Spiking Neural Network (SNN) model to study the problem of learning hierarchically-structured concepts. We introduce an abstract data model that describes simple hierarchical concepts. We define a feed-forward layered SNN model, with learning modeled using Oja's local learning rule, a well known biologically-plausible rule for adjusting synapse weights. We define what it means for such a network to recognize hierarchical concepts; our notion of recognition is robust, in that it tolerates a bounded amount of noise. Then, we present a learning algorithm by which a layered network may learn to recognize hierarchical concepts according to our robust definition. We analyze correctness and performance rigorously; the amount of time required to learn each concept, after learning all of the sub-concepts, is approximately O 1 η k ℓmax log (k) + 1 ɛ + b log (k) , where k is the number of sub-concepts per concept, ℓmax is the maximum hierarchical depth, η is the learning rate, ɛ describes the amount of uncertainty allowed in robust recognition, and b describes the amount of weight decrease for "irrelevant" edges. An interesting feature of this algorithm is that it allows the network to learn sub-concepts in a highly interleaved manner. This algorithm assumes that the concepts are presented in a noise-free way; we also extend these results to accommodate noise in the learning process. Finally, we give a simple lower bound saying that, in order to recognize concepts with hierarchical depth two with noise-tolerance, a neural network should have at least two layers. The results in this paper represent first steps in the theoretical study of hierarchical concepts using SNNs. The cases studied here are basic, but they suggest many directions for extensions to more elaborate and realistic cases. [ABSTRACT FROM AUTHOR]

Find the global optimal solution of the model is one promising research topic in computational intelligent community. Dependent on analogies to natural processes, the evolutionary swarm intelligent algorithms are widely used for solving global optimization problems which directed by the fitness values. In this paper, we propose one efficient fractional global learning machine (Fragmachine) which includes two stages (descending and ascending) to determine the optimal search path. The neural network model is used to approach the given fitness value. Specifically, for the descending stage, the integer gradient of the network output with respect the current location is employed to find the next descending point, while for the ascending stage, the fractional gradient is implemented to climb and escape from the local optimal point. We further propose one adaptive learning rate during training which relies on both the current gradient (integer or fractional) information and the fitness value. Finally, a series of numerical experiments verify the effectiveness of the proposed algorithm, Fragmachine. [ABSTRACT FROM AUTHOR]

Most deep neural networks (DNNs) are trained with large amounts of noisy labels when they are applied. As DNNs have the high capacity to fit any noisy labels, it is known to be difficult to train DNNs robustly with noisy labels. These noisy labels cause the performance degradation of DNNs due to the memorization effect by over-fitting. Earlier state-of-the-art methods used small loss tricks to efficiently resolve the robust training problem with noisy labels. In this paper, relationship between the uncertainties and the clean labels is analyzed. We present novel training method to use not only small loss trick but also labels that are likely to be clean labels selected from uncertainty called "Uncertain Aware Co-Training (UACT)". Our robust learning techniques (UACT) avoid over-fitting the DNNs by extremely noisy labels. By making better use of the uncertainty acquired from the network itself, we achieve good generalization performance. We compare the proposed method to the current state-of-the-art algorithms for noisy versions of MNIST, CIFAR-10, CIFAR-100, T-ImageNet and News to demonstrate its excellence. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm for the end-to-end recognition of slab identification numbers (SINs). In the steel industry, automatic recognition of an individual product information is important for production management. The recognition of SINs in actual factory scenes is a challenging problem due to complicated background and low-quality of characters. Conventional rule-based algorithms were developed to extract information of SINs, but these methods require engineering knowledge and tedious work for parameter tuning. The proposed algorithm employs a data-driven method to overcome these limitations and to handle the challenges for the recognition of SINs. This paper proposes accumulated response map and model-based score function to effectively use the outputs of a deep convolutional neural network. Experiments were thoroughly conducted for industrial data collected from an actual steelworks to verify the effectiveness of the proposed algorithm. Experiment results demonstrate that simultaneous recognition of entire characters in a SIN by optimizing the model-based score function is more effective for the robust performance compared to separated recognition of individual characters. [ABSTRACT FROM AUTHOR]

Recently, Extreme learning machine (ELM), an efficient training algorithm for single-hidden-layer feedforward neural networks (SLFN), has gained increasing popularity in machine learning communities. In this paper the ELM based Area Under the ROC Curve (AUC) optimization algorithms are studied so as to further improve the performance of ELM for imbalanced datasets. For binary class problems, a novel ELM algorithm is proposed based on an efficient least square method. For multi-class problems, the following works are done in this paper: First of all, theoretical comparison analysis is proposed for the potential multi-class extensions of AUC; Secondly, a unified objective function for multi-class AUC optimization is proposed following the theoretical analysis; Subsequently, two ELM based multi-class AUC optimization algorithms called E L M M A U C and E L M m a c r o A U C respectively are proposed followed with complexity analyses; Finally, the generalization analysis is established for E L M M A U C in search of theoretical supports. Empirical study on a variety of real-world datasets show the effectiveness of our proposed algorithms. [ABSTRACT FROM AUTHOR]

Regarded as a promising technology, proton exchange membrane fuel cell (PEMFC) are not far from a large-scale deployment. However, some improvements are still needed to extend the lifetime of these systems. The discipline of PHM (Prognostic and health management) seems like a great solution to help against this problem. The objective is to predict the evolution of the behavior of a system using algorithms to estimate in advance when a fault occurs. This knowledge of the default before its occurrence allows to anticipate a decision, often by using a fault-tolerant control. Different methodologies exist to make a prognostic algorithm: model based, data based or a hybridization between these two previous methodologies. This paper will focus on the data based prognosis, mainly due to the fact that all of the phenomena involved in the degradation of a PEMFC are not yet fully known, thus not yet modeled. The first innovation of this paper concern the use of a new neural network paradigm, the Echo State Network, which is a part of Reservoir Computing methods. This new paradigm gives very interesting results, with a mean average percentage error less than 5% in our study case. The other contribution is the definition of a filtering method, regarding to the test bench, by evaluating the Hurst exponent of the signal filtered by wavelet. [ABSTRACT FROM AUTHOR]

This survey makes an overview of the most recent applications on the neural networks for the computer-aided medical diagnosis (CAMD) over the past decade. CAMD can facilitate the automation of decision making, extraction and visualization of complex characteristics for clinical diagnosis purposes. Over the past decade, neural networks have attained considerable research interest and are widely employed to complex CAMD systems in diverse clinical application domains, such as detecting diseases, classification of diseases, testing the compatibility of new drugs, etc. Overall, this paper reviews the state-of-the-art of neural networks for CAMD. It helps the readers understand the topic of neural networks for CAMD by summarizing the findings addressed in recent academic papers as well as presenting a few open issues of developing the research on this topic. [ABSTRACT FROM AUTHOR]

This paper proposes a change detection algorithm based on Fully Convolutional Siamese Networks for optical aerial images, which is trained by using an improved Contrastive Loss-Focal Contrastive Loss (FCL). The proposed framework equipped with contrastive loss can extract features directly from image pairs and measure changes by using a distance metric. In other words, this method encourages reducing intra-class variance and enlarging inter-class difference, so that the binarized change map can be obtained by a simple threshold. In change detection task, a critical problem is how to overcome example imbalance (i.e. unchanged examples are much more than changed examples). To address this challenge, a novel focal contrastive loss is proposed to further improve the performance of the model. FCL can reduce the impact of example imbalance and make the model focus learning on hard examples. Extensive experiments demonstrate that the proposed approach is more abstract as well as robust. Compared with other baseline methods, the presented method achieves better results on SAZDA, TISZADOB, CDD, and WHU-CD data set. It achieves state-of-the-art performance in terms of the F1 measure. [ABSTRACT FROM AUTHOR]

Recently, tracking models based on bounding box regression (such as region proposal networks), built on the Siamese network, have attracted much attention. Despite their promising performance, these trackers are less effective in perceiving the target information in the following two aspects. First, existing regression models cannot take a global view of a large-scale target since the effective receptive field of a neuron is too small to cover the target with a large scale. Second, the neurons with a fixed receptive field (RF) size in these models cannot adapt to the scale and aspect ratio changes of the target. In this paper, we propose an adaptive ensemble perception tracking framework to address these issues. Specifically, we first construct a per-pixel prediction model, which predicts the target state at each pixel of the correlated feature. On top of the per-pixel prediction model, we then develop a confidence-guided ensemble prediction mechanism. The ensemble mechanism adaptively fuses the predictions of multiple pixels with the guidance of confidence maps, which enlarges the perception range and enhances the adaptive perception ability at the object-level. In addition, we introduce a receptive field adaption model to enhance the adaptive perception ability at the neuron-level, which adjusts the RF by adaptively integrating the features with different RFs. Extensive experimental results on the VOT2018, VOT2016, UAV123, LaSOT, and TC128 datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods in terms of accuracy and speed. [ABSTRACT FROM AUTHOR]

• We propose a DSNnet optimization model with non-convex equality constraints for unsupervised representation learning. • We design a neural network based algorithm to solve the proposed DSNnet model. • We introduce a novel similarity measurement between input data and learned features as a regularization term of DSNnet. Deep Semi-NMF (DSN), which learns hierarchical representations by stacking multiple layers Semi-NMF, shows competitive performance in unsupervised data analysis. However, the features learned from DSN always lack of representativity and discriminativity. In this paper, we build a novel Deep Semi-NMF network (DSNnet) to address the issues of DSN. Specifically, DSNnet contains multiple fully-connected layers, in which the activation function of each layer adopts Smoothly Clipped Absolute Deviation (SCAD). The non-negative hidden features are computed forwardly, while the network parameters are updated by the stochastic gradient descent method. Moreover, to enhance the discriminativity of features, we suggest simultaneously minimizing the reconstruction error of input and output, and maximizing the similarity between input and learned features. The proposed similarity measurement, which consists of global geometric similarity and local pointwise similarity, encourages the compactness between similar points and separateness between dissimilar points in the feature space, and is beneficial to preserve intrinsic information of original data. Extensive experiments conducted on several datasets illustrate the superiority of the proposed approach in comparison with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The paper presents an approach to machine learning involving the use of a hybrid method in Neural ODE. The authors consider a way of the Neural ODE application with an embedded hybrid method for intelligent manipulator control in a non-deterministic environment. To reduce computational resources, the number of layers of the neural network using ODE is reduced, the solution of which is carried out by a hybrid transformation method. The hybrid method includes normalizing the system, linear transformation, and polynomial transformation. Using the hybrid method in Neural ODE can increase the learning and computation speed. The transformation method has high accuracy with low computational complexity of the algorithm. As a result of applying the hybrid method, the original nonlinear system is transformed to a simpler form. To solve the simplified transformed system, the scheme of the numerical Runge-Kutta method of the third order with an adaptive step is used. The results of the computational experiment show an increase in the speed and accuracy of the calculation. The presented approach to implementing the hybrid method in Neural ODE allows faster training of the neural network of the world model on limited data obtained from the real environment. After training on the data generated by the model of the world, a robotic arm always successfully reaches the object during subsequent interaction with the real environment. This solves the problem of the limited ability of the agent to interact when learning with the real environment in robotic systems. [ABSTRACT FROM AUTHOR]

In this paper, we propose a computationally efficient Correlational Neural Network (CorrNN) learning model and an automated diagnosis system for detecting Chronic Kidney Disease (CKD). A Support Vector Machine (SVM) classifier is integrated with the CorrNN model for improving the prediction accuracy. The proposed hybrid model is trained and tested with a novel sensing module. We have monitored the concentration of urea in the saliva sample to detect the disease. Experiments are carried out to test the model with real-time samples and to compare its performance with conventional Convolutional Neural Network (CNN) and other traditional data classification methods. The proposed method outperforms the conventional methods in terms of computational speed and prediction accuracy. The CorrNN-SVM combined network achieved a prediction accuracy of 98.67%. The experimental evaluations show a reduction in overall computation time of about 9.85% compared to the conventional CNN algorithm. The use of the SVM classifier has improved the capability of the network to make predictions more accurately. The proposed framework substantially advances the current methodology, and it provides more precise results compared to other data classification methods. • Explores the use of salivary urea as a biomarker to detect CKD. • An efficient CKD detection module is implemented for the detection. • A new correlational neural network learning model is introduced. • Performance of the network is compared with traditional learning techniques. [ABSTRACT FROM AUTHOR]

In this study, Artificial Neural Networks (ANN) were used to model parameters of scheduling of reconfigurable embedded systems containing resource constraints for applications running in real-time. The main goal is to implement a neural network based approach for real-time scheduling in order to handle real-time constraints in execution scenarios. Many techniques have been proposed for both the planning of tasks and reducing energy consumption. This paper presents a new hybrid contribution that handles the real-time scheduling of embedded systems by keeping energy consumption at a low power depending on the combination of Dynamic Voltage Scaling (DVS) and the energy Priority Earlier Deadline First (PEDF) algorithm. Indeed, in our original proposed approach, an other combination of DVS and time feedback can be used to scale the frequency by dynamically adjusting the operating voltage. The originality of our algorithm appears by allowing medium priority tasks to be executed more quickly before their deadline while decreasing their ability to be send again to the waiting list in order to ensure the execution of a task with the lowest voltage possible. [ABSTRACT FROM AUTHOR]

Temperature variations, climatic changes or human interventions are the main cause buildings and streets deteriorate over time. Since manual verification of such structures completely depends on a specialist's knowledge and experience it is often time-consuming, costly, and dangerous, therefore an automated approach would be very beneficial. Automated devices using computer vision that detect anomalies in targeted structures have the potential of creating a better and safer environment, periodically checking for possible faults and improving worker safety. The system presented in this paper is an Android application with the purpose of field use, the goal being that either the worker could use it to detect potential hazards or an autonomous system might use it in inhospitable scenarios. The model created contains two modules, the U-Net algorithm, and the Android application; the novelty of the approach comes from offline use and accuracy, optimizations have been made in order for a reasonably powerful device to run the model and classify in real-time without the use of servers or mobile data. Adapting the neural network model to the mobile application was a challenge for our team, but in the end, the mobile application works as we intended with good results. [ABSTRACT FROM AUTHOR]