Search

This paper introduces a diagnostic model that effectively diagnoses in fourteen different stages, by fusing functional magnetic resonance imaging (fMRI) and structural MRI (sMRI) information. Georgios Theodoridis and Athanasios Tsadiras from the Aristotle University of Thessaloniki, Greece, have authored the seventh paper which is entitled "Applying machine learning techniques to predict and explain subscriber churn of an online drug information platform." Machine learning (ML) and more specifically deep learning (DL) algorithms are considered among the most paramount technologies of both artificial intelligence (AI) and 4 SP th sp industrial revolution. This paper provides an in-depth comparison of various machine learning (ML) techniques and advanced preprocessing methods, in an effort to successfully perform online subscriber churn prediction. [Extracted from the article]

This study attempts to determinate color changes based on time in inks applied on the surface of wood-free uncoated paper with offset printing during drying. This study consists of two main cases: (1) Experimental analysis: By preparing a test page according to the 12647-2 principle with an offset printing system, test prints were applied to 120 g/m wood-free uncoated paper using an ECI 2002 CMYK test chart. Each press was measured being subject to process every 15 min in the first 2 h, then hour by hour between 2 and 12 h, then 4-4 h between 12 and 24 h, and then 6-6 h between 24 and 48 h. CIELAB and reflectance values between 380 and 720 nm of the target, 1,485 colors of the test chart were obtained. To see the drying and color changes of the ink on paper, changes were determined by printing on the paper and applying artificial neural network (ANN) to spectrophotometer data at the stated time intervals. (2) Empirical analysis: The use of the ANN has been proposed as numerical approach to get of empirical equations of color changes in inks applied on the surface of wood-free uncoated paper with offset printing during drying. Based on the outputs of the study, ANN model can be used to estimate the effects of digital proofing systems used in color management on print quality with high confidence with the use of the acquired equations without experimental study. In the study, as colors are defined in terms of wave length, in case, all wave lengths are taken into consideration, certain wave length changes have been taken into consideration. [ABSTRACT FROM AUTHOR]

The model integrates artificial intelligence (AI) and big data analytics, utilizing IoMT devices for data acquisition and Hadoop ecosystem for managing big data. The field of medical diagnosis is currently undergoing a remarkable transformation with the emergence of artificial intelligence (AI) techniques, particularly deep learning and big data analytics. By harnessing the power of deep learning and big data analytics, AI-based e-diagnosis has the potential to revolutionize healthcare delivery. [Extracted from the article]

This cannot be achieved only through conventional Machine Learning (ML) frameworks and technologies. The technological advancement in recent years has seen a great shift leading to a greater magnitude of data storage, communication and subsequent processing with reduced size and cost of the systems. The thirteen paper "A Novel Emergency Situation Awareness Machine Learning Approach to Assess Flood Disaster Risk based on Chinese Weibo" is authored by Bai Hua, Yu Hualong, Yu Guang and Huang Xing. [Extracted from the article]

With the ongoing integration of information technology and industrialization, strategic emerging industries are becoming an increasingly important force in guiding future economic and social development. As one of the strategic emerging industries' development priorities and a replacement for scarce labor resources, industrial robots will be widely used in labor-intensive industries. It is a contentious topic how to evaluate and improve robot knowledge education. There are modular features introduced in this paper, which builds a modular network for the evaluation of robot knowledge education quality and enhances the cognitive computing ability of artificial neural networks and their ability to process complex information. A modular neural network-based model of feature combination robot knowledge education quality evaluation is developed based on the three aspects of module division method, subnet structure selection, and feature combination output. The following are some of the paper's most important contributions: K-OD algorithm of density clustering optimized by K-means is proposed. Because of its high level of modularized partition simulating, this method has an excellent clustering effect, and it identifies the core points, boundary points, as well as outliers. Using K-OD algorithm, the calculation of density radius and threshold is optimized by using density clustering, which reduces the overall computational complexity. Find out how SOM neural networks learn from competition. SOM network's competition layer neuron weights are prone to falling into local optimal solutions, so an SASOM neural network with weight adjustment simulated by an annealing algorithm is proposed to address this issue. It is more accurate in terms of prediction and error, and it is better at identifying sample attribute features. This work builds a modular neural network for evaluating robot knowledge education quality using K-OD clustering algorithm and SASOM neural network, which introduces the simulated annealing mechanism. [ABSTRACT FROM AUTHOR]

Mental stress is a common problem that affects individuals all over the world. Stress reduces human functionality during routine work and may lead to severe health defects. Early detection of stress is important for preventing diseases and other negative health-related consequences of stress. Several neuroimaging techniques have been utilized to assess mental stress, however, due to its ease of use, robustness, and non-invasiveness, electroencephalography (EEG) is commonly used. This paper aims to fill a knowledge gap by reviewing the different EEG-related deep learning algorithms with a focus on Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) for the evaluation of mental stress. The review focuses on data representation, individual deep neural network model architectures, hybrid models, and results amongst others. The contributions of the paper address important issues such as data representation and model architectures. Out of all reviewed papers, 67% used CNN, 9% LSTM, and 24% hybrid models. Based on the reviewed literature, we found that dataset size and different representations contributed to the performance of the proposed networks. Raw EEG data produced classification accuracy around 62% while using spectral and topographical representation produced up to 88%. Nevertheless, the roles of generalizability across different deep learning models and individual differences remain key areas of inquiry. The review encourages the exploration of innovative avenues, such as EEG data image representations concurrently with graph convolutional neural networks (GCN), to mitigate the impact of inter-subject variability. This novel approach not only allows us to harmonize structural nuances within the data but also facilitates the integration of temporal dynamics, thereby enabling a more comprehensive assessment of mental stress levels. [ABSTRACT FROM AUTHOR]

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

Promoting the development of enterprises is a common task of all countries in the world, and the government has always taken promoting enterprise development as a long-term strategy. With the development for market, as an integral part of the social market economy, enterprises have made great contributions to the rapid of national economy. The enterprises are increasing, but the market competition is becoming increasingly fierce, and the weaknesses of enterprises such as limited scale, lax management and difficult financing are constantly highlighted. The appearance of these problems makes enterprises encounter many bottleneck problems in the process of development. Innovation, as the inexhaustible power of enterprise development, plays a significant role in enterprise growth, it is the key to solving the bottleneck problem of enterprise development. If an enterprise wants to achieve considerable development, it must innovate and enhance its competitiveness through innovation. In this context, how to evaluate enterprise innovation has become an important work. This work proposes an IPSO-ATT-MSCNN network via PSO from swarm optimization algorithm and artificial neural network to evaluate enterprise innovation. First, this work designs a multi-scale convolutional neural network (ATT-MSNN) via attention mechanism. This method uses multi-scale convolution to extract features of different scales, which improves the richness of features. This adds attention mechanisms to enhance useful features and reduce the impact of unwanted features such as noise. Second, in view of the performance degradation caused by the random initialization, this paper uses improved PSO algorithm to optimize the initial parameters. Third, this work proposes a series of strategies for promoting enterprise innovation. Finally, this work carried out a comprehensive and systematic experiment for the designed method, and the experiment verified the superiority of this method. [ABSTRACT FROM AUTHOR]

Hand gestures are becoming an important part of the communication method between humans and machines in the era of fast-paced urbanization. This paper introduces a new standard dataset for hand gesture recognition, Static HAnd PosturE (SHAPE), with adequate side, variation, and practicality. Compared with the previous datasets, our dataset has more classes, subjects, or scenes than other datasets. In addition, the SHAPE dataset is also one of the first datasets to focus on Asian subjects with Asian hand gestures. The SHAPE dataset contains more than 34,000 images collected from 20 distinct subjects with different clothes and backgrounds. A recognition architecture is also presented to investigate the proposed dataset. The architecture consists of two phases that are the hand detection phase for preprocessing and the classification phase by customized state-of-the-art deep neural network models. This paper investigates not only the high accuracy, but also the lightweight hand gesture recognition models that are suitable for resource-constrained devices such as portable edge devices. The promising application of this study is to create a human–machine interface that solves the problem of insufficient space for a keyboard or a mouse in small devices. Our experiments showed that the proposed architecture could obtain high accuracy with the self-built dataset. Details of our dataset can be seen online at https://users.soict.hust.edu.vn/linhdt/dataset/ [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurological disease that has been reported to have affected most people worldwide. Recent research pointed out that about 90% of PD patients possess voice disorders. Motivated by this fact, many researchers proposed methods based on multiple types of speech data for PD prediction. However, these methods either face the problem of low rate of accuracy or lack generalization. To develop an approach that will be free of these issues, in this paper we propose a novel ensemble approach. These paper contributions are two folds. First, investigating feature selection integration with deep neural network (DNN) and validating its effectiveness by comparing its performance with conventional DNN and other similar integrated systems. Second, development of a novel ensemble model namely EOFSC (Ensemble model with Optimal Features and Sample Dependant Base Classifiers) that exploits the findings of recently published studies. Recent research pointed out that for different types of voice data, different optimal models are obtained which are sensitive to different types of samples and subsets of features. In this paper, we further consolidate the findings by utilizing the proposed integrated system and propose the development of EOFSC. For multiple types of vowel phonations, multiple base classifiers are obtained which are sensitive to different subsets of features. These features and sample-dependent base classifiers are integrated, and the proposed EOFSC model is constructed. To evaluate the final prediction of the EOFSC model, the majority voting methodology is adopted. Experimental results point out that feature selection integration with neural networks improves the performance of conventional neural networks. Additionally, feature selection integration with DNN outperforms feature selection integration with conventional machine learning models. Finally, the newly developed ensemble model is observed to improve PD detection accuracy by 6.5%. [ABSTRACT FROM AUTHOR]

IoT is an emerging technology that is rapidly gaining traction throughout the world. With the incredible power and capacity of IoT, anyone may connect to any network or service at any time, from anywhere. IoT-enabled gadgets have transformed the medical industry by granting unprecedented powers such as remote patient monitoring and self-monitoring. Accurate electrocardiogram (ECG) interpretation is critical in the clinical ECG process since it is most often connected with a condition that might create serious difficulties in the body. Cardiologists and medical practitioners frequently utilize ECG to evaluate heart health. The human heart has an electric transmission system that creates regular electrical signals unintentionally and transmits them to the whole heart. Many individuals die as a result of heart disease all around the world. The doctor will be able to provide exceptional treatment to the patients, and the patients will be able to monitor their own health. This research offers an IoT-based ECG monitoring system that uses a heart rate sensor to create data and an intelligent hybrid classification algorithm to classify the data. ECG monitoring has become a widely used method for detecting cardiac problems. The following are the primary contributions of this paper: To begin, this paper introduces WISE (wearable IoT cloud-based health monitoring system), a unique system for real-time personal health monitoring. In order to offer real-time health monitoring, WISE uses the BASN (body area sensor network) infrastructure. Data from the BASN are instantly transferred to the cloud in WISE, and a lightweight wearable LCD may be incorporated to provide rapid access to real-time data. This hybrid model can manage with the problem of class imbalance in the ECG dataset, which will aid in the development of an IoT-based smart and accurate healthcare system. This research uses ADNN, which correctly predicts an abnormal ECG 98.1% of the time. The suggested hybrid model's results are compared to those of other classification models to determine its accuracy and suitability. [ABSTRACT FROM AUTHOR]

This paper analyzes the inherent relationship between convolutional neural networks and sparse representation and proposes an improved convolutional neural network model for image synthesis in response to problems with current methods. In the testing phase, the calculation of the sparse coefficients involves the solution of complex optimization problems, which greatly reduce the operating efficiency, inspired by the successful application of convolutional neural networks in the field of image reconstruction. Compared with the traditional image portrait synthesis method, this model not only has an end-to-end closed form but also does not need to solve complex optimization problems in the synthesis stage. The synthesis experiment on an image dataset shows that this method not only improves the synthesis effect but also improves the efficiency of the traditional method by one to two orders of magnitude, demonstrating its potential application value. Blocking processing is a common method for sparse domain image modeling. It improves the computational efficiency but also decreases the global structure of the image, which is difficult to compensate for through the aggregation and overlap of image blocks. In response to this problem, this paper proposes a low-rank image inpainting method based on a Gaussian mixture model. This method embeds the local statistical characteristics of image blocks into the kernel norm model and not only uses the Gaussian mixture model to maintain the local details of the image but also describes the global low-rank structure of the image through the kernel norm, thus restoring a class of image data with a potential low-rank structure and theoretically revealing the structured sparse nature of the Gaussian mixture model. This paper optimizes the strategy based on random hidden neuron nodes and proposes a dropout anti-overfitting strategy based on sparsity. The experiments show that this strategy can effectively improve the convergence speed while ensuring good performance and can effectively prevent overfitting. [ABSTRACT FROM AUTHOR]

In order to improve the effectiveness of signal processing, according to the actual needs of signal processing and the current problems in signal processing, this paper introduces an improved LSTM recurrent neural network algorithm to construct the signal processing algorithm. Moreover, this paper sets up the functional structure of this paper based on the neural network model structure, and builds an intelligent analysis system for signal processing tasks based on the LSTM recurrent neural network algorithm. In addition, this paper analyzes the system algorithm flow in detail, and combines experimental research to carry out the effectiveness of the system constructed in this paper, and conducts quantitative analysis from two aspects of signal threshold prediction and signal processing effect. Finally, this paper conducts experimental results research with the support of mathematical statistics methods. From the research point of view, it can be known that the system constructed in this paper has good signal processing functions. [ABSTRACT FROM AUTHOR]

A novel investigation of the bearing capacity of ring footings embedded in undrained anisotropic clays using a new hybrid soft computation technique that cooperates between finite element limit analysis (FELA) and artificial neural networks (ANNs) is presented in this paper. The undrained shear strength of clays is considered to be anisotropic and linearly increased with depth. The anisotropic undrained shear strength (AUS) model is employed to demonstrate the anisotropic behaviour of the undrained clays. The FLEA solutions of this problem based on lower bound (LB) and upper bound (UB) solutions are presented. The variations of bearing capacity factor (N) and the failure patterns of ring footings are examined by considering the changes in the geometric ratio of the internal radius and external radius (ri/ro), the embedment ratio (D/ro), the rates of increase of undrained shear with depth (ρro/suTC0), and the ratio of anisotropic (re). The results of the paper are presented in the simple dimensionless design charts and tables that show the relationships between N and all investigated parameters which will be beneficial to practitioners. Furthermore, the application of artificial neural networks (ANNs) is adopted to do sensitivity analysis and build an empirical equation for the complex relationship between the input variables and output bearing capacity factor. As the results, the radius ratio ri/ro is the most important variable on bearing capacity factor and the lower importance parameters are D/ro, ρro/suTC0, and re with relative importance 37.01, 30.37; 21.59; 11.03%, respectively. The proposed empirical equation is also proved to be an efficient method as evidenced by the high agreement between its predicted values and those from FELA with R2 of 99.95%. [ABSTRACT FROM AUTHOR]

Various applications of control charts in the field of health-care monitoring and surveillance can be found in the literature. As one of the major categories, monitoring binary outcomes of cardiac surgeries with the aim of logistic regression model for the patients' death probability has been extended by different researchers. For this aim, statistical control charts, such as cumulative sum (CUSUM) chart, are applied as a risk-adjusted method to monitoring patients' mortality rate. However, employing machine learning techniques such as artificial neural network (ANN) has not been paid attention. So, this paper proposes a novel ANN-based control chart with a heuristic training approach to monitor binary surgical outcomes by control charts. Performance of the proposed approach is investigated and compared with existing studies, based on the average run lengths (ARL) criterion and the results demonstrated a superior performance of the proposed approach. Nevertheless, to demonstrate the application of the proposed approach, some real-life applications are also provided in this paper. Furthermore, robustness of the proposed method is investigated by considering Beta distribution for the death rate in addition to the logistic model. [ABSTRACT FROM AUTHOR]

Cross-domain few-shot classification aims to recognize images in the new categories and domains that only contain few but unacquainted images. Considering the problems of fine-grained recognition in cross-domain few-shot classification including marginal overall-discrepancy in feature distribution and obvious fine-grained difference in dataset, this paper proposes a simple and effective attentive fine-grained recognition (AFGR) model. Specifically, the residual attention module is stacked into the feature encoder based on the residual network, which can linearly enhance different semantic feature information to help the metric function better locate the fine-grained feature information of the image. In addition, a bilinear metric function structure is proposed to learn and fuse different fine-grained image features, respectively, since the weights of bilinear measurement functions are not shared. Eventually, the final classification result is obtained by merging the recognition of bilinear metric function through posterior probability multiplication. In this paper, ablation experiments and comparative experiments are carried out with the typical few-shot dataset mini-ImageNet as the training domain and the CUB, Cars, Places and Plantae datasets as the test domain. The experimental results demonstrate that the proposed AFGR method is effective, with the highest increase in recognition accuracy 13.82% and 7.95% compared with the latest results under the experimental settings of 5-way1-shot and 5-way5-shot, respectively, which also proves the problems of fine-grained recognition in cross-domain small sample classification. [ABSTRACT FROM AUTHOR]

English expression, language characteristics and usage norms are quite special, which is quite different from Chinese. This has special requirements for auxiliary teaching tools that use computer technology for English text processing. Based on neural network algorithm, this paper combines the actual needs of English grammar error correction to construct an English grammar error correction model based on neural network. In data processing, after feature selection, logistic regression model is used to analyze the influence of different features on article error correction. The article error correction incorporating word vector features mainly explores how to effectively express the features in English grammar error correction. In addition, this paper proposes two methods to optimize the feature representation in article error correction. One is to directly use the word vector corresponding to the word as a feature, replacing the original One-hot encoding, and the other uses a clustering method to compress the article features. Finally, this paper designs experiments to study the performance of the model constructed in this paper. The results obtained show that the model constructed in this paper has a certain effect. [ABSTRACT FROM AUTHOR]

In order to overcome the shortcomings of the current English network learning system, based on the neural network algorithm, this paper constructs an intelligent English network learning system based on the improved algorithm. Moreover, by analyzing the coupling between recurrent neural networks by contrast methods, this paper infers the coupling between recurrent neural networks. Moreover, this paper studies the continuous attractors of the autoencoder neural network and studies the continuous attractors of different types of autoencoder models. On this basis, this paper expands the existing model, adds the module of the interaction between the external input and the visible layer and studies the conditions required for the continuous attractor of the autoencoder model. In addition, on the basis of actual needs, this paper constructs the basic structure of the model and integrates it into the improved algorithm proposed in this paper to realize English online intelligent learning. Finally, this paper designs experiments to analyze the practical effects of this model and analyzes the experimental results through mathematical statistics. The research results show that the English network learning system constructed in this paper is effective. [ABSTRACT FROM AUTHOR]

ExSeisDat is designed using standard message passing interface (MPI) library for seismic data processing on high-performance super-computing clusters. These clusters are generally designed for efficient execution of complex tasks including large size IO. The IO performance degradation issues arise when multiple processes try accessing data from parallel networked storage. These complications are caused by restrictive protocols running by a parallel file system (PFS) controlling the disks and due to less advancement in storage hardware itself as well. This requires and leads to the tuning of specific configuration parameters to optimize the IO performance, commonly not considered by users focused on writing parallel application. Despite its consideration, the changes in configuration parameters are required from case to case. It adds up to further degradation in IO performance for a large SEG-Y format seismic data file scaling to petabytes. The SEG-Y IO and file sorting operations are the two of the main features of ExSeisDat. This research paper proposes technique to optimize these SEG-Y operations based on artificial neural networks (ANNs). The optimization involves auto-tuning of the related configuration parameters, using IO bandwidth prediction by the trained ANN models through machine learning (ML) process. Furthermore, we discuss the impact on prediction accuracy and statistical analysis of auto-tuning bandwidth results, by the variation in hidden layers nodes configuration of the ANNs. The results have shown the overall improvement in bandwidth performance up to 108.8% and 237.4% in the combined SEG-Y IO and file sorting operations test cases, respectively. Therefore, this paper has demonstrated the significant gain in SEG-Y seismic data bandwidth performance by auto-tuning the parameters settings on runtime by using an ML approach. [ABSTRACT FROM AUTHOR]

Oxygen content in the flue gas system of power plants is an essential factor affecting boiler efficiency. Accurate oxygen content measurement is vital in evaluating boiler combustion efficiency. The device measuring oxygen content in flue gases at an oil refinery uses a Zirconia oxygen analyzer. This sensor utilization without sensor redundancy makes the oxygen content measurement conducted manually. Workers' manual measurement is risky because it is a high-risk work area. In addition, the oxygen content in flue gas also indicates boiler combustion efficiency and the amount of other harmful gases produced by the boiler. This paper proposes a soft sensor using artificial neural networks (ANN) and extreme gradient boosting (XGBoost) to predict oxygen content. The dataset used is collected from the historical data of the distributed control system of an oil refinery system boiler. The experimental results show that the one hidden layer ANN model achieves an MAE of 0.0715 and RMSE of 0.0935, while the XGBoost model with hyperparameter tuning and seven features achieves an MAE of 0.0452 and RMSE of 0.0642. The results suggest that the XGBoost model with hyperparameter tuning and seven features outperforms the one hidden layer ANN model. The use of the seven features of the XGBoost model is the result of optimization between computational complexity and system performance. [ABSTRACT FROM AUTHOR]

As a main electronic material, X-ray circuits are widely used in various electronic devices, and their quality has an important impact on the overall quality of electronic products. In the process of mass production of circuit boards, due to the large number of layers, tight lines and some harmful external factors, circuit board quality may be problematic. Detecting circuit board defects are important for improving the reliability of electronic products. This paper introduces deep learning and artificial intelligence technology to conduct research on the automatic detection of X-ray circuit board defects. The study used a defect detection system to study X-ray circuit boards as a detection object and obtained the structure, lighting system and composition of the detection system. The working principle of the detection system is explained, and the image is preprocessed. Testing the processing performance of the PCB defect detection system, when the number of pixels is 6526, 7028, 7530 and 8032, the time consumption ratios between the proposed detection system and image processing on a traditional PC are 35.17%, 35.4%, 35% and 35.28%, respectively. The experimental results make a certain contribution to the future artificial intelligence X-ray PCB defect automatic diagnosis algorithm. [ABSTRACT FROM AUTHOR]

Combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) produces a powerful architecture for video classification problems as spatial–temporal information can be processed simultaneously and effectively. Using transfer learning, this paper presents a comparative study to investigate how temporal information can be utilized to improve the performance of video classification when CNNs and RNNs are combined in various architectures. To enhance the performance of the identified architecture for effective combination of CNN and RNN, a novel action template-based keyframe extraction method is proposed by identifying the informative region of each frame and selecting keyframes based on the similarity between those regions. Extensive experiments on KTH and UCF-101 datasets with ConvLSTM-based video classifiers have been conducted. Experimental results are evaluated using one-way analysis of variance, which reveals the effectiveness of the proposed keyframe extraction method in the sense that it can significantly improve video classification accuracy. [ABSTRACT FROM AUTHOR]

The radiotelephony communication is a voice communication mode between air traffic service unit and aircraft currently. The control instruction is a kind of unstructured data, so that the automatic systems cannot use understand its semantic. If control instruction is regarded as a sort of special "natural language," methods such as syntax analysis and sematic analysis can be adopted to generate the structured instruction. The correct recognition of the language must be important for the control instruction. However, the control instruction in Chinese is different from the general use of Chinese language in form, resulting in prepositions becoming important for semantic analysis. This paper proposes a deep neural network-based Chinese language control construction algorithm for the trajectory prediction. In particular, analysis of sematic characteristics of control instruction is realized by using cognitive linguistics theory and construction grammar theory. The control instruction is then designed by the semantic ontology. Based on the deep neural networks by considering the word sequence of instruction as the inputs. The test results have demonstrated the effectiveness of the proposed algorithm with a developed entity extracting model. (The results are quantified using the BiLSTM-LAN-CRF in detail.) [ABSTRACT FROM AUTHOR]

The prediction of stock prices has been a major area of interest in recent years, and many methods have been applied in this field. In this paper, to determine the method to predict stock prices, a 25-7-5 three-layer BP neural network based on a time series is constructed considering the daily opening price, highest price, lowest price, closing price and trading volume. A network based on a time series can reflect the trend of stock prices in a period more comprehensively. There are some disadvantages of the traditional BP neural network training algorithm to predict stock prices with large quantities of sample data and large parameters to be estimated in neural networks such as slow training speed and low accuracy. In this paper, the LM-BP algorithm is proposed to overcome these disadvantages. The network structure of stock price prediction based on the LM-BP neural network is given in this paper. Currently, there is no reliable theory to determine the overfitting critical point. In this paper, the repeated division and count in intervals (RDCI) method is proposed for the lack of research in this area. In this paper, the curves of MRE2-MRE1 are drawn, and the fitting accuracy corresponding to the best prediction accuracy of the BP neural network is reasonably estimated based on several independent repeated tests. The experiments indicate that the prediction of stock prices based on the LM-BP neural network and the estimation of the overfitting point by RDCI in this paper achieves better results than existing methods. [ABSTRACT FROM AUTHOR]

Credit rating is an important part of bank credit risk management. Since the traditional radial basis function network model is more susceptible to outliers and cannot effectively process the classification data, it is very sensitive in terms of the initial center and class width of the selected model. This paper mainly studies the application of the radial basis function neural network model combined with the optimal segmentation algorithm in the personal loan credit rating model of banks or other financial institutions. The optimal segmentation algorithm is improved and applied to the training of RBF neural network parameters in this paper to increase the center and width of the class, and the center and width of the RBF network model are further improved. Finally, the adaptive selection of the number of hidden nodes is realized by using the differential objective function of the class to adjust dynamically the structure of the radial basis function network model, which is used to establish the credit rating model. The experimental results show that the improved model has higher precision when dealing with non-numeric data, and the robustness of the improved model has been improved. [ABSTRACT FROM AUTHOR]

Due to the characteristics of time-varying traffic and nonlinearity, the short-term traffic flow data are difficult to predict accurately. The purpose of this paper is to improve the short-term traffic flow prediction accuracy through the proposed improved wavelet neural network prediction model and provide basic data and decision support for the intelligent traffic management system. In view of the extremely strong nonlinear processing power, self-organization, self-adaptation and learning ability of wavelet neural network (WNN), this paper uses it as the basic prediction model and uses the particle swarm optimization algorithm for the slow convergence rate and local optimal problem of WNN prediction algorithm. With the advantages of fast convergence, high robustness and strong global search ability, an improved particle swarm optimization algorithm is proposed to optimize the wavelet neural network prediction model. The improved wavelet neural network is used to predict short-term traffic flow. The experimental results show that the proposed algorithm is more efficient than the WNN and PSO–WNN algorithms alone. The prediction results are more stable and more accurate. Compared with the traditional wavelet neural network, the error is reduced by 14.994%. [ABSTRACT FROM AUTHOR]

The monitoring of physical activities and recognition of motion disorders belong to important diagnostical tools in neurology and rehabilitation. The goal of the present paper is in the contribution to this topic by (1) analysis of accelerometric signals recorded by wearable sensors located at specific body positions and by (2) implementation of deep learning methods to classify signal features. This paper uses the general methodology to analysis of accelerometric signals acquired during cycling at different routes followed by the global positioning system. The experimental dataset includes 850 observations that were recorded by a mobile device in the spine area (L3 verterbra) for cycling routes with the different slope. The proposed methodology includes the use of deep learning convolutional neural networks with five layers applied to signal values transformed into the frequency domain without specification of any signal features. The accuracy of discrimination between different motion patterns for the uphill and downhill cycling and recognition of 4 classes associated with different route slopes was 96.6% with the loss criterion of 0.275 for sigmoidal activation functions. These results were compared with those evaluated for selected sets of features estimated for each observation and classified by the support vector machine, Bayesian methods, and the two-layer neural network. The best cross-validation error of 0.361 was achieved for the two-layer neural network model with the sigmoidal and softmax transfer functions. Our methodology suggests that deep learning neural networks are efficient in the assessment of motion activities for automated data processing and have a wide range of applications, including rehabilitation, early diagnosis of neurological problems, and possible use in engineering as well. [ABSTRACT FROM AUTHOR]

The risk of death incurred by breast cancer is rising exponentially, especially among women. This made the early breast cancer detection a crucial problem. In this paper, we propose a computer-aided diagnosis (CAD) system, called CADNet157, for mammography breast cancer based on transfer learning and fine-tuning of well-known deep learning models. Firstly, we applied hand-crafted features-based learning model using four extractors (local binary pattern, gray-level co-occurrence matrix, and Gabor) with four selected machine learning classifiers (K-nearest neighbors, support vector machine, random forests, and artificial neural networks). Then, we performed some modifications on the Basic CNN model and fine-tuned three pre-trained deep learning models: VGGNet16, InceptionResNetV2, and ResNet152. Finally, we conducted a set of experiments using two benchmark datasets: Digital Database for Screening Mammography (DDSM) and INbreast. The results of the conducted experiments showed that for the hand-crafted features based CAD system, we achieved an area under the ROC curve (AUC) of 95.28% for DDSM using random forest and 98.10% for INbreast using support vector machine with the histogram of oriented gradients extractor. On the other hand, CADNet157 model (i.e., fine-tuned ResNet152) was the best performing deep model with an AUC of 98.90% (sensitivity: 97.72%, specificity: 100%), and 98.10% (sensitivity: 100%, specificity: 96.15%) for, respectively, DDSM and INbreast. The CADNet157 model overcomes the limitations of traditional CAD systems by providing an early detection of breast cancer and reducing the risk of false diagnosis. [ABSTRACT FROM AUTHOR]

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

The adversary makes malicious samples capable of triggering erroneous judgments in deep learning models by introducing imperceptible perturbations to the original benign texts. These malicious samples are referred to as adversarial texts. The exploration of adversarial text generation methods not only facilitates our understanding of the robustness of mainstream deep neural networks against such adversarial attacks but also aids in developing appropriate defensive strategies. Nevertheless, the mainstream research on textual adversarial attacks has mainly focused on attack effectiveness, overlooking the associated attack cost. For real-world attacks, considerations such as the time cost, material cost, manpower cost, and various constraints are also crucial. In this paper, we propose a low-cost adversarial text generation method based on the universal strategy in the black-box attack scenario, Universal Chinese Text Tricker (UCTT), for tendency classification on Chinese texts. UCTT is both text-independent and model-independent, which markedly reduces its attack cost. Instead of crafting adversarial texts for a specific text, UCTT generates universal perturbations based on a universal word substitution list, which is applicable to any data in tendency classification datasets. Given a perturbation rate, we can use the word list to craft adversarial texts by simple substitutions without accessing the target model. In the framework of adversarial text generation based on word importance, UCTT utilizes count, arithmetic progression, linear normalization, and nonlinear normalization to calculate the scores of the important words in the dataset and then computes the candidate word frequencies, which in turn constructs the universal word substitution list. Compared with other black-box methods, the experimental results on real-world tendency classification datasets show that UCTT exhibits an effective attack capability while significantly reducing the attack cost. Compared to the powerful baseline we designed that exceeds the SOTA, UCTT improves the efficiency of adversarial text generation by up to a factor of 7 without accessing the target model. In addition to demonstrating excellent attack performance on mainstream models, UCTT is also capable of attacking the powerful ChatGPT in the physical world, which cannot be directly attacked by traditional adversarial text generation methods due to the hard labels produced by the target model. [ABSTRACT FROM AUTHOR]

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

Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept; large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches. [ABSTRACT FROM AUTHOR]

Implicit discourse relation recognition (IDRR) is to detect and classify relation sense between two text segments without an explicit connective. Existing neural network models learn a semantic representation for each argument from its compositional words and classify discourse relation by the interactive semantic representation of an argument pair. As the basic English unit, a word only carries a simple and limited meaning that may be incorrectly interpreted in an argument without considering its syntactic context. This motivates us to explore whether we can learn an argument's semantic representation from another language unit phrase which usually contains full contextual meaning. We also argue that some semantic connection in between phrase pairs can be further exploited to infer the discourse relation between arguments. In this paper, we propose an Attentive Phrase Interaction Learning (APIL) model to parse and encode the interactive phrase structure for the IDRR task. In APIL, we propose a minimum subtree algorithm to obtain the phrase sequence of input arguments from its constituency syntax tree. We also design an Attentive Matching Network to learn the representation for each phrase from both arguments' semantic context and words' linguistic evidence. Furthermore, we propose a Phrase Inference Network to encode the linguistic relations of phrase pairs as semantic connections for relation inference. Experiments on the PDTB corpus show that our APIL model outperforms the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Reinforcement learning (RL) and imitation learning (IL) are quite two useful machine learning techniques that were shown to be potential in enhancing navigation performance. Basically, both of these methods try to find a policy decision function in a reinforcement learning fashion or through imitation. In this paper, we propose a novel algorithm named Reinforcement Imitation Learning (RIL) that naturally combines RL and IL together in accelerating more reliable and efficient navigation in dynamic environments. RIL is a hybrid approach that utilizes RL for policy optimization and IL as some kind of learning from expert demonstrations with the inclusion of guidance. We present the comparison of the convergence of RIL with conventional RL and IL to provide the support for our algorithm's performance in a dynamic environment with moving obstacles. The results of the testing indicate that the RIL algorithm has better collision avoidance and navigation efficiency than traditional methods. The proposed RIL algorithm has broad application prospects in many specific areas such as an autonomous driving, unmanned aerial vehicles, and robots. [ABSTRACT FROM AUTHOR]

Automatic handwritten character recognition plays a significant role in various applications across multiple fields. With the growing interest in automatic handwriting recognition and the advancement of deep learning methods, researchers have achieved significant improvements in the development of English handwriting recognition methods. However, the recognition of Arabic handwriting has received insufficient attention. In this paper, a novel "DeepAHR" model is presented to accurately and efficiently recognize Arabic handwritten characters using deep learning techniques. The "DeepAHR" model is based on a convolutional neural network (CNN) and is trained using two recent public datasets: Hijaa and Arabic handwritten characters dataset (AHCD). The overall accuracies of the proposed model were 98.66% and 88.24% on the AHCD and Hijaa datasets, respectively.The experimental results showed that DeepAHR outperformed state-of-the-art methods in the literature. These promising results provide evidence of the successful use of the DeepAHR model for recognizing handwritten Arabic characters [ABSTRACT FROM AUTHOR]

With the development of economic science and technology, the development of computer vision has undergone rapid changes, and various products relying on computer vision are also more and more, such as smart home, robot technology, and so on. At present, robot technology has become a very important part of the development of human science and technology, and in the field of industrial robots, the most rapid development is the robot with robot arm adaptive motion. It is very necessary to study the adaptive motion control of the manipulator based on machine learning. The robot with the adaptive motion of the manipulator can carry out logistics express sorting, operate in the doors and windows outside the building, and pick fruits in the orchard, which can ensure the effective implementation of hard work. Therefore, this paper proposes a mechanical adaptive control method based on a neural network. According to the motion model of the manipulator, the RBF neural network model is used to judge the stability of the system according to the Lyapunov function. The related algorithms of machine learning and multi-degree of freedom manipulator are studied and improved. The RBF neural network model approximates the unknown function infinitely and then establishes the complex motion model. Aiming at the adaptive neural network of a manipulator, a network adaptive terminal control method is proposed. Firstly, a stable manipulator motion system is designed by using a neural network, and then the terminal synovial controller is designed by using backstepping control technology. The stability of the method is proved by using the approximation virtual control technology of the neural network. The adaptive control is realized by using the learning and self-adaptability of the neural network; thus, the stability analysis of the closed-loop system is realized. [ABSTRACT FROM AUTHOR]

Source localization with a network of low-cost motes with limited processing, memory, and energy resources is considered in this paper. The state-of-the-art methods are mostly based on complicated signal processing approaches in which motes send their (processed) data to a fusion center (FC) wherein the source is localized. These methods are resource-demanding and mostly do not meet the limitations of motes and network. In this paper, we consider distributed detection where each mote performs a binary hypothesis test to detect locally the existence of a desired source and sends its (potentially erroneous) decision to FC during just one bit (1 indicates source existence and 0 otherwise). Hence, both processing and bandwidth constraints are met. We propose to use an artificial neural network (ANN) to correct erroneous local decisions. After error correction, the region affected by the source is specified by nodes with decision 1. Moreover, we propose to localize the source by deep learning in FC which converts the network of decisions 1 and 0 to a black and white image with white pixels in the locations of motes with decision 1. The proposed schemes of error correction by ANN (ECANN) and source localization with deep learning (SoLDeL) were evaluated in a fire detection application. We showed that SoLDeL performs appropriately and scales well into large networks. Moreover, the applicability of ECANN in delineation of farm management zones was illustrated. [ABSTRACT FROM AUTHOR]

The purpose of smart city is to enhance the optimal utilization of scarce resources and improve the resident's quality of live. The smart cities employed Internet of Things (IoT) to create a sustainable urban life. The IoT devices such as sensors, actuators, and smartphones in the smart cities generate data. The data generated from the smart cities are subjected to analytics to gain insight and discover new knowledge for improving the efficiency and effectiveness of the smart cities. Recently, the application of deep learning in smart cities has gained a tremendous attention from the research community. However, despite raise in popularity and achievements made by deep learning in solving problems in smart cities, no survey has been dedicated mainly on the application of deep learning in smart cities to show recent progress and direction for future development. To bridge this gap, this paper proposes to conduct a dedicated survey on the applications of deep learning in smart cities. In this paper, recent progress, new taxonomies, challenges and opportunities for future research opportunities on the application of deep learning in smart cities have been unveiled. The paper can provide opportunities for experts in the research community to propose a novel approach for developing the research area. On the other hand, new researchers interested in the research area can use the paper as an entry point. [ABSTRACT FROM AUTHOR]

Quality of Service (QoS) is the key parameter to measure the overall performance of service-oriented applications. In a myriad of web services, the QoS data has multiple highly sparse and enormous dimensions. It is a great challenge to reduce computational complexity by reducing data dimensions without losing information to predict QoS for future intervals. This paper uses an Induced Ordered Weighted Average (IOWA) layer in the prediction layer to lessen the size of a dataset and analyse the prediction accuracy of cloud QoS data. The approach enables stakeholders to manage extensive QoS data better and handle complex nonlinear predictions. The paper evaluates the cloud QoS prediction using an IOWA operator with nine neural network methods—Cascade-forward backpropagation, Elman backpropagation, Feedforward backpropagation, Generalised regression, NARX, Layer recurrent, LSTM, GRU and LSTM-GRU. The paper compares results using RMSE, MAE, and MAPE to measure prediction accuracy as a benchmark. A total of 2016 QoS data are extracted from Amazon EC2 US-West instance to predict future 96 intervals. The analysis results show that the approach significantly decreases the data size by 66%, from 2016 to 672 records with improved or equal accuracy. The case study demonstrates the approach's effectiveness while handling complexity, reducing data dimension with better prediction accuracy. [ABSTRACT FROM AUTHOR]

The COVID-19 epidemic has swept the world for over two years. However, a large number of infectious asymptomatic COVID-19 cases (ACCs) are still making the breaking up of the transmission chains very difficult. Efforts by epidemiological researchers in many countries have thrown light on the clinical features of ACCs, but there is still a lack of practical approaches to detect ACCs so as to help contain the pandemic. To address the issue of ACCs, this paper presents a neural network model called Spatio-Temporal Episodic Memory for COVID-19 (STEM-COVID) to identify ACCs from contact tracing data. Based on the fusion Adaptive Resonance Theory (ART), the model encodes a collective spatio-temporal episodic memory of individuals and incorporates an effective mechanism of parallel searches for ACCs. Specifically, the episodic traces of the identified positive cases are used to map out the episodic traces of suspected ACCs using a weighted evidence pooling method. To evaluate the efficacy of STEM-COVID, a realistic agent-based simulation model for COVID-19 spreading is implemented based on the recent epidemiological findings on ACCs. The experiments based on rigorous simulation scenarios, manifesting the current situation of COVID-19 spread, show that the STEM-COVID model with weighted evidence pooling has a higher level of accuracy and efficiency for identifying ACCs when compared with several baselines. Moreover, the model displays strong robustness against noisy data and different ACC proportions, which partially reflects the effect of breakthrough infections after vaccination on the virus transmission. [ABSTRACT FROM AUTHOR]

Recognizing the plant disease and pests in its golden time is a highly critical problem to be addressed, since the herbalist can apply treatments within this period and save the agricultural product. In this paper, a deep learning approach to recognize the disease from the leaves of the plants has been pursued. A client-server system is proposed in which the server-side model can leverage huge deep CNN architectures to classify the diseases, whereas the client-side model is to be chosen among small deep CNN architectures with low number of parameters in order to be easily deployed on the end-user mobile devices with poor processing powers. Here, a novel knowledge distillation technique has been leveraged that improves the accuracy level of the small client-side model significantly. This technique distills the perception knowledge of a large model classifier and transfers this knowledge to the small model in order to perform a similar prediction capability. By applying this idea on Plantvillage dataset, we could achieve 97.58 % accuracy on a small MobileNet architecture which is very close to the accuracy of a large Xception model on the server with 99.73 % accuracy. Through applying this teacher-student idea, we could improve the classification rate of the state-of-the-art tiny model by 2.12 % . [ABSTRACT FROM AUTHOR]

Personalization systems have proved to be one of the most powerful tools for e-commerce sites, assisting users in discovering the most relevant products across enormous product catalogues. The formulation of product suggestions in the most widely used collaborative filtering is dependent on ratings contributed by the customer base. Though numerous domains consider allowing users to give an overall rating to products, a burgeoning number of online platforms are allowing users to rate products on a variety of dimensions. According to previous research, these multidimensional ratings offer valuable perceptions that can be used in generating a personalization list for users. Within the personalization systems research domain, multi-criteria systems have garnered significant attention since they use multiple criteria to predict rating scores. New strategies for leveraging information produced from multi-criteria scores to increase the prediction precision of multi-criteria (MC) systems are presented in this paper. In particular, we propose to fuse deep neural networks (DNN), matrix factorization (MF), and social spider optimization (SSO) to exploit nonlinear, non-trivial, and concealed interactions between users in terms of MC preferences. Experimenting on Yahoo! and TripAdvisor datasets reveals that our proposed approach outperforms both modern single-rating recommender systems based on MF and traditional multi-criteria systems. As a result, we believe that using multi-criteria customer evaluations can help e-commerce companies enhance the quality and specificity of their recommended services. [ABSTRACT FROM AUTHOR]

Based on the hardware and sensors of image acquisition, the noise in the image has been easily generated. In this paper, an improved method of image decompression has proposed the shortcoming of the above-mentioned hardware algorithm. The traditional filter desiccation algorithm can only remove one or two specific noises, and it is not effective for other types. We combine some excellent neural network models. In this paper, an image mixing noise removal algorithm based on convolution nerve has been mentioned. Aiming at realizing the super-resolution of the image, the deconvolution layer can be used only to enlarge the image. The magnification factor is the step of deconvolution. This paper aims to eliminate the interference of the image noise. The effect of magnification on the deconvolution layer is impossible. The results of experimental test show that the algorithm achieves a good noise removal effect and is suitable for various mixed noise images. The algorithm used in this paper improves the subjective visual effect and objective evaluation index. [ABSTRACT FROM AUTHOR]

As a common data-driven method, artificial neural networks have been widely used in electricity spot price forecasting. To improve the accuracy of short-term forecasts, this paper proposes an optimized artificial neural network model for monthly electricity spot prices forecasting. A genetic algorithm is applied to regulate the weights and biases parameters of the artificial neural network structure. This study uses various historical dataset at monthly periods selected from Nordic electricity spot prices. For efficiency comparison, one-step ahead forecast method based on Schwartz-Smith stochastic model and two other prediction models, artificial neural network trained by Levenberg–Marquardt and particle swarm optimization algorithms are also presented. The comparison results show that the prediction model based on the genetic optimization algorithm is more accurate than the other prediction models. The proposed forecasting model can be considered as an alternative technique for the electricity spot price forecasting in the Nordic regions. [ABSTRACT FROM AUTHOR]

In this research paper, we study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history, leveraging a database of synthetic storm simulations. Traditionally, computational fluid dynamics (CFD) solvers are employed to numerically solve the storm surge governing equations that correspond to expensive to evaluate partial differential equations (PDE). This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations. This model can serve as a fast and affordable emulator for the expensive CFD solvers creating the original database. The neural network model is trained with the storm track parameters used to drive the CFD solvers, and the output of the model is the time-series evolution of the predicted storm surge across multiple nodes within the spatial domain of interest. Once the model is trained, it can be deployed for further predictions based on new storm track inputs. The developed neural network model is a time-series model, composed of a long short-term memory (LSTM), a variation of recurrent neural network (RNN), further enriched with convolutional neural networks (CNNs). The convolutional neural network is employed to capture the correlation of data spatially (across the aforementioned nodes). Therefore, the temporal and spatial correlations of data are captured by the combination of the mentioned models, representing the ConvLSTM model. As the problem is a sequence to sequence time-series problem, an encoder–decoder ConvLSTM model is designed. Furthermore, the performance of the developed convolutional recurrent neural network model is improved by residual connection networks. Additional techniques are employed in the process of model training to enrich the model performance that the model can learn from the data in a more effective way. The performance of the developed model is compared with the results provided by a Gaussian process (GP) implementation, representing a state-of-the-art alternative for establishing time-series emulation of storm surge predictions. The results show that the proposed convolutional recurrent neural network outperforms the GP implementation for the examined synthetic storm database. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) are vulnerable to being attacked by adversarial examples, leading to DNN misclassification. Perturbations in adversarial examples usually exist in the form of noise. In this paper, we proposed a lightweight joint contrastive learning and frequency domain denoising network (CFNet), which can effectively remove adversarial perturbations from adversarial examples. First, CFNet separates the channels of the features obtained by the multilayer convolution of the adversarial examples, and the separated feature maps are used to calculate the similarity with the high- and low-frequency feature maps obtained by Gaussian low-pass filtering of the clean examples. Second, by adjusting the network's attention to high-frequency feature images, CFNet can effectively remove the perturbations in adversarial examples and obtain reconstructed examples with high visual quality. Finally, to further improve the robustness of CFNet, contrastive regularization is proposed to bring the reconstructed examples back to the manifold decision boundary of clean examples, thus improving the classification accuracy of reconstructed examples. On the CIFAR-10 dataset, compared with the existing state-of-the-art defense model, the defense accuracy of CFNet is improved by 16.93% and 5.67% under untargeted and targeted projected gradient descent attacks, respectively. The AutoAttack untargeted attack defense accuracy increased by 30.81%. Experiments show that our approach provides better protection than existing state-of-the-art approaches, especially against unseen (untrained) types of attacks and adaptive attacks. [ABSTRACT FROM AUTHOR]