Search

In this paper two procedures are developed for the identification of the parameters contained in an orthotropic elastic-plastic-hardening model for free standing foils, particularly of paper and paperboard. The experimental data considered are provided by cruciform tests and digital image correlation. A simplified version of the constitutive model proposed by Xia et al. (Int J Solids Struct 39:4053-4071, ) is adopted. The inverse analysis is comparatively performed by the following alternative computational methodologies: (a) mathematical programming by a trust-region algorithm; (b) proper orthogonal decomposition and artificial neural network. The second procedure rests on preparatory once-for-all computations and turns out to be applicable economically and routinely in industrial environments. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

This paper is about the opposite of judgement and calculation. This opposition has been a traditional anchor of critiques concerned with the rise of AI decision making over human judgement. Contrary to these approaches, it is argued that human judgement is not and cannot be replaced by calculation, but that it is human judgement that contextualises computational structures and gives them meaning and purpose. The article focuses on the epistemic structure of algorithms and artificial neural networks to find that they always depend on human judgement to be related to real life objects or purposes. By introducing the philosophical concept of judgement, it becomes clear that the property of judgement to provide meaning and purposiveness is based on the temporality of human life and the ambiguity of language, which quantitative processes lack. A juxtaposition shows that calculations and clustering can be used and referred to in more or less prejudiced and reflecting as well as opaque and transparent ways, but thereby always depend on human judgement. The paper clearly asserts that the transparency of AI is necessary for their autonomous use. This transparency requires the explicitness of the judgements that constitute these computational structures, thereby creating an awareness of the conditionality of such epistemic entities. [ABSTRACT FROM AUTHOR]

Email phishing is a social engineering scheme that uses spoofed emails intended to trick the user into disclosing legitimate business and personal credentials. Many phishing email detection techniques exist based on machine learning, deep learning, and word embedding. In this paper, we propose a new technique for the detection of phishing emails using word embedding (Word2Vec, FastText, and TF-IDF) and deep learning techniques (DNN and BiLSTM network). Our proposed technique makes use of only four header based (From, Returnpath, Subject, Message-ID) features of the emails for the email classification. We applied several word embeddings for the evaluation of our models. From the experimental evaluation, we observed that the DNN model with FastText-SkipGram achieved an accuracy of 99.52% and BiLSTM model with FastText-SkipGram achieved an accuracy of 99.42%. Among these two techniques, DNN outperformed BiLSTM using the same word embedding (FastText-SkipGram) techniques with an accuracy of 99.52%. [ABSTRACT FROM AUTHOR]

Topography can strongly affect ground motion, and studies of the quantification of hill surfaces' topographic effect are relatively rare. In this paper, a new quantitative seismic topographic effect prediction method based upon the BP neural network algorithm and three-dimensional finite element method (FEM) was developed. The FEM simulation results were compared with seismic records and the results show that the PGA and response spectra have a tendency to increase with increasing elevation, but the correlation between PGA amplification factors and slope is not obvious for low hills. New BP neural network models were established for the prediction of amplification factors of PGA and response spectra. Two kinds of input variables' combinations which are convenient to achieve are proposed in this paper for the prediction of amplification factors of PGA and response spectra, respectively. The absolute values of prediction errors can be mostly within 0.1 for PGA amplification factors, and they can be mostly within 0.2 for response spectra's amplification factors. One input variables' combination can achieve better prediction performance while the other one has better expandability of the predictive region. Particularly, the BP models only employ one hidden layer with about a hundred nodes, which makes it efficient for training. [ABSTRACT FROM AUTHOR]

Today according to social media, the internet, Etc. Data is rapidly produced and occupies a large space in systems that have resulted in enormous data warehouses; the progress in information technology has significantly increased the speed and ease of data flow.text mining is one of the most important methods for extracting a useful model through extracting and adapting knowledge from data sets. However, many studies have been conducted based on the usage of deep learning for text processing and text mining issues.The idea and method of text mining are one of the fields that seek to extract useful information from unstructured textual data that is used very today. Deep learning and machine learning techniques in classification and text mining and their type are discussed in this paper as well. Neural networks of various kinds, namely, ANN, RNN, CNN, and LSTM, are the subject of study to select the best technique. In this study, we conducted a Systematic Literature Review to extract and associate the algorithms and features that have been used in this area. Based on our search criteria, we retrieved 130 relevant studies from electronic databases between 1997 and 2021; we have selected 43 studies for further analysis using inclusion and exclusion criteria in Section 3.2. According to this study, hybrid LSTM is the most widely used deep learning algorithm in these studies, and SVM in machine learning method high accuracy in result shown. [ABSTRACT FROM AUTHOR]

Organs-at-risk contouring is time consuming and labour intensive. Automation by deep learning algorithms would decrease the workload of radiotherapists and technicians considerably. However, the variety of metrics used for the evaluation of deep learning algorithms make the results of many papers difficult to interpret and compare. In this paper, a qualitative evaluation is done on five established metrics to assess whether their values correlate with clinical usability. A total of 377 CT volumes with heart delineations were randomly selected for training and evaluation. A deep learning algorithm was used to predict the contours of the heart. A total of 101 CT slices from the validation set with the predicted contours were shown to three experienced radiologists. They examined each slice independently whether they would accept or adjust the prediction and if there were (small) mistakes. For each slice, the scores of this qualitative evaluation were then compared with the Sørensen-Dice coefficient (DC), the Hausdorff distance (HD), pixel-wise accuracy, sensitivity and precision. The statistical analysis of the qualitative evaluation and metrics showed a significant correlation. Of the slices with a DC over 0.96 (N = 20) or a 95% HD under 5 voxels (N = 25), no slices were rejected by the readers. Contours with lower DC or higher HD were seen in both rejected and accepted contours. Qualitative evaluation shows that it is difficult to use common quantification metrics as indicator for use in clinic. We might need to change the reporting of quantitative metrics to better reflect clinical acceptance. [ABSTRACT FROM AUTHOR]

Adversarial examples which mislead deep neural networks by adding well-crafted perturbations have become a major threat to classification models. Gradient-based white-box attack algorithms have been widely used to generate adversarial examples. However, most of them are designed for multi-class models, and only a few gradient-based adversarial attack algorithms specifically designed for multi-label classification models. Due to the correlation between multiple labels, the performance of these gradient-based algorithms in generating adversarial examples for multi-label classification is worthy of analyzing and evaluating comprehensively. In this paper, we first transplant five typical gradient-based adversarial attack algorithms in the multi-class environment to the multi-label environment. Secondly, we comprehensively compared the performance of these five attack algorithms and the other four existing multi-label adversarial attack algorithms by experiments on six different attack types, and evaluated the transferability of adversarial examples generated by all algorithms under two attack types. Experimental results show that, among different attack types, the majority of multi-step attack algorithms have higher attack success rates compared to one-step attack algorithms. Additionally, these gradient-based algorithms face greater difficulty in augmenting labels than in hiding them. For transfer experimental results, the adversarial examples generated by all attack algorithms exhibit weaker transferability when attacking other different models. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks have been widely applied in medical image segmentation. However, the existence of local inductive bias in convolutional operations restricts the modeling of long-term dependencies. The introduction of Transformer enables the modeling of long-term dependencies and partially eliminates the local inductive bias in convolutional operations, thereby improving the accuracy of tasks such as segmentation and classification. Researchers have proposed various hybrid structures combining Transformer and Convolutional Neural Networks. One strategy is to stack Transformer blocks and convolutional blocks to concentrate on eliminating the accumulated local bias of convolutional operations. Another strategy is to nest convolutional blocks and Transformer blocks to eliminate bias within each nested block. However, due to the granularity of bias elimination operations, these two strategies cannot fully exploit the potential of Transformer. In this paper, a parallel hybrid model is proposed for segmentation, which includes a Transformer branch and a Convolutional Neural Network branch in encoder. After parallel feature extraction, inter-layer information fusion and exchange of complementary information are performed between the two branches, simultaneously extracting local and global features while eliminating the local bias generated by convolutional operations within the current layer. A pure convolutional operation is used in decoder to obtain final segmentation results. To validate the impact of the granularity of bias elimination operations on the effectiveness of local bias elimination, the experiments in this paper were conducted on Flare21 dataset and Amos22 dataset. The average Dice coefficient reached 92.65% on Flare21 dataset, and 91.61% on Amos22 dataset, surpassing comparative methods. The experimental results demonstrate that smaller granularity of bias elimination operations leads to better performance. [ABSTRACT FROM AUTHOR]

Fungal keratitis (FK) is a common and severe corneal disease, which is widely spread in tropical and subtropical areas. Early diagnosis and treatment are vital for patients, with confocal microscopy cornea imaging being one of the most effective methods for the diagnosis of FK. However, most cases are currently diagnosed by the subjective judgment of ophthalmologists, which is time-consuming and heavily depends on the experience of the ophthalmologists. In this paper, we introduce a novel structure-aware automatic diagnosis algorithm based on deep convolutional neural networks for the accurate diagnosis of FK. Specifically, a two-stream convolutional network is deployed, combining GoogLeNet and VGGNet, which are two commonly used networks in computer vision architectures. The main stream is used for feature extraction of the input image, while the auxiliary stream is used for feature discrimination and enhancement of the hyphae structure. Then, the features are combined by concatenating the channel dimension to obtain the final output, i.e., normal or abnormal. The results showed that the proposed method achieved accuracy, sensitivity, and specificity of 97.73%, 97.02%, and 98.54%, respectively. These results suggest that the proposed neural network could be a promising computer-aided FK diagnosis solution. [ABSTRACT FROM AUTHOR]

With the continuous mining and gradual reduction of shallow deposits, deep prospecting has become a new global prospecting trend. In addition, with the development of artificial intelligence, deep learning provides a favorable means for geological big data analysis. This paper, researches the No. II Orebody of the Xiongcun deposit. First, based on previous research results and metallogenic regularity, prospecting information, namely, lithology, Au-Ag-Cu chemical elements and wall rock alteration is extracted, and the block model is established by combining the Kriging interpolation structure. Second, the datasets are divided into dataset I and dataset II according to "randomness" and "depth". Third, deep prospecting prediction models based on deep neural networks (DNN) and the convolutional neural networks (CNN) is constructed, and the model parameters are optimized. Finally, the models are applied to the deep prediction of the Xiongcun No. II Orebody. The results show that the accuracy rate and recall rate of the prediction model based on the DNN algorithm are 96.15% and 89.23%, respectively, and the AUC is 96.39%, which are higher values than those of the CNN algorithm, indicating that the performance of the prediction model based on the DNN algorithm is better. The accuracy of prediction model based on dataset I is higher than that of dataset II. The accuracy of deep metallogenic prediction based on the DNN algorithm is approximately 89%, that based on the CNN is approximately 87%, and that based on prospecting information method is approximately 61.27%. The prediction results of the DNN algorithm are relatively consistent in the spatial location and scale of the orebody. Therefore, based on the work done in this paper, it is feasible to use a deep learning method to carry out deep mineral prediction. [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]

The external and middle ear conditions are diagnosed using a digital otoscope. The clinical diagnosis of ear conditions is suffered from restricted accuracy due to the increased dependency on otolaryngologist expertise, patient complaint, blurring of the otoscopic images, and complexity of lesions definition. There is a high requirement for improved diagnosis algorithms based on otoscopic image processing. This paper presented an ear diagnosis approach based on a convolutional neural network (CNN) as feature extraction and long short-term memory (LSTM) as a classifier algorithm. However, the suggested LSTM model accuracy may be decreased by the omission of a hyperparameter tuning process. Therefore, Bayesian optimization is used for selecting the hyperparameters to improve the results of the LSTM network to obtain a good classification. This study is based on an ear imagery database that consists of four categories: normal, myringosclerosis, earwax plug, and chronic otitis media (COM). This study used 880 otoscopic images divided into 792 training images and 88 testing images to evaluate the approach performance. In this paper, the evaluation metrics of ear condition classification are based on a percentage of accuracy, sensitivity, specificity, and positive predictive value (PPV). The findings yielded a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a PPV of 100% for the testing database. Finally, the proposed approach shows how to find the best hyperparameters concerning the Bayesian optimization for reliable diagnosis of ear conditions under the consideration of LSTM architecture. This approach demonstrates that CNN-LSTM has higher performance and lower training time than CNN, which has not been used in previous studies for classifying ear diseases. Consequently, the usefulness and reliability of the proposed approach will create an automatic tool for improving the classification and prediction of various ear pathologies. [ABSTRACT FROM AUTHOR]

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

In the present paper, deep convolutional neural network (DCNN) is applied to multilocus protein subcellular localization as it is more suitable for multi-class classification. There are two main problems with this application. First, the appropriate features for correlation between multiple sites are hard to find. Second, the classifier structure is difficult to determine as it is greatly affected by the distribution of classified data. To solve these problems, a self-evoluting framework using DCNNs for multilocus protein subcellular localization is proposed. It has three characteristics that the previous algorithms do not. The first is that it combines the ant colony algorithm with the DCNN to form a self-evoluting algorithm for multilocus protein subcellular localization. The second is that it randomly groups subcellular sites using a limited random k-labelsets multi-label classification method. It also solves complex problems in a divide-and-conquer approach and proposes a flexible expansion model. The third is that it realizes the random selection feature extraction method in the positioning process and avoids the defects in individual feature extraction methods. The algorithm in the present paper is tested on the human database, and the overall correct rate is 67.17%, which is higher than that for the stacked self-encoder (SAE), support vector machine (SVM), random forest classifier (RF), or single deep convolutional neural network. Graphical abstract [ABSTRACT FROM AUTHOR]

Breast cancer is the second most common cancer among women worldwide, and the diagnosis by pathologists is a time-consuming procedure and subjective. Computer-aided diagnosis frameworks are utilized to relieve pathologist workload by classifying the data automatically, in which deep convolutional neural networks (CNNs) are effective solutions. The features extracted from the activation layer of pre-trained CNNs are called deep convolutional activation features (DeCAF). In this paper, we have analyzed that all DeCAF features are not necessarily led to higher accuracy in the classification task and dimension reduction plays an important role. We have proposed reduced DeCAF (R-DeCAF) for this purpose, and different dimension reduction methods are applied to achieve an effective combination of features by capturing the essence of DeCAF features. This framework uses pre-trained CNNs such as AlexNet, VGG-16, and VGG-19 as feature extractors in transfer learning mode. The DeCAF features are extracted from the first fully connected layer of the mentioned CNNs, and a support vector machine is used for classification. Among linear and nonlinear dimensionality reduction algorithms, linear approaches such as principal component analysis (PCA) represent a better combination among deep features and lead to higher accuracy in the classification task using a small number of features considering a specific amount of cumulative explained variance (CEV) of features. The proposed method is validated using experimental BreakHis and ICIAR datasets. Comprehensive results show improvement in the classification accuracy up to 4.3% with a feature vector size (FVS) of 23 and CEV equal to 0.15. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have achieved outstanding results in domains such as image processing, computer vision, natural language processing and bioinformatics. In recent years, many methods have been proposed that can provide a visual explanation of decision made by such classifiers. Saliency maps are probably the most popular. However, it is still unclear how to properly interpret saliency maps for a given image and which techniques perform most accurately. This paper presents a methodology to practically evaluate the real effectiveness of saliency map generation methods. We used three state-of-the-art network architectures along with specially prepared benchmark datasets, and we proposed a novel metric to provide a quantitative comparison of the methods. The comparison identified the most reliable techniques and the solutions which usually failed in our tests. [ABSTRACT FROM AUTHOR]

Adaptive algorithms are widely used in deep learning because of their fast convergence. Among them, Adam is the most widely used algorithm. However, studies have shown that Adam's generalization ability is weak. AdaX is a variant of Adam, which introduces a novel second-order momentum, modifies the second-order moment of Adam, and has good generalization ability. However, these algorithms may fail to converge due to instability and extreme learning rates during training. In this paper, we propose a new adaptive and momental bound algorithm, called AdaXod, which characterizes of exponentially averaging the learning rate and is particularly useful for training deep neural networks. By setting an adaptively limited learning rate in the AdaX algorithm, the resultant AdaXod can effectively eliminate the problem of excessive learning rate in the later stage of neural networks training and thus results in stable training. We conduct extensive experiments on different datasets and verify the advantages of the AdaXod algorithm by comparing with other advanced adaptive optimization algorithms. AdaXod eliminates large learning rates during neural networks training and outperforms other optimizers, especially for some neural networks with complex structures, such as DenseNet. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (LDCT) is an effective way to reduce radiation exposure for patients. However, it will increase the noise of reconstructed CT images and affect the precision of clinical diagnosis. The majority of the current deep learning-based denoising methods are built on convolutional neural networks (CNNs), which concentrate on local information and have little capacity for multiple structures modeling. Transformer structures are capable of computing each pixel's response on a global scale, but their extensive computation requirements prevent them from being widely used in medical image processing. To reduce the impact of LDCT scans on patients, this paper aims to develop an image post-processing method by combining CNN and Transformer structures. This method can obtain a high-quality images from LDCT. A hybrid CNN-Transformer (HCformer) codec network model is proposed for LDCT image denoising. A neighborhood feature enhancement (NEF) module is designed to introduce the local information into the Transformer's operation, and the representation of adjacent pixel information in the LDCT image denoising task is increased. The shifting window method is utilized to lower the computational complexity of the network model and overcome the problems that come with computing the MSA (Multi-head self-attention) process in a fixed window. Meanwhile, W/SW-MSA (Windows/Shifted window Multi-head self-attention) is alternately used in two layers of the Transformer to gain the information interaction between various Transformer layers. This approach can successfully decrease the Transformer's overall computational cost. The AAPM 2016 LDCT grand challenge dataset is employed for ablation and comparison experiments to demonstrate the viability of the proposed LDCT denoising method. Per the experimental findings, HCformer can increase the image quality metrics SSIM, HuRMSE and FSIM from 0.8017, 34.1898, and 0.6885 to 0.8507, 17.7213, and 0.7247, respectively. Additionally, the proposed HCformer algorithm will preserves image details while it reduces noise. In this paper, an HCformer structure is proposed based on deep learning and evaluated by using the AAPM LDCT dataset. Both the qualitative and quantitative comparison results confirm that the proposed HCformer outperforms other methods. The contribution of each component of the HCformer is also confirmed by the ablation experiments. HCformer can combine the advantages of CNN and Transformer, and it has great potential for LDCT image denoising and other tasks. [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]

Salp swarm algorithm (SSA) is a swarm intelligence algorithm inspired by the swarm behavior of salps in oceans. In this paper, a adaptive multi-group salp swarm algorithm (AMSSA) with three new communication strategies is presented. Adaptive multi-group mechanism is to evenly divide the initial population into several subgroups, and then exchange information among subgroups after each adaptive iteration. Communication strategy is also an important part of adaptive multi-group mechanism. This paper proposes three new communication strategies and focuses on promoting the performance of SSA. These measures significantly improve the cooperative ability of SSA, accelerate convergence speed, and avoid easily falling into local optimum. And the benchmark functions confirm that AMSSA is better than the original SSA in exploration and exploitation. In addition, AMSSA is combined with prediction of wind power based on back propagation (AMSSA-BP) neural network. The simulation results show that the AMSSA-BP neural network prediction model can achieve a better prediction effect of wind power. [ABSTRACT FROM AUTHOR]

The use of face video information for driver fatigue detection has received extensive attention because of its low cost and non-invasiveness. However, the current vehicle-mounted embedded device has insufficient memory and limited computing power, which cannot complete the real-time detection of driver fatigue based on deep learning. Therefore, this paper designs a lightweight neural network model to solve this problem. The model includes object detection and fatigue detection. First, a lightweight object detection network is designed, which can quickly identify the opening and closing states of the driver's eyes and mouth in the time series video. Secondly, the EYE-MOUTH (EM) driver fatigue detection model is designed, which encodes the driver's eye and mouth opening and closing state, and calculates the driver's PERCLOS (Percentage of Eyelid Closure over the Pupil) and FOM (Frequency of Open Mouth) according to the coding sequence. Finally, the multi-feature fusion judgment algorithm is used to realize the judgment of the driver's fatigue state. The experimental results show that our method has an accuracy rate of 98.30% for drowsiness and yawning behaviors in a real vehicle environment, and a detection speed of 27FPS, which is better than other advanced methods and meets the requirements of real-time detection. [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]

Human facial analysis (HFA) has recently become an attractive topic for computer vision research due to technological progress and mobile applications. HFA explores several issues as gender recognition (GR), facial expression, age, and race recognition for automatically understanding social life. This study explores HFA from the angle of recognizing a person's gender from their face. Several hard challenges are provoked, such as illumination, occlusion, facial emotions, quality, and angle of capture by cameras, making gender recognition more difficult for machines. The Archimedes optimization algorithm (AOA) was recently designed as a metaheuristic-based population optimization method, inspired by the Archimedes theory's physical notion. Compared to other swarm algorithms in the realm of optimization, this method promotes a good balance between exploration and exploitation. The convergence area is increased By incorporating extra data into the solution, such as volume and density. Because of the preceding benefits of AOA and the fact that it has not been used to choose the best area of the face, we propose utilizing a wrapper feature selection technique, which is a real motivation in the field of computer vision and machine learning. The paper's primary purpose is to automatically determine the optimal face area using AOA to recognize the gender of a human person categorized by two classes (Men and women). In this paper, the facial image is divided into several subregions (blocks), where each area provides a vector of characteristics using one method from handcrafted techniques as the local binary pattern (LBP), histogram-oriented gradient (HOG), or gray-level co-occurrence matrix (GLCM). Two experiments assess the proposed method (AOA): The first employs two benchmarking datasets: the Georgia Tech Face dataset (GT) and the Brazilian FEI dataset. The second experiment represents a more challenging large dataset that uses Gallagher's uncontrolled dataset. The experimental results show the good performance of AOA compared to other recent and competitive optimizers for all datasets. In terms of accuracy, the AOA-based LBP outperforms the state-of-the-art deep convolutional neural network (CNN) with 96.08% for the Gallagher's dataset. [ABSTRACT FROM AUTHOR]

In a complex environment with multiple feasible paths, planning a globally optimal path and performing dynamic path planning for robots is challenging. Therefore, this paper proposed a new adaptive Differential Evolution algorithm combined with K-modes clustering, BP neural network, and other strategies (KBPDE) to overcome this issue. The proposed KBPDE algorithm applies a new population initialization strategy based on K-modes clustering and a two-population strategy to enhance the population diversity and prevent the algorithm from falling into local optima. A BP neural network model is developed to obtain the appropriate mutation scale factor F at each generation G. Based on the positional relationships among individuals in the current generation, a novel mutation strategy is presented. Finally, an adaptive population size strategy is introduced to raise the algorithm's efficiency. In a complicated environment with several feasible paths, the experimental results demonstrate that KBPDE can obtain the globally optimal path in contrast to GA, DE, and the excellent versions of DE. In a partially known environment, the EKBPDE can plan the path successfully. [ABSTRACT FROM AUTHOR]

This study reports an effective and robust edge-based scheme for the reconstruction of 3D human faces from input of single images, addressing drawbacks of existing methods in case of large face pose angles or noisy input images. Accurate 3D face reconstruction from 2D images is important, as it can enable a wide range of applications, such as face recognition, animations, games and AR/VR systems. Edge features extracted from 2D images contain wealthy and robust 3D geometric information, which were used together with landmarks for face reconstruction purpose. However, the accurate reconstruction of 3D faces from contour features is a challenging task, since traditional edge or contour detection algorithms introduce a great deal of noise, which would adversely affect the reconstruction. This paper reports on the use of a hard-blended face contour feature from a neural network and a Canny edge extractor for face reconstruction. The quantitative results indicate that our method achieves a notable improvement in face reconstruction with a Euclidean distance error of 1.64 mm and a normal vector distance error of 1.27 mm when compared to the ground truth, outperforming both traditional and other deep learning-based methods. These metrics show particularly significant advancements, especially in face shape reconstruction under large pose angles. The method also achieved higher accuracy and robustness on in-the-wild images under conditions of blurring, makeup, occlusion and poor illumination. [ABSTRACT FROM AUTHOR]

Image registration is a fundamental task in various applications of medical image analysis and plays a crucial role in auxiliary diagnosis, treatment, and surgical navigation. However, cardiac image registration is challenging due to the large non-rigid deformation of the heart and the complex anatomical structure. To address this challenge, this paper proposes an independently trained multi-scale registration network based on an image pyramid. By down-sampling the original input image multiple times, we can construct image pyramid pairs, and design a multi-scale registration network using image pyramid pairs of different resolutions as the training set. Using image pairs of different resolutions, train each registration network independently to extract image features from the image pairs at different resolutions. During the testing stage, the large deformation registration is decomposed into a multi-scale registration process. The deformation fields of different resolutions are fused by a step-by-step deformation method, thereby addressing the challenge of directly handling large deformations. Experiments were conducted on the open cardiac dataset ACDC (Automated Cardiac Diagnosis Challenge); the proposed method achieved an average Dice score of 0.828 in the experimental results. Through comparative experiments, it has been demonstrated that the proposed method effectively addressed the challenge of heart image registration and achieved superior registration results for cardiac images. [ABSTRACT FROM AUTHOR]

Deep learning techniques have recently yielded remarkable results across various fields. However, the quality of these results depends heavily on the quality and quantity of data used during the training phase. One common issue in multi-class and multi-label classification is class imbalance, where one or several classes make up a substantial portion of the total instances. This imbalance causes the neural network to prioritize features of the majority classes during training, as their detection leads to higher scores. In the context of object detection, two types of imbalance can be identified: (1) an imbalance between the space occupied by the foreground and background and (2) an imbalance in the number of instances for each class. This paper aims to address the second type of imbalance without exacerbating the first. To achieve this, we propose a modification of the copy-paste data augmentation technique, combined with weight-balancing methods in the loss function. This strategy was specifically tailored to improve the performance in datasets with a high instance density, where instance overlap could be detrimental. To validate our methodology, we applied it to a highly unbalanced dataset focused on nuclei detection. The results show that this hybrid approach improves the classification of minority classes without significantly compromising the performance of majority classes. [ABSTRACT FROM AUTHOR]

Low-dose computer tomography (LDCT) has been widely used in medical diagnosis. Various denoising methods have been presented to remove noise in LDCT scans. However, existing methods cannot achieve satisfactory results due to the difficulties in (1) distinguishing the characteristics of structures, textures, and noise confused in the image domain, and (2) representing local details and global semantics in the hierarchical features. In this paper, we propose a novel denoising method consisting of (1) a 2D dual-domain restoration framework to reconstruct noise-free structure and texture signals separately, and (2) a 3D multi-depth reinforcement U-Net model to further recover image details with enhanced hierarchical features. In the 2D dual-domain restoration framework, the convolutional neural networks are adopted in both the image domain where the image structures are well preserved through the spatial continuity, and the sinogram domain where the textures and noise are separately represented by different wavelet coefficients and processed adaptively. In the 3D multi-depth reinforcement U-Net model, the hierarchical features from the 3D U-Net are enhanced by the cross-resolution attention module (CRAM) and dual-branch graph convolution module (DBGCM). The CRAM preserves local details by integrating adjacent low-level features with different resolutions, while the DBGCM enhances global semantics by building graphs for high-level features in intra-feature and inter-feature dimensions. Experimental results on the LUNA16 dataset and 2016 NIH-AAPM-Mayo Clinic LDCT Grand Challenge dataset illustrate the proposed method outperforms the state-of-the-art methods on removing noise from LDCT images with clear structures and textures, proving its potential in clinical practice. [ABSTRACT FROM AUTHOR]

Regional debris flow susceptibility assessment is an effective method to prevent debris flow hazards, and deep learning is emerging as a novel approach in this discipline with the development of computers. However, when debris flow samples are insufficient, there will be problems like overfitting or misclassification. To overcome these problems, this paper proposes a semi-supervised deep neural network model (LPA-DNN) combined with label propagation algorithm (LPA), which utilizes high confidence unlabeled samples as pseudo-samples reasonably in few-label scenarios. Xinzhou, Shanxi Province, was selected as the study area, and a dataset containing 292 debris flow samples and 10 types of impact factors was compiled based on watershed units. Using the dataset and pseudo-samples, the LPA-DNN model was built to get debris flow susceptibility map. Meanwhile, DNN and SVM were set up for comparison to demonstrate that the proposed LPA-DNN model has excellent performance and higher accuracy. LPA-DNN alleviates the problem of low accuracy that caused by samples lacking in deep learning to a certain extent, and obtains great classification results, which proves that it is quite potential in regional debris flow susceptibility assessment. [ABSTRACT FROM AUTHOR]

Intrusion detection is a crucial technology in the communication network security field. In this paper, a dynamic evolutionary sparse neural network (DESNN) is proposed for intrusion detection, named as DESNN algorithm. Firstly, an ensemble neural network model is constructed, which is processed by a dynamic pruning rule and further divided into advantage subnetworks and disadvantage subnetworks. The dynamic pruning rule can effectively reduce the subnetworks weight parameters, thereby increasing the speed of the subnetworks intrusion detection. Then considering the subnetworks performance loss caused by the dynamic pruning rule, a novel evolutionary mechanism is proposed to optimize the training process of the disadvantage subnetworks. The weight of the disadvantage subnetworks approach the weight of the advantage subnetworks by the evolutionary mechanism, such that the performance of the ensemble neural network can be improved. Finally, an optimal subnetwork is selected from the ensemble neural network, which is used to detect multiple types of intrusion. Experiments show that the proposed DESNN algorithm improves intrusion detection speed without causing significant performance loss compare with other fully-connected neural network models. [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]

The paper proposes the concept of inverse P-augmented matrix, and gives its structure; the inverse P-augmented matrix is obtained by improving the common augmented matrix; under certain condition, the inverse P-augmented matrix is reduced to the common augmented matrix. Inverse P-sets is the theoretical basis of proposing inverse P-augmented matrix, which is a new set model with dynamic feature. The paper gives the introduction of inverse-P set, the generation method of inverse P-augmented matrix and the relation between inverse P-augmented matrix and common augmented matrix, and gives the application of inverse P-augmented matrix in the dynamic findings of unknown information by virtue of these studies. [ABSTRACT FROM AUTHOR]

Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) are widely regarded as the most effective learning tool for dealing with large datasets, and they have been successfully used in thousands of applications in a variety of fields. Based on these large datasets, they are trained to learn the relationships between various variables. The adaptive moment estimation (Adam) algorithm, a highly efficient adaptive optimization algorithm, is widely used as a learning algorithm in various fields for training DNN models. However, it needs to improve its generalization performance, especially when training with large-scale datasets. Therefore, in this paper, we propose HN Adam, a modified version of the Adam Algorithm, to improve its accuracy and convergence speed. The HN_Adam algorithm is modified by automatically adjusting the step size of the parameter updates over the training epochs. This automatic adjustment is based on the norm value of the parameter update formula according to the gradient values obtained during the training epochs. Furthermore, a hybrid mechanism was created by combining the standard Adam algorithm and the AMSGrad algorithm. As a result of these changes, the HN_Adam algorithm, like the stochastic gradient descent (SGD) algorithm, has good generalization performance and achieves fast convergence like other adaptive algorithms. To test the proposed HN_Adam algorithm performance, it is evaluated to train a deep convolutional neural network (CNN) model that classifies images using two different standard datasets: MNIST and CIFAR-10. The algorithm results are compared to the basic Adam algorithm and the SGD algorithm, in addition to other five recent SGD adaptive algorithms. In most comparisons, the HN Adam algorithm outperforms the compared algorithms in terms of accuracy and convergence speed. AdaBelief is the most competitive of the compared algorithms. In terms of testing accuracy and convergence speed (represented by the consumed training time), the HN-Adam algorithm outperforms the AdaBelief algorithm by an improvement of 1.0% and 0.29% for the MNIST dataset, and 0.93% and 1.68% for the CIFAR-10 dataset, respectively. [ABSTRACT FROM AUTHOR]

An automated diagnosis system is crucial for helping radiologists identify brain abnormalities efficiently. The convolutional neural network (CNN) algorithm of deep learning has the advantage of automated feature extraction beneficial for an automated diagnosis system. However, several challenges in the CNN-based classifiers of medical images, such as a lack of labeled data and class imbalance problems, can significantly hinder the performance. Meanwhile, the expertise of multiple clinicians may be required to achieve accurate diagnoses, which can be reflected in the use of multiple algorithms. In this paper, we present Deep-Stacked CNN, a deep heterogeneous model based on stacked generalization to harness the advantages of different CNN-based classifiers. The model aims to improve robustness in the task of multi-class brain disease classification when we have no opportunity to train single CNNs on sufficient data. We propose two levels of learning processes to obtain the desired model. At the first level, different pre-trained CNNs fine-tuned via transfer learning will be selected as the base classifiers through several procedures. Each base classifier has a unique expert-like character, which provides diversity to the diagnosis outcomes. At the second level, the base classifiers are stacked together through neural network, representing the meta-learner that best combines their outputs and generates the final prediction. The proposed Deep-Stacked CNN obtained an accuracy of 99.14% when evaluated on the untouched dataset. This model shows its superiority over existing methods in the same domain. It also requires fewer parameters and computations while maintaining outstanding performance. [ABSTRACT FROM AUTHOR]

If lung cancer is not detected in its initial phases, it can be fatal. However, because of the quantity and structure of its nodules, lung cancer is difficult to detect early. For accurate detections, radiologists require assistance from automated tools. Numerous expert methods have been created over time to assist radiologists in the diagnosis of lung cancer. However, this requires accurate research. Therefore, in this article, we propose a framework to precisely detect lung cancer by categorizing it between benign and malignant nodules. To achieve this objective, an efficient deep-learning algorithm is presented. The presented technique consists of four stages, namely pre-processing, segmentation, classification, and severity stage analysis. Initially, the collected image is given to the pre-processing stage to eliminate the distortion present in the image. Then, the noise-free image is given to the segmentation stage. For segmentation, in this paper, modified regularized K-means (MRKM) clustering algorithm is presented. After the segmentation process, the segmented nodule image is fed to the classification stage to categorize the nodule as benign or malignant (risk nodule). For classification, an improved convolution neural network (ICNN) is presented. The proposed ICNN is designed by modifying CNN with the integration of the adaptive tree seed optimization (ATSO) algorithm. Finally, the stage identification is carried out based on the size of the nodule and we classify the malignant nodule as S1–S4. The presented technique attained the maximum accuracy of 96.5% and performance compared with existing state-of-art methods. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is one of the most common consequences of diabetes. It affects the retina, causing blood vessel damage which can lead to loss of vision. Saving patients from losing their sight or at least slowing the progress of this disease depends mainly on the early detection of this pathology, on top of the detection of its specific stage. Furthermore, the early detection of diabetic retinopathy and the follow-up of the patient's condition remains an arduous task, whether for an experienced expert ophthalmologist or a computer-aided diagnosis technician. In this paper, we aim to propose a new automatic diabetic retinopathy severity level detection method. The proposed approach merges the pyramid hierarchy of the discrete wavelet transform of the retina fundus image with the modified capsule network and the modified inception block proposed, in addition to a new deep hybrid model that concatenates the inception block with capsule networks. The performance of our proposed approach has been validated on the APTOS dataset, as it achieved a high training accuracy of 97.71% and a high testing accuracy score of 86.54%, which is considered one of the best scores achieved in this field using the same dataset. [ABSTRACT FROM AUTHOR]

The end-to-end convolutional neural network models have been widely used in single image de-raining, which can extract clean background images from rainy images. However, they suffer from gradient vanishing with increased network depth. With the aim of tackling this problem, this paper proposes an effective rain removal algorithm based on dual parallel branch residual overlay network (DBRONet). Firstly, the two parallel branches with different functions are combined with increasing the width of the network, which can reduce the depth of the network effectively. Secondly, the upper branch uses multi-scale rain streak extraction blocks (MRSEB) composed of multi-scale residual blocks and extracts rain streaks of different densities, sizes and directions in the rainy images. The lower branch utilizes dilated convolution attention residual block (DARB) to expand the receptive field and obtains more context information without increasing the depth of the network. Finally, the de-raining image is obtained by superposition features of the two branches and the original image. Experimental results on synthetic and real datasets show that DBRONet can effectively reduce the depth of the network and the number of parameters. Compared with the existing methods in terms of quantitative and qualitative indicators, it has achieved the most advanced results. When comparing with other methods on Rain100H, Rain100L, Rain12, Rain1400 with the improvements of 0.76 dB, 0.29 dB, 0.11 dB and 0.25 dB on PSNR value and 0.4%, 0.3%, 0.4%, 1.2% on SSIM value, respectively. The source code can be found at https://github.com/RemeberMeX/DBRONet. [ABSTRACT FROM AUTHOR]

The hybrid neural network model proposed in this paper consists of two main parts: extracting local features of text vectors by convolutional neural network, extracting global features related to text context by BiLSTM, and fusing the features extracted by the two complementary models. In this paper, the pre-processed sentences are put into the hybrid neural network for training. The trained hybrid neural network can automatically classify the sentences. When testing the algorithm proposed in this paper, the training corpus is Word2vec. The test results show that the accuracy rate of text categorization reaches 94.2%, and the number of iterations is 10. The results show that the proposed algorithm has high accuracy and good robustness when the sample size is seriously unbalanced. [ABSTRACT FROM AUTHOR]

The early stage lung cancer often appears as ground-glass nodules (GGNs). The diagnosis of GGN as preinvasive lesion (PIL) or invasive adenocarcinoma (IA) is very important for further treatment planning. This paper proposes an automatic GGNs' invasiveness classification algorithm for the adenocarcinoma. 1431 clinical cases and a total of 1624 GGNs (3–30 mm) were collected from Shanghai Cancer Center for the study. The data is in high-resolution computed tomography (HRCT) format. Firstly, the automatic GGN detector which is composed by a 3D U-Net and a 3D multi-receptive field (multi-RF) network detects the location of GGNs. Then, a deep 3D convolutional neural network (3D-CNN) called Attention-v1 is used to identify the GGNs' invasiveness. The attention mechanism was introduced to the 3D-CNN. This paper conducted a contract experiment to compare the performance of Attention-v1, ResNet, and random forest algorithm. ResNet is one of the most advanced convolutional neural network structures. The competition performance metrics (CPM) of automatic GGN detector reached 0.896. The accuracy, sensitivity, specificity, and area under curve (AUC) value of Attention-v1 structure are 85.2%, 83.7%, 86.3%, and 92.6%. The algorithm proposed in this paper outperforms ResNet and random forest in sensitivity, accuracy, and AUC value. The deep 3D-CNN's classification result is better than traditional machine learning method. Attention mechanism improves 3D-CNN's performance compared with the residual block. The automatic GGN detector with the addition of Attention-v1 can be used to construct the GGN invasiveness classification algorithm to help the patients and doctors in treatment. [ABSTRACT FROM AUTHOR]

Positioning accuracy is one of the main challenges in wireless sensor networks. Both the existing localization algorithms and the ranging accuracy need to be improved. This paper demonstrates that the PSO-BP method can effectively estimate the coordinates of mobile nodes in the indoor three-dimensional space. Convergence speed and estimation accuracy of the BP neural network model optimized for the PSO are also discussed. A hybrid GA-PSO-BP algorithm is then proposed. It improves the BP neural network's prediction performance by optimizing parameters such as the number of neurons for each hidden layer, the learning rate and the error target of the BP network. The value of the coordinates of the specified beacon node and the RSSI value are the inputs of the BP neural network. The method for estimating the floor which the mobile node is on is used to further improve the node coordinate prediction accuracy. Compared with the PSO-BP, the simulation results show that the convergence speed of the hybrid GA-PSO-BP model is faster. It can effectively improve the node coordinate estimation accuracy of the mobile sensor networks. The average coordinate estimation error of the hybrid GA-PSO-BP algorithm proposed in this paper is about 0.215 m, which is 49.2. [ABSTRACT FROM AUTHOR]

The goal of this paper is twofold. Firstly, a Siamese-twin random projection neural network (ST-RPNN) is proposed for unsupervised binary hashing of images and compared with state-of-the-art techniques. Secondly, a comparison between Hamming-distance-based retrieval and a proposed bagging trees retrieval (BT-retrieval) algorithm operating directly on the PCA features is made with respect to performance, storage and search time. The ST-RPNN is made of two identical random projection neural networks and is trained to produce similar binary codes for similar input image pairs and different binary codes otherwise. The learning process is divided into two steps: a fast sparse neurons selection algorithm followed by an unsupervised bagging trees algorithm to extract the compact required-length code. Moreover, a BT-retrieval algorithm is proposed in this paper as a fast retrieval tool that ranks the database with respect to a query without distance calculations. Furthermore, (BT-PCA) is a novel extension where the BT-retrieval is applied directly on the PCA features with a significantly lower time search than Hamming-distance-based approach. The proposed technique is compared with ten unsupervised image binary hashing techniques on the COREL1K dataset and the CIFAR10 dataset. The proposed technique obtained better precision–recall results than all compared techniques on the COREL1K dataset, and better than eight of them on the CIFAR10 dataset. [ABSTRACT FROM AUTHOR]

The new image de-nosing algorithm based on improved deep convolutional neural network in the monogenic wavelet domain is proposed in this paper. The monogenic wavelet transform was employed to describe the amplitude and phase information of the noisy image. Then, the amplitude and phase information are simultaneously used as input of proposed improved convolutional neural network for denoising. Finally, the monogenic wavelet inverse transform is used to obtain the denoised image. The experimental results illustrate that the proposed algorithm achieves superior performance both in visual quality and objective peak signal-to-noise ratio values, compared with other state-of-the-art de-noising algorithms. [ABSTRACT FROM AUTHOR]

Landslides, widespread and highly dangerous geological disasters, pose significant risks to humankind and the ecological environment. Consequently, predicting landslides is vital for disaster prevention and mitigation strategies. At present, the predominant methods for predicting landslide susceptibility are evolving from conventional machine learning techniques to deep learning approaches. At present, the predominant methods for predicting landslide susceptibility are evolving from conventional machine learning techniques to deep learning approaches. Prior studies have shown that in the context of landslide susceptibility, these models frequently underperform relative to tree-based machine learning algorithms. This shortcoming has restricted the application of deep learning in this domain. To overcome this challenge, this study presents the TabNet algorithm, which combines the interpretability and selective feature extraction of tree models with the representation learning and comprehensive training capabilities of neural network models. This paper explores the potential of employing the TabNet algorithm for landslide susceptibility analysis in China's WanZhou region and evaluates its performance against traditional machine learning techniques. The experimental data indicate that the TabNet algorithm achieves a recall score of 0.898 and an AUC of 0.915, demonstrating a generalization capability that is comparable to that of classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

This paper presents novel way to achieve fast and accurate Artificial Neural Network (ANN) modeling of Radio Frequency (RF) front end Low Noise Amplifier (LNA). Multilayer perceptron neural network is implemented to model high gain, ultra-low noise pseudomorhic High Electron Mobility Transistor (pHEMT) based LNA. Datasets are developed for input and output that is obtained from the Electro-Magnetic simulator. Different neural networks such as PatternNet, FitNet, and CascadeForwardNet with different algorithms are trained, tested, and compared to learn the behavior of the amplifier, and the best model is analyzed. Neural networks are modeled for LNA S-parameters and NF. It is observed that greater than 99% accuracy is achieved for PatternNet Bayesian regularization algorithm with less number of hidden layers and also it is found that the simulation results are almost similar to the developed ANN. [ABSTRACT FROM AUTHOR]

Due to the continuous development of neural network technology, it has been widely applied in fields such as autonomous driving and biomedicine. However, adversarial attacks can significantly degrade the performance and reliability of neural networks, making defending against such attacks a crucial research area. In this paper, we propose a robust U-Net and adversarial generative network-based defense method, training the target model on a clean training set without adversarial samples. Firstly, we train the target neural network on a clean training set. Then, we train the robust U-Net using the clean training set, employing reparameterization and random noise to resist adversarial perturbations. To supervise the quality of transformed images, we employ the adversarial generative network, utilizing the RU-Net as the generator and a discriminator to ensure the quality of generated images. Finally, we use the transformed images to retrain the target neural network, obtaining a robust neural network model capable of defending against adversarial attacks. Experimental evaluations on CIFAR-10 and Tiny Image Net demonstrate the effectiveness of our method in countering adversarial attacks and enhancing neural network robustness. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative and effective approach called the ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine algorithm is used to extract and optimize features in order to only select the most descriptive ones. Second, to further improve the capability, thereby providing the highest accuracy performance, the newly gathered dataset is introduced as input to an ensemble learning paradigm, which merges the benefits of boosting and bagging techniques with an artificial neural network classifier. The essential goal of the developed proposal is to discriminate between the diverse operating conditions (one healthy and six faulty conditions). Three potential and frequent types of faults that can affect the system behaviors including short-circuit, open-circuit, and wear-out are considered and thereby injected at diverse locations and sides (grid and generator sides) in order to evaluate the availability and performance of the proposed technique when compared to the conventional FDD methods. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. The acquired outcomes demonstrate the efficiency of the suggested diagnostic paradigm compared to conventional FDD techniques (accuracy rate has been successfully achieved 98.35%). [ABSTRACT FROM AUTHOR]