Search

In view of the issue that the features of the images in the shallow layer cannot be fully utilized when the image description is generated and the target association of the image cannot be sufficiently obtained, a generation method for the description of the acquisition of attention images is put forward in this paper. The proportions of the features of images at various depths are autonomously assigned based on the content data of the language model, and the images thus generated are all pictures with image features with attention. In this way, the effect of description generation of images has been improved. After the testing of the database, the results indicate that the calculation method of the algorithm put forward in this paper is more accurate than the top-down multimedia image algorithm generated by a single attention. [ABSTRACT FROM AUTHOR]

Blade icing seriously affects wind turbines' aerodynamic performance and output power. Timely and accurately predicting blade icing status is crucial to improving the economy and safety of wind farms. However, existing blade icing prediction methods cannot effectively solve the problems of unbalanced icing/non-icing data and low prediction accuracy. In order to solve the above problems, this paper proposes a wind turbine blade icing prediction method based on the focal loss function and CNN-Attention-GRU. First, the recursive feature elimination method combined with the physical mechanism of icing is used to extract features highly correlated with blade icing, and a new feature subset is formed through a sliding window algorithm. Then, the focal loss function is utilized to assign more weight to the ice samples with a lower proportion, addressing the significant class imbalance between the ice and non-ice categories. Finally, based on the CNN-Attention-GRU algorithm, a blade icing prediction model is established using continuous 24-h historical data as the input and the icing status of the next 24 h as the output. The model is compared with advanced neural network models. The results show that the proposed method improves the prediction accuracy and F1 score by an average of 6.41% and 4.27%, respectively, demonstrating the accuracy and effectiveness of the proposed method. [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]

With the increasing demand for security in many fastest growing applications, biometric recognition is the most prominent authentication system. User authentication through speech and face recognition is the important biometric technique to enhance the security. This paper proposes a speech and facial feature-based multi-modal biometric recognition technique to improve the authentication of any system. Mel Frequency Cepstral Coefficients (MFCC) is extracted from audio as speech features. In visual recognition, this paper proposes cascade hybrid facial (visual) feature extraction method based on static, dynamic and key-point salient features of the face and it proves that the proposed feature extraction method is more efficient than the existing method. In this proposed method, Viola–Jones algorithm is used to detect static and dynamic features of eye, nose, lip, Scale Invariant Feature Transform (SIFT) algorithm is used to detect some stable key-point features of face. In this paper, a research on the audio-visual integration method using AND logic is also made. Furthermore, all the experiments are carried out using Artificial Neural Network (ANN) and Support Vector Machine (SVM). An accuracy of 94.90% is achieved using proposed feature extraction method. The main objective of this work is to improve the authenticity of any application using multi-modal biometric features. Adding facial features to the speech recognition improve system security because biometric features are unique and combining evidence from two modalities increases the authenticity as well as integrity of the system. [ABSTRACT FROM AUTHOR]

Intelligent video analysis has broad application prospects. How to automatically analyze and identify human behavior in video has attracted extensive attention from researchers at home and abroad. Moreover, researching effective video behavior recognition algorithms and designing efficient behavior recognition systems has important theoretical and practical value. This paper studies the nonlinear classification technique and applies the video behavior recognition algorithm to basketball recognition. Moreover, this paper studies the classical convolutional neural network model and several improvements. In addition, this paper explains the advantages of convolutional neural networks in feature extraction compared with traditional neural networks and analyzes the performance of the algorithm by designing actual experiments. The research results show that the algorithm can quickly identify multiple players on the field, and the method can effectively deal with occlusion and other issues with high accuracy and real-time. [ABSTRACT FROM AUTHOR]

To ensure the safe operation of highway traffic lines, given the imperfect feature extraction of existing road pit defect detection models and the practicability of detection equipment, this paper proposes a lightweight target detection algorithm with enhanced feature extraction based on the YOLO (You Only Look Once) algorithm. The BIFPN (Bidirectional Feature Pyramid Network) network structure is used for multi-scale feature fusion to enhance the feature extraction ability, and Varifocal Loss is used to optimize the sample imbalance problem, which improves the accuracy of road defect target detection. In the evaluation test of the model in the constructed PCD1 (Pavement Check Dataset) dataset, the mAP@.5 (mean Average Precision when IoU = 0.5) of the BV-YOLOv5S (BiFPN Varifocal Loss-YOLOv5S) model increased by 4.1%, 3%, and 0.9%, respectively, compared with the YOLOv3-tiny, YOLOv5S, and B-YOLOv5S (BiFPN-YOLOv5S; BV-YOLOv5S does not use the Improved Focal Loss function) models. Through the analysis and comparison of experimental results, it is proved that the proposed BV-YOLOv5S network model performs better and is more reliable in the detection of pavement defects and can meet the needs of road safety detection projects with high real-time and flexibility requirements. [ABSTRACT FROM AUTHOR]

Twitter is a social networking platform that has become popular in recent years. It has become a versatile information dissemination tool used by individuals, businesses, celebrities, and news organizations. It allows users to share messages called tweets with one another. These messages can contain different types of information from personal opinions of users, advertisement of products belonging to all kinds of businesses to the news. Tweets can also contain messages that are racist, bigotry, offensive, and of extremist views as shown by research. Manual identification of such tweets is impossible as hundreds of millions of tweets are posted every day and hence a solution to automate the identification of these types of tweets through classification is required for the Twitter administrators or an intelligence and security analyst. This paper presents a comparative study of traditional machine learning algorithms and deep learning algorithms for the task of tweet classification to detect different categories of abusive languages with the aim to determine which algorithm performs best in detecting abusive language that is prevalent on social media. Two approaches for building feature vectors were explored. Feature vectors based on the bag-of-words method and feature vectors based on word embeddings. These two methods of feature representation were evaluated in this paper using tweet messages representing five abusive language categories. The experiments show that the deep learning algorithms trained with word embeddings outperformed all the other machine learning algorithms that were trained with feature vectors based on the bag-of-words approach. [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]

Fuzzy English recognition is affected by many factors, which leads to certain accuracy problems in intelligent recognition results. In order to improve the automatic recognition efficiency of fuzzy English, based on machine learning technology, this study constructs a neural network model. At the same time, this paper analyzes the research status and existing problems of handwritten character recognition, analyzes the model, and adopts multiple modules for automatic English recognition. In addition, the system is built on the basis of algorithms and model support, which makes fuzzy English recognition intelligent. Finally, in order to study the algorithm and model performance, the fuzzy English recognition is carried out through experiments. The research shows that the model constructed in this paper has certain recognition effect, which can be applied to practice, and can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

Compared with other applications in computer vision, convolutional neural networks (CNNs) have underperformed on pedestrian detection. A breakthrough was made very recently using sophisticated deep CNN (DCNN) models, with a number of handcrafted features or explicit occlusion handling mechanism. In this paper, we show that by reusing the convolutional feature maps of a DCNN model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labeling may be simply combined with a detector to boost the detection performance. By adding complementary handcrafted features such as optical flow, the DCNN-based detector can be further improved. We advance the state-of-the-art results by lowering the log-average miss rate from 11.7% to 8.9% on the Caltech data set and from 11.2% to 8.6% on the Inria data set. We also achieve a comparable result to state-of-the-art approaches on the KITTI data set. [ABSTRACT FROM AUTHOR]

Pipe burst events pose threats to the safety and stability of water supply networks. Deep learning models have been studied for burst location analysis in recent years, but the applicability of the methods needs further research to cope with different size and hydraulic status of pipe networks. A novel framework of burst area identification based on an improved DenseNet model is proposed in this paper. First, according to regional characteristics of hydraulic state caused by pipe burst events, pipe network is divided into monitoring areas. Then, a new model by fully linear DenseNet with attention mechanism (FA-DenseNet) is developed for effective feature extraction and burst area identification. Thirdly, Bayesian optimization algorithm is introduced to automatically optimize the hyperparameters of the deep learning model for better accuracy. The proposed framework was tested in a real-life example network with synthetic burst monitoring data, and the accuracy of burst area identification reaches 0.918. The model is also compared with a traditional BP neural network and a DenseNet model without attention mechanism, and the results show that FA-DenseNet is more robust with the respects of different pipe burst conditions, monitoring noise and the number of pressure monitoring points. The proposed framework provides water companies an applicable and effective method of pipe burst identification and inspection. [ABSTRACT FROM AUTHOR]

A variety of open relation extraction systems have been developed in the last decade. And deep learning, especially with attention model, has gained much success in the task of relation classification. Nevertheless, there is, yet, no research reported on classifying open relation tuples to our knowledge. In this paper, we propose a novel semieager learning algorithm (SemiE) to tackle the problem of open relation classification. Different from the eager learning approaches (e.g., ANNs) and the lazy learning approaches (e.g., kNN), the SemiE offers the benefits of both categories of learning scheme, with its significantly lower computational cost (O(n)). This algorithm can also be employed in other classification tasks. Additionally, this paper presents an adapted attention model to transform relation phrases into vectors by using word embedding. The experimental results on two benchmark datasets show that our method outperforms the state-of-the-art methods in the task of open relation classification. [ABSTRACT FROM AUTHOR]

To study the characteristics of license plate characters recognition, this paper proposes a method for feature extraction of license plate characters based on two-dimensional wavelet packet. We decompose license plate character images with two dimensional-wavelet packet and search for the optimal wavelet packet basis. This paper presents a criterion of searching for the optimal wavelet packet basis, and a practical algorithm. The obtained optimal wave- let packet basis is used as the feature of license plate character, and a BP neural network is used to classify the character. The testing results show that the proposed method achieved higher recognition rate than the traditional methods. [ABSTRACT FROM AUTHOR]

The key of classification diagnosis of diabetic retinopathy lies in the recognition of the features of small lesions, and it is difficult to extract the features of too small lesions by general extraction methods. In order to solve the problem that it is difficult to extract small focus, a hybrid attention mechanism combined with residual convolutional neural network model algorithm is proposed to improve the classification accuracy of diabetic retinopathy. Firstly, a multiscale deep learning network model with hybrid attention is designed, and then, the high-level features of images are extracted by using the network model; finally, after balancing different types of samples by sampling algorithm, the spatial attention and channel attention of the extracted features are enhanced; small-step learning strategy, loss function, and initial parameters are used to optimize the performance of the network model. The classifier based on multiscale hybrid attention network is used to judge the five classifications. Experimental results show that the proposed algorithm can learn more features of small targets and can effectively improve the classification performance of diabetic retina. An experimental test was performed on Kaggle's publicly available dataset of diabetic retinas, and the classification accuracy was 93.8%, compared to some existing classification models; the method proposed in this paper can achieve better classification results for diabetic retinopathy. [ABSTRACT FROM AUTHOR]

Due to lack of a central bureaucrat in mobile ad hoc networks, the security of the network becomes serious issue. During malicious attacks, according to the motivation of intruder the severity of the threat varies. It may lead to loss of data, energy or throughput. This paper proposes a lightweight Intruder Node Detection and Isolation Action mechanism (INDIA) using feature extraction, feature optimization and classification techniques. The indirect and direct trust features are extracted from each node and the total trust feature is computed by combining them. The trust features are extracted from each node of MANET and these features are optimized using Particle Swarm Optimization (PSO) algorithm as feature optimization technique. These optimized feature sets are then classified using Neural Networks (NN) classifier which identifies the intruder node. The performance of the proposed methodology is studied in terms of various parameters such as success rate in packet delivery, delay in communication and the amount of energy consumption for identifying and isolating the intruder. [ABSTRACT FROM AUTHOR]

Under-complete models, which derive lower dimensional representations of input data, are valuable in domains in which the number of input dimensions is very large, such as data consisting of a temporal sequence of images. This paper presents the under-complete product of experts (UPoE), where each expert models a one-dimensional projection of the data. Maximum-likelihood learning rules for this model constitute a tractable and exact algorithm for learning under-complete independent components. The learning rules for this model coincide with approximate learning rules proposed earlier for under-complete independent component analysis (UICA) models. This paper also derives an efficient sequential learning algorithm from this model and discusses its relationship to sequential independent component analysis (ICA), projection pursuit density estimation, and feature induction algorithms for additive random field models. This paper demonstrates the efficacy of these novel algorithms on high-dimensional continuous datasets. [ABSTRACT FROM AUTHOR]

An intrusion detection system is a security system that aims to detect sabotage and intrusions on networks to inform experts of the attack and abuse of the network. Different classification methods have been used in the intrusion detection systems such as fuzzy, genetic algorithms, decision trees, artificial neural networks, and support vector machines. Moreover, ensemble classifiers have shown more robust and effective performance for various tasks in the field. In this paper, we adopt ensemble models in order to improve the performance of intrusion detection and, at the same time, decrease the false alarm rate. We use kNN for multi-class classification, as well as SVM to approach the classification problem in normal-based detection. In order to combine multiple outputs, we use the Dempster–Shafer method in which there is the possibility of explicit retrieval of uncertainty. Moreover, we utilize deep learning for extracting features to train the samples, selected by the sample selection algorithm based on ensemble margin. We compare our results with state-of-the-art methods on benchmarking datasets such as UNSW-NB15, CICIDS2017, and NSL-KDD. Our proposed method indicates the superiority in terms of prominent metrics Accuracy, Precision, Recall, and F-measure. [ABSTRACT FROM AUTHOR]

This paper deals with image processing algorithm that gives a solution for the problem of medical image segmentation. Biological neural network is an artificial abstract model of different parts of the brain or nervous system, featuring essential properties of the system using biologically realistic models. Artificial Neura Networks (ANNs) have been developed for a wide range of applications such as image analysis, enhancement, segmentation, feature extraction and pattern recognition. Among these, image segmentation is more important as it is widely used for object recognition. The watershed transformation algorithm used for segmentation of blood vessels from angiographic images results in some faulty segmented pixels while the use of neural network technique increases the performance with occurrence of some errors. Artificial neural network results in improved quality of image segmentation reflecting the mean square error to be minimum. The proposed algorithm using the combination of morphological filters and back propagation neural network are used for extracting blood vessels from angiographic images of human heart as they have linear structure and Gaussian like profile. Results on various medical data from a set of normal patients are presented and show that this algorithm can be used as a robust segmentation tool. [ABSTRACT FROM AUTHOR]

Recently, demand for handwriting recognition, such as automation of mail sorting, license plate recognition, and electronic memo pads, has exponentially increased in various industrial fields. In addition, in the image recognition field, methods using artificial convolutional neural networks, which show outstanding performance, have been applied to handwriting recognition. However, owing to the diversity of recognition application fields, the number of dimensions in the learning and reasoning processes is increasing. To solve this problem, a principal component analysis (PCA) technique is used for dimensionality reduction. However, PCA is likely to increase the accuracy loss due to data compression. Therefore, in this paper, we propose a line-segment feature analysis (LFA) algorithm for input dimensionality reduction in handwritten text recognition. This proposed algorithm extracts the line segment information, constituting the image of input data, and assigns a unique value to each segment using 3 × 3 and 5 × 5 filters. Using the unique values to identify the number of line segments and adding them up, a 1-D vector with a size of 512 is created. This vector is used as input to machine-learning. For the performance evaluation of the method, the Extending Modified National Institute of Standards and Technology (EMNIST) database was used. In the evaluation, PCA showed 96.6% and 93.86% accuracy with k-nearest neighbors (KNN) and support vector machine (SVM), respectively, while LFA showed 97.5% and 98.9% accuracy with KNN and SVM, respectively. [ABSTRACT FROM AUTHOR]

After the development of deep learning object tracking methods in recent years, the fully convolutional siamese network object tracking algorithm SiamFC has become a more classic deep learning object tracking algorithm. In view of the problem that the accuracy of the tracking results of SiamFC will be reduced in the case of complex backgrounds, this paper introduces the attention mechanism based on the SiamFC, which performs channel and spatial weighting on the feature maps obtained by convolution of the input image. At the same time, the backbone network model of CNN in the algorithm is adjusted, then the siamese network combined with attention mechanism for object tracking is proposed. It can strengthen the effectiveness of the results of feature extraction and enhance the ability of the network model to discriminate targets. In this paper, the algorithm is tested on the OTB2015, VOT2016 and VOT2017 datasets, and compared with multiple object tracking algorithms. Experimental results show that the algorithm in this paper can better solve the complex background problem in object tracking, and has certain advantages compared with other algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we focus on tackling the problem of automatic accurate localization of detected objects in high-resolution remote sensing images. The two major problems for object localization in remote sensing images caused by the complex context information such images contain are achieving generalizability of the features used to describe objects and achieving accurate object locations. To address these challenges, we propose a new object localization framework, which can be divided into three processes: region proposal, classification, and accurate object localization process. First, a region proposal method is used to generate candidate regions with the aim of detecting all objects of interest within these images. Then, generic image features from a local image corresponding to each region proposal are extracted by a combination model of 2-D reduction convolutional neural networks (CNNs). Finally, to improve the location accuracy, we propose an unsupervised score-based bounding box regression (USB-BBR) algorithm, combined with a nonmaximum suppression algorithm to optimize the bounding boxes of regions that detected as objects. Experiments show that the dimension-reduction model performs better than the retrained and fine-tuned models and the detection precision of the combined CNN model is much higher than that of any single model. Also our proposed USB-BBR algorithm can more accurately locate objects within an image. Compared with traditional features extraction methods, such as elliptic Fourier transform-based histogram of oriented gradients and local binary pattern histogram Fourier, our proposed localization framework shows robustness when dealing with different complex backgrounds. [ABSTRACT FROM PUBLISHER]

A modified version of Boosted Mixture of Experts (BME) for low-resolution face recognition is presented in this paper. Most of the methods developed for low-resolution face recognition focused on improving the resolution of face images and/or special feature extraction methods that can deal effectively with low-resolution problem. However, we focused on the classification step of face recognition process in this paper. Using Neural Networks (NN) combinations is an efficient approach to deal with complex classification problems, such as the low-resolution face recognition which involves high-dimensional feature sets and highly overlapped classes. Mixture of Experts (ME) and boosting methods are two of the most popular and interesting NN combining methods, which have great potential for improving performance in classification. A modified combining approach based on both features of ME and boosting is presented in order to deal with this complex classification problem efficiently. Previous works [1,2] made attempts to incorporate the complementary features of boosting method in ME training algorithm to boost the performance. These approaches called Boosted Mixture of Experts (BME) have some drawbacks. Based on the analysis of the problems of previous approaches, some modifications are suggested in this paper. A modification in the pre-loading (initialization) procedure of ME is proposed to address the limitations of previous approaches and overcome them using a two stages pre-loading procedure. In our suggested approach, both the error and confidence measures are used as the difficulty criteria in boosting-based partitioning of the problem space. Regarding the nature of this approach, we call the proposed method Boosted Pre-loaded Mixture of Experts (BPME). The proposed method is tested in a low-resolution face recognition problem and compared to the other variations of ME and boosting method. The experiments are conducted using low-resolution variations of two common face databases including the ORL and Yale databases. The experimental results show that BPME method has significant better recognition rates against the other compared combining methods in various tested conditions including different quality grades of face images and different sizes of the training set. [ABSTRACT FROM AUTHOR]

This paper presents a novel intelligent autoreclosure technique to discriminate temporary faults from permanent faults, and to accurately determine fault extinction time. A variety of fault simulations is carried out on a specified transmission line on the standard IEEE 9-bus electric power system by using MATLAB/SimPowerSytems. Prony analysis is employed to extract data features from each simulated fault. The fault identification prior to reclosing is accomplished by an artificial neural network trained by Levenberg Marquardt and resilient backpropagation algorithms, which are developed by using MATLAB. Some important parameters which strongly affect the entire training process are fine-tuned to their corresponding best values with the help of Taguchi's method. Test results show the robustness and efficacy of the proposed autoreclosure scheme. [ABSTRACT FROM AUTHOR]

A novel framework using a Bayesian approach for content-based phishing web page detection is presented. Our model takes into account textual and visual contents to measure the similarity between the protected web page and suspicious web pages. A text classifier, an image classifier, and an algorithm fusing the results from classifiers are introduced. An outstanding feature of this paper is the exploration of a Bayesian model to estimate the matching threshold. This is required in the classifier for determining the class of the web page and identifying whether the web page is phishing or not. In the text classifier, the naive Bayes rule is used to calculate the probability that a web page is phishing. In the image classifier, the earth mover's distance is employed to measure the visual similarity, and our Bayesian model is designed to determine the threshold. In the data fusion algorithm, the Bayes theory is used to synthesize the classification results from textual and visual content. The effectiveness of our proposed approach was examined in a large-scale dataset collected from real phishing cases. Experimental results demonstrated that the text classifier and the image classifier we designed deliver promising results, the fusion algorithm outperforms either of the individual classifiers, and our model can be adapted to different phishing cases. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel feature-based neural network (NN) approach for estimation of blood pressure (BP) from wrist oscillometric measurements. Unlike previous methods that use the raw oscillometric waveform envelope (OMWE) as input to the NN, in this paper, we propose to use features extracted from the envelope. The OMWE is mathematically modeled as a sum of two Gaussian functions. The optimum parameters of this model are found by minimizing the least squares error between the model and the OMWE using the Levenberg–Marquardt algorithm and are used as features. Two separate feed-forward NNs (FFNNs) are then designed to estimate the systolic and diastolic BPs using these features. The FFNNs are trained using the resilient backpropagation learning algorithm and tested on a data set of BP measurements recorded from 85 subjects. The performance is then compared with that of the conventional maximum amplitude algorithm, adaptive neuro-fuzzy inference system, and already published NN-based methods. It is found that the proposed approach achieves lower values of mean absolute error and standard deviation of error in the estimation of BP. In addition, the proposed approach has the following advantages: lower complexity with respect to the design parameters, smaller training data set, and lower computational load. [ABSTRACT FROM PUBLISHER]

The Industry 4.0 revolution is insisting strongly for use of machine learning-based processes and condition monitoring. In this paper, emphasis is given on machine learning-based approach for condition monitoring of shaft misalignment. This work highlights combined approach of artificial neural network and support vector machine for identification and measure of shaft misalignment. The measure of misalignment requires more features to be extracted under variable load conditions. Hence, primary objective is to measure misalignment with a minimum number of extracted features. This is achieved through normalization of vibration signal. An experimental setup is prepared to collect the required vibration signals. The normalized time domain nonstationary signals are given to discrete wavelet transform for features extraction. The extracted features such as detailed coefficient is considered for feature selection viz. Skewness, Kurtosis, Max, Min, Root mean square, and Entropy. The ReliefF algorithm is used to decide best feature on rank basis. The ratio of maximum energy to Shannon entropy is used in wavelet selection. The best feature is used to train machine learning algorithm. The rank-based feature selection has improved classification accuracy of support vector machine. The result obtained with the combined approach are discussed for different misalignment conditions. [ABSTRACT FROM AUTHOR]

Virtual network embedding arranges virtual network services onto substrate network components. The performance of embedding algorithms determines the effectiveness and efficiency of a virtualized network, making it a critical part of the network virtualization technology. To achieve better performance, the algorithm needs to automatically detect the network status which is complicated and changes in a time-varying manner, and to dynamically provide solutions that can best fit the current network status. However, most existing algorithms fail to provide automatic embedding solutions in an acceptable running time. In this paper, we combine deep reinforcement learning with a novel neural network structure based on graph convolutional networks, and propose a new and efficient algorithm for automatic virtual network embedding. In addition, a parallel reinforcement learning framework is used in training along with a newly-designed multi-objective reward function, which has proven beneficial to the proposed algorithm for automatic embedding of virtual networks. Extensive simulation results under different scenarios show that our algorithm achieves best performance on most metrics compared with the existing state-of-the-art solutions, with upto 39.6% and 70.6% improvement on acceptance ratio and average revenue, respectively. Moreover, the results also demonstrate that the proposed solution possesses good robustness. [ABSTRACT FROM AUTHOR]

Because of the hierarchical significance of traffic sign images, the traditional methods do not effectively control and extract the brightness and features of layered images. Therefore, an automatic recognition algorithm for traffic signs based on a convolution neural network is proposed in this paper. First, the histogram equalization method is used to pre-process the traffic sign images, with details of the images being enhanced and contrast of the images improved. Then, the traffic sign images are recognized by a convolution neural network and the large scale structure of information in the traffic sign images are obtained by using a hierarchical significance detection method based on graphical models. Next, the area of interest in the traffic sign images are extracted by using the hierarchical significance model. Finally, the Softmax classifier is selected to classify the input feature images to realize the automatic recognition of traffic signs. Experimental results show that the proposed algorithm can control the brightness of traffic sign images, which can accurately extract image regions of interest and complete the automatic recognition of traffic signs. [ABSTRACT FROM AUTHOR]

The shortage of training samples remains one of the main obstacles in applying the neural networks to the hyperspectral images classification. To fuse the spatial and spectral information, pixel patches are often utilized to train a model, which may further aggregate this problem. In the existing works, an artificial neural network (ANN) model supervised by centerloss (ANNC) was introduced. Training merely with spectral information, the ANNC yields discriminative spectral features suitable for the subsequent classification tasks. In this paper, we propose a novel convolutional neural network (CNN)-based spatial feature fusion (CSFF) algorithm, which allows a smart integration of spatial information to the spectral features extracted by ANNC. As a critical part of CSFF, a CNN-based discriminant model is introduced to estimate whether two pixels belong to the same class. At the testing stage, by applying the discriminant model to the pixel pairs generated by a test pixel and each of its neighbors, the local structure is estimated and represented as a customized convolutional kernel. The spectral–spatial feature is generated by a convolutional operation between the estimated kernel and the corresponding spectral features within a local region. The final label is determined by classifying the resulting spectral–spatial feature. Without increasing the number of training samples or involving pixel patches at the training stage, the CSFF framework achieves the state of the art by declining 20%–50% classification failures in experiments on three well-known hyperspectral images. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) using neural networks is an active research field with many applications to signal processing and data analysis. This paper presents a PCA neural network endowed with a novel learning algorithm, and an analysis of its features. As the basic discrete-time Oja's PCA neural network does not converge globally, it is important to derive a robust and globally convergent PCA learning algorithm. Based on previous works on the globally convergent PCA learning algorithm, a robust and globally convergent PCA learning algorithm is proposed in this paper. The behavior of this discrete-time learning algorithm is directly studied in this paper. We show that the algorithm is robust and globally convergent, The selection of the parameters of this algorithm will also be discussed in details. Finally, simulation results are provided to verify the theoretical results presented. Compared to other PCA learning algorithms, the proposed algorithm performs favorably in terms of robust stability, global convergence, speed and accuracy. [ABSTRACT FROM AUTHOR]

A fast target maneuver detecting and highly accurate tracking technique using a neural fuzzy network based on Kalman filter is proposed in this paper. In the automatic target tracking system, there exists an important and difficult problem: how to detect the target maneuvers and fast response to avoid miss-tracking? The traditional maneuver detection algorithms, such as variable dimension filter (VDF) and input estimation (IE) etc., are computation intensive and difficult to implement in real time. To solve this problem, neural network algorithms have been issued recently. However, the normal neural networks such as backpropagation networks usually produce the extra problems of low convergence speed and/or large network size. Furthermore, the way to decide the network structure is heuristic. To overcome these defects and to make use of neural learning ability, a developed standard Kalman filter with a self-constructing neural fuzzy inference network (KF-SONFIN) algorithm for target tracking is presented in this paper. By generating possible target trajectories including maneuver information to train the SONFIN, the trained SONFIN can detect when the maneuver occurred, the magnitude of maneuver values and when the maneuver disappeared. Without having to change the structure of Kalman filter nor modeling the maneuvering target, this new algorithm, SONFIN, can always find itself an economic network size with a fast learning process. Simulation results show that the KF-SONFIN is superior to the traditional IE and VDF methods in estimation accuracy. [ABSTRACT FROM AUTHOR]

Accurate recognition method of pitaya in natural environment provides technical support for automatic picking. Aiming at the intricate spatial position relationship between pitaya fruits and branches, a pitaya recognition method based on improved YOLOv4 was proposed. GhostNet feature extraction network was used instead of CSPDarkNet53 as the backbone network of YOLOv4. A structure of generating a large number of feature maps through a small amount of calculation was used, and the redundant information in feature layer was obtained with lower computational cost, which can reduce the number of parameters and computation of the model. Coordinate attention was introduced to enhance the extraction of fine-grained feature of targets. An improved combinational convolution module was designed to save computing power and prevent the loss of effective features and improve the recognition accuracy. The Ghost Module was referenced in Yolo Head to improve computing speed and reduce delay. Precision, Recall, F1, AP, detection speed and weight size were selected as performance evaluation indexes of recognition model. 8800 images of pitaya fruit in different environments were used as the dataset, which were randomly divided into the training set, the validation set and the test set according to the ratio of 7:1:2. The research results show that the recognition accuracy of the improved YOLOv4 model for pitaya fruit is 99.23%. Recall, F1 and AP are 95.10%, 98% and 98.94%, respectively. The detection speed is 37.2 frames⋅s-1, and the weight size is 59.4MB. The improved YOLOv4 recognition algorithm can meet the requirements for the accuracy and the speed of pitaya fruit recognition in natural environment, which will ensure the rapid and accurate operation of the picking robot. [ABSTRACT FROM AUTHOR]

In the large data environment, there are many problems in the parallel deep convolution neural network（DCNN） algorithm, such as excessive data redundancy, slow convolution layer operation and poor convergence of loss function. This paper proposed a parallel deep convolution neural network optimization algorithm based on the Im2 col method. First, the algorithm proposed a parallel feature extraction strategy based on Marr-Hildreth operator to extract target features from data as input of convolution neural network, which can effectively avoid the problem of excessive data redundancy. Secondly, the algorithm designed a parallel model training strategy based on the Im2 col method. The redundant convolution kernel is removed by designing the Mahalanobis distance center value, and the convolution layer operation speed is improved by combining the MapReduce and Im2 col methods. Finally, the algorithm proposed an improved small-batch gradient descent strategy, which eliminates the effect of abnormal data on the batch gradient and solves the problem of poor convergence of the loss function. The experimental results show that IA-PDCNNOA algorithm performs well in deep convolution neural network calculation under large data environment and is suitable for parallel DCNN model training of large datasets. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) recognition is an important tool for online monitoring of gas insulated switchgear (GIS) and diagnosing existing defects. At present, there are two different types of data patterns used for analysis and evaluation of PD signals: phase resolved partial discharge (PRPD) mode and time resolved partial discharge (TRPD) mode. Using different types of data patterns separately can lead to inconsistent or even conflicted recognition results, but the two types of data patterns having complementary information between each other can be used together for data fusion. Dempster-Shafer (DS) evidence theory is introduced to address the problem of evidence conflict and low fusion efficiency. First, two sub-networks for PD recognition are established and compared employing the back propagation neural network (BPNN) learning algorithm under the two modes respectively. Secondly, to minimize (with possible elimination of) the possibility of misclassification, a new fusion decision-making system for PD recognition is proposed on the basis of fusing the results from the sub-networks. Finally, extensive field experiments on two artificial defects are conducted in order to evaluate the performance of the proposed method in this paper. The classification results reveal that the proposed method significantly outperforms the ways of using only single type of data patterns. The method proposed in this paper reduces the uncertainty and effectively improves the credibility of diagnosis. [ABSTRACT FROM AUTHOR]

Movie trailers are usually extracted from the most exciting, interesting, or other noteworthy parts of the movies in order to attract the audience and persuade them to see the film. At present, hand-crafted movie trailers currently occupy almost all the filming market, which is costly and time-consuming. In this paper, we propose an embedded learning algorithm to generate movie trailers automatically without human interventions. Firstly, we use CNN to extract features of candidate frames from the film by a rank-tracing technique. Secondly, SURF algorithm is utilized to match the frames of the movie with the corresponding trailer, thus the labeled and unlabeled dataset are prepared. Thirdly, the mutual information theory is introduced into the embedded machine learning to formulate a new embedded classification algorithm and hence characterize similar key elements of the trailers. Finally, semi-supervised support vector machine is applied as the classifier to obtain the satisfactory key frames to produce the predicted trailers. By treating several famous movies and their manual handling trailers as the ground-truth, series of experiments are carried out, which indicate that our method is feasible and competitive, providing a good potential for promoting the rapid development of the film industry in terms of publicity, as well as providing users with possible solutions for filtering large amounts of Internet videos. [ABSTRACT FROM AUTHOR]

Object detection plays an important role in intelligent transportation systems and intelligent vehicles. Although the topic of object detection has been studied for decades, it is still challenging to accurately detect objects under complex scenarios. The contributing factors for challenges include diversified object and background appearance, motion blur, adverse weather conditions, and complex interactions among objects. In this paper, we propose a new convolutional neural network (CNN) model for traffic object detection, by using multi-scale local and global feature representation (MFR). The proposed model consists of two components: a region proposal network that generates candidate object regions and an object detection network that incorporates multi-scale features and global information, namely MFR-CNN. These two components are jointly optimized. Once the system is trained, it can detect real-world traffic objects accurately, especially small objects and heavily occluded objects. We evaluate the proposed method on four benchmark datasets, achieving consistent improvements over the state of the art. [ABSTRACT FROM AUTHOR]

Using spikes to represent and convey information, SNN is more biologically plausible than traditional artificial neural networks. However, a classical SNN has limited feature extraction ability due to the shallow network structure, leading to inferior classification performance to CNN especially on multi-class classification tasks such as object categorization. Inspired by the powerful convolutional structure of CNN, this paper proposed a SCSNN. By exploiting convolutional structures and dynamic impulse triggered property of biological neurons, the proposed SCSNN organized integrate-and-fire models in a convolutional fashion, and trained by a new surrogate gradient back-propagation algorithm directly. It validated the proposed SCSNN on the MNIST and Fashion-MNIST dataset respectively, obtaining superior performance to state-or-the-art SNN on both datasets. The classification accuracy reaches 99. 62% on the MNIST dataset, and 93. 52% on the Fashion-MNIST dataset, which verifies the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

This paper presents a neural network-based method to generate multiple images with different exposures from a single input low dynamic range (LDR) image for improved high dynamic range (HDR) imaging. The proposed algorithm consists of three steps: 1) 2-D histogram estimation; 2) neural network-based LDR images estimation; and 3) generation of an optimal set of differently exposed images. The proposed method first generates image features by estimating a patched-based 2-D histogram. The extracted features are used in an input layer of the neural network, which plays a role to select an optimal set of LDR images. A set of LDR images is generated using a curvature-based contrast enhancement method. Experimental results show that the proposed method can generate an optimal set of LDR images using neural network and provide improved HDR images. In addition, the proposed method can be implemented as a preprocessing step in most existing HDR frameworks. The proposed HDR approach is considered as a single-input method that gives almost the same performance to multiple image-based HDR method. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework. By analysing 3D saliency in the case of RGB images and depth images, the class-conditional mutual information is computed for measuring the dependence of deep features extracted using a convolutional neural network; then, the posterior probability of the RGB-D saliency is formulated by applying Bayes' theorem. By assuming that deep features are Gaussian distributions, a discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map. The Gaussian distribution parameters can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm. The experimental results on RGB-D images from the NLPR dataset and NJU-DS400 dataset show that the proposed model performs better than other existing models. [ABSTRACT FROM AUTHOR]

Following the great success of deep convolutional neural networks (CNNs) in computer vision, this paper proposes a complex-valued CNN (CV-CNN) specifically for synthetic aperture radar (SAR) image interpretation. It utilizes both amplitude and phase information of complex SAR imagery. All elements of CNN including input-output layer, convolution layer, activation function, and pooling layer are extended to the complex domain. Moreover, a complex backpropagation algorithm based on stochastic gradient descent is derived for CV-CNN training. The proposed CV-CNN is then tested on the typical polarimetric SAR image classification task which classifies each pixel into known terrain types via supervised training. Experiments with the benchmark data sets of Flevoland and Oberpfaffenhofen show that the classification error can be further reduced if employing CV-CNN instead of conventional real-valued CNN with the same degrees of freedom. The performance of CV-CNN is comparable to that of existing state-of-the-art methods in terms of overall classification accuracy. [ABSTRACT FROM PUBLISHER]

In this paper, we have proposed a novel methodology based on statistical features and different machine learning algorithms. The proposed model can be divided into three main stages, namely, preprocessing, feature extraction, and classification. In the preprocessing stage, the median filter has been used in order to remove salt-and-pepper noise because MRI images are normally affected by this type of noise, the grayscale images are also converted to RGB images in this stage. In the preprocessing stage, the histogram equalization has also been used to enhance the quality of each RGB channel. In the feature extraction stage, the three channels, namely, red, green, and blue, are extracted from the RGB images and statistical measures, namely, mean, variance, skewness, kurtosis, entropy, energy, contrast, homogeneity, and correlation, are calculated for each channel; hence, a total of 27 features, 9 for each channel, are extracted from an RGB image. After the feature extraction stage, different machine learning algorithms, such as artificial neural network, k -nearest neighbors' algorithm, decision tree, and Naïve Bayes classifiers, have been applied in the classification stage on the features extracted in the feature extraction stage. We recorded the results with all these algorithms and found that the decision tree results are better as compared to the other classification algorithms which are applied on these features. Hence, we have considered decision tree for further processing. We have also compared the results of the proposed method with some well-known algorithms in terms of simplicity and accuracy; it was noted that the proposed method outshines the existing methods. [ABSTRACT FROM AUTHOR]

In recent years, many alternative methodologies and techniques have been proposed to perform nondestructive inspection and maintenance operations of moving structures. In particular, ultrasonic techniques have shown to be very promising for automatic inspection systems. From the literature, it is evident that the neural paradigms are considered, by now, the best choice to automatically classify ultrasound data. At the same time, the most appropriate preprocessing technique is still undecided. The aim of this paper is to propose a new and innovative data preprocessing technique that converts real-valued ultrasonic data into complex-valued signals. This allows analysis using phase synchrony, a robust tool that has been previously employed in brain science for establishing robust features in noisy data. Synchrony estimation is achieved using complex extensions of empirical mode decomposition, a data-driven algorithm for detecting temporal scales, thus facilitating the modeling of nonlinear and nonstationary signal dynamics. Experimental tests aiming to detect defective areas in composite materials are reported, and the effectiveness of the proposed methodology is illustrated. [ABSTRACT FROM PUBLISHER]

The image sensor-based target identification is one of the important for vehicle identification and intelligent transportation applications. Based on neural network classification algorithms, one vehicle identification method is proposed. The main work includes: (1) designing the parameter extraction of vehicle shape based on Sobel operator and mathematical morphology; (2) introducing a vehicle feature extraction method based on "I"-shape model; (3) designing a momentum backpropagation algorithm with the smallest error and a variable learning rate of an exponential function, verify the algorithm by simulation experiments. The proposed algorithm combines the advantages of the algorithm with additional momentum and variable learning rate while the convergence speed is accelerated and jumps out of local minimum points. The results of simulation experiments show that the proposed algorithm can quickly and effectively identify the various types of vehicle models. [ABSTRACT FROM AUTHOR]

Feature technology is considered an essential tool for integrating design and manufacturing. Automatic feature recognition (AFR) has provided the greatest contribution to fully automated computer-aided process planning system development. The objective of this paper is to review approaches based on application of artificial neural networks for solving major AFR problems. The analysis presented in this paper shows which approaches are suitable for different individual applications and how far away we are from the formation of a general AFR algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a novel intelligent autoreclosure technique to discriminate temporary faults from permanent faults and accurately determine fault extinction time. A variety of fault simulations are carried out on a specified transmission line on the standard IEEE 9-bus electric power system using MATLAB/SimPowerSytems. FFT and Prony analysis methods are employed to extract data features from each simulated fault. The fault identification prior to reclosing is accomplished by an artificial neural network trained by standard Error Back-Propagation, Levenberg Marquardt, and Resilient Back-Propagation algorithms which are developed using MATLAB. Some important parameters which strongly affect the entire training process are fine tuned with Taguchi's method to their corresponding best values. The robustness of the developed ANN identifier is verified by testing it with the data patterns which consists of high impedance faults obtained from IEEE 14-bus benchmark system. Test results show the efficacy of the proposed AR scheme. [ABSTRACT FROM AUTHOR]

This paper presents the Visual Attention Engine (VAE), which is a digital cellular neural network (CNN) that executes the VA algorithm to speed up object-recognition. The proposed time-multiplexed processing element (TMPE) CNN topology achieves high performance and small area by integrating 4800 (80\,\times\,60) cells and 120 PEs. Pipelined operation of the PEs and single-cycle global shift capability of the cells result in a high PE utilization ratio of 93%. The cells are implemented by 6T static random access memory-based register files and dynamic shift registers to enable a small area of 4.5 mm^2. The bus connections between PEs and cells are optimized to minimize power consumption. The VAE is integrated within an object-recognition system-on-chip (SoC) fabricated in the 0.13-\mum complementary metal-oxide—semiconductor process. It achieves 24 GOPS peak performance and 22 GOPS sustained performance at 200 MHz enabling one CNN iteration on an 80\,\times\,60 pixel image to be completed in just 4.3 \mus. With VA enabled using the VAE, the workload of the object-recognition SoC is significantly reduced, resulting in 83% higher frame rate while consuming 45% less energy per frame without degradation of recognition accuracy. [ABSTRACT FROM AUTHOR]

A modified Hopfield neural network with a novel cost function was presented for detecting wood defects boundary in the image. Different from traditional methods, the boundary detection problem in this paper was formulated as an optimization process that sought the boundary points to minimize a cost function. An initial boundary was estimated by Canny algorithm first. The pixel gray value was described as a neuron state of Hopfield neural network. The state updated till the cost function touches the minimum value. The designed cost function ensured that few neurons were activated except the neurons corresponding to actual boundary points and ensured that the activated neurons are positioned in the points which had greatest change in gray value. The tools ofMatlab were used to implement the experiment. The results show that the noises of the image are effectively removed, and our method obtains more noiseless and vivid boundary than those of the traditional methods. [ABSTRACT FROM AUTHOR]

Copyright of Revista Brasileira de Medicina do Esporte is the property of Redprint Editora Ltda. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)