Search

Developers in large software development environments rely on bug reports to complete fixes. Since reporters may use different representations to describe the same bug due to different expression habits, automated detection of duplicate bug reports can reduce development redundancy as well as maintenance costs. Recent detection of repetitive bug reports tends to use deep neural networks and considers both structured and unstructured information to generate hybrid representation features. In order to obtain the features of unstructured information of bug reports more effectively, this paper proposes a D＿BBAS(Doc2 Vec and BERT BiLSTM-Attention Similarity) method, which trains a feature extraction model based on a large-scale bug report library to generate a bug summary text representation set and a bug description text representation set that can reflect deep semantic information. Then, these two distributed representation sets compute the similarity of bug report pairs, resulting in two new similarity features. These two new features will participate in the detection of duplicate bug reports when combined with the traditional features generated based on structured information. In this paper, the effectiveness of the proposed approach is verified on the bug report repositories of well-known open-source projects Eclipse, NetBeans and Open Office, which contain more than 500, 000 bug reports. The experimental results show that compared with the representative methods, the method in this paper improves the F1 value by 1.7% on average, which proves the effectiveness of the method in this paper. [ABSTRACT FROM AUTHOR]

This paper proposed a new network framework for RGB-D salient object detection (SR-Net). In order to effectively integrate the complementarity of multi-model features, this paper took the depth feature extraction as an independent branch, use the Convolutional Block Attention Module (CBAM) to enhance the depth feature, and integrate the complementary information of the enhanced depth feature and RGB feature. Then, in order to remove feature redundancy and reduce the interference of background noise on the prediction results, it proposed a sequential refining network in the up-sampling network, that is, first, the primary global features are obtained by integrating the complementarity of multi-level and multiscale features, and used the Primary Global Feature Weight Matrix Acquisition Module (PFW) which based on the channel weight to obtains the weight matrix of the primary global feature, and then uses the obtained weight matrix to refine the features of each level to suppress the interference which caused by background noise. Finally, in order to better optimize the whole network, it proposed a new loss function. The experimental results on four public datasets show that the model is superior to nine advanced methods in different model evaluation indexes, and achieves more advanced performance. [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]

Objectives: The scale of buildings and their distribution is key indicators to measure the economic and social development of a region. Therefore, it is significant to study the extraction of buildings based on remote sensing images. Existing neural network methods still have shortcomings in the completeness of building extraction and the accuracy of building edges. To solve the above problems, this paper proposes a multi-level feature fusion network (MFFNet) based on high-resolution images. Methods: Firstly, we use edge detection operators to improve the ability of the network to recognize the boundaries of buildings. Secondly, we use a multi-path convolution fusion module to extract building features from multiple dimensions, and introduce a large receptive field convolution module to break through feature extraction. The process is limited by the size of the receptive field. After fusing the extracted features, the convolutional attention module is used to compress them, and the global features are further mined by pyramid pooling, so as to achieve high-precision extraction of buildings. Results: The current mainstream UNet, pyramid scene parsing network (PSPNet),multi attending path neural network (MAPNet) and multiscale-feature fusion deep neural networks with dilated convolution (MDNNet) are used as the comparison methods, and we use Wuhan University Aerial Image Dataset, Satellite Dataset II (East Asia) and Inria Aerial Image Dataset as experimental data for testing. Compared with the other four methods, MFFNet improves intersection over union, precision, recall, F1-score and mean average precision by 1.53%, 2.65%, 2.41%, 3.32% and 1.19% on average, achieves a better effect. Conclusions: MFFNet not only accurately captures the detail features of buildings, but also strengthens the extraction and utilization of global features. It has better ex‐ traction effect on large buildings and buildings in complex environment. [ABSTRACT FROM AUTHOR]

The distributed denial of service ( DDoS) attack detection method in traditional software defined network ( SDN ) requires frequent communication between the control plane and the data plane, which will lead to significant overhead and delay, and the current programmable data plane can not implement complex detection algorithms, so it is difficult to ensure high detection efficiency. To solve the above problems, this paper proposed a DDoS attack detection method based on programming protocol-independent packet processors ( P4 ) programmable data plane. First of all, the method used the improved information entropy based on P4 as initial detection to determine whether suspicious traffic occurred . Then, it took advantage of the microsecond time required for feature extraction by P4 to extract the six-tuple features of suspicious traffic, and imported them into the data standardization-deep neural network ( DS-DNN ) reinspection module to determine whether they were DDoS attack traffic . Finally, it tested the evaluation indicators of the method in the real environment. The experimental results show that this method can better detect DDoS attacks in SDN environments, ensure high detection rate and accuracy, effectively reduce the false alarm rate, and shorten the detection time to millisecond level. [ABSTRACT FROM AUTHOR]

In the field of tumor diagnosis, the AI-assisted diagnosis system can accurately distinguish tumor attributes and malignant tumor stages, thereby prolonging the survival time of patients. Taking breast tumor as an example, this paper proposes an artificial intelligence-assisted diagnosis model based on supervised learning to solve the problem of overfitting caused by the large amount of data in the feature extraction process. When extracting features, effective feature dimensionality reduction is achieved by introducing hierarchical clustering analysis, and the classified feature data is used as the feature input of the artificial neural network model, so as to realize the effective training of the classifier. The experimental results show that the accuracy and AUC value of the proposed algorithm are improved compared with the control algorithm, indicating that the model can not only solve the problem of overfitting caused by the description of massive feature regions, but also enhance the generalization of the artificial intelligence-aided diagnosis system. The ability to achieve high-precision differentiation of mammography-targeted breast tumors. [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]

To improve the correct rate of image classification by convolutional neural network, this paper proposed a multimodel fusion convolutional neural network after research on the network structure. By extracting the output feature vectors of a single model and then fusing them, it obtained the new output feature vectors, and then set up a single classifier to classify the images, and improved the accuracy of the classification. By comparing the classification accuracy of single model and multimodel fusion, the class ification accuracy of multi-model fu sion convolutional neural network was improved. This paper analyzed the weight distribution of the last layer of the convolutional neural network, and found that the weight distribution curve of the same model on different data sets was similar and the weight distribution curve of the network model with better classification effect was more gentle. [ABSTRACT FROM AUTHOR]

Due to the irregular features of the airport pavement cracks with variable shapes，narrow widths， different lengths，and free⁃form spatial trends，the existing algorithms perform not well. To solve this problem，this paper constructs a neural network model based on deformable convolution and feature fusion （DFNet）. Firstly， the deformable convolution module is used to enhance the learning of fracture morphological characteristics by feature extraction network. Secondly，the multi⁃scale convolution module captures the global information of the fracture under different receptive fields. Finally，the feature fusion module is used to extract the characteristics of different levels of the fracture，through combining low⁃level and high⁃level features of cracks to achieve accurate segmentation of cracks on airport pavements. On the collected actual airport pavement crack data set，comparative experiments are carried out with other six existing algorithms. The proposed algorithm reaches 90.95% on the F1⁃Score of pixel⁃level segmentation， which is better than those of all other compared algorithms. The DFNet algorithm improves the ability of detecting cracks in airport pavements. Experimental results show that the proposed algorithm better meets the actual engineering requirements. [ABSTRACT FROM AUTHOR]

At present,the vibration signal recognition algorithm for national musical instrument plate has the shortcomings of complex feature extraction and time-consuming. To solve this problem,this paper proposed a classification algorithm of wood vibration signal based on convolution neural network,to identify the quality of the musical instrument. Convolution neural network combined feature extraction and classification process to train the neural network, which owned the advantages of high recognition rate and good robustness. Firstly,this paper mainly analyzed and discussed spectrogram characteristics of the extraction of wood vibration signals. Then combining convolution neural network and grid search method, it could adjust the parameters. In order to avoid over-fitting,it obtained the final classification results by using new technologies such as ReLU and dropout. The experiments show that the accuracy of the test sample reaches 96% , which is obviously better than the traditional method. This method can reduce the error of manual measurement and speed up the selection time of the plate,and provide a more convenient method for the selection of the national musical instrument manufacturing field. [ABSTRACT FROM AUTHOR]

With the rapid development of Internet technology, sensitive content images have changed from basic concealed content exchange to mass data sharing. The traditional method of sensitive content detection based on image feature extraction is no longer applicable. To overcome these difficulties, this paper proposed a sensitive content detection method based on sparse semantics and double-layer deep convolution neural network. In this method, the upper network preprocessed the training samples and constructed sparse semantic representation of the image as the input of the neural network, while the lower network further considered the third-party control mechanism (such as government agents) and proposed a sensitive content image detection method for specific groups. Compared with the existing image detection methods for sensitive content, this method can effectively reduce the number of training samples, and the detection accuracy is more than 7% higher than that of traditional image detection methods ( such as visual word bag method). [ABSTRACT FROM AUTHOR]

The traditional sentence classification model has many disadvantages such as complex feature extraction process and low classification accuracy. This paper used the advantages of the popular deep learning model based convolutional neural network in feature extraction, combined with the traditional sentence classification method, proposed a sentence classification model based on convolutional neural network and Bayesian classifier. The model first used convolutional neural network to extract text features, and secondly used principal component analysis method to reduce the dimensionality of text features. Finally, Bayesian classifier were used to classify sentences. The experimental results show that on Cornell University's public film review dataset and Stanford Sentiment Treebank dataset, the proposed model is superior to the model using only deep learning or the traditional sentence classification model. [ABSTRACT FROM AUTHOR]

To improve the accuracy of the pedestrian detection method. this paper proposed a rectangular input of convolution neural network enhance the new pedestrian detection method based on the depth residual network and YOLO object detection method. The rectangular input helped the model gain the pedestrian characteristics expression by analyzing the expression and distribution characteristics of pedestrians in the images. The depth residual network with pre-activation for YOLO object detection improved the feature extraction ability through more layers of convolution neural networks. Hybrid dataset training and cluster anchor boxes could also improve the pedestrian detection performance. Hie test results of INRIA dataset prove that the method has better detection performance than the popular pedestrian detection methods, the index of false positive per image can reduce to 13.86% .improving ranging from 1.51% to 58. 62% in varying degrees. [ABSTRACT FROM AUTHOR]

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying batch normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93. 50%and 68. 32%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition. [ABSTRACT FROM AUTHOR]

Since the convolution neural network needs to input a fixed size image when performing image processing, this will lead to the loss of most of the original information in the scaling process. In addition, the feature extraction of images will not be put in place when the network has only one structure. To solve the above two problems, this paper presented a face detection algorithm combining cascade convolution neural network and spatial pyramid pooling. In this method, it cascaded three different convolution neural network models, the structure of which were from simple to complex, and extracted different face features at different levels to complete the detection of the face areas of images. At the same time, it added the pyramid pool at each level of the network, and this pooling strategy did not require a fixed size input, increasing dimension selection of model input. Compared with the traditional method, this method realizes the multi-scale input of the model, improves the detection performance, and reduces the time of face detection in the standard face data set. [ABSTRACT FROM AUTHOR]