Journal articles on the topic 'Convolutional model'
To see the other types of publications on this topic, follow the link: Convolutional model.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Convolutional model.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sarada, N., and K. Thirupathi Rao. "A Neural Network Architecture Using Separable Neural Networks for the Identification of “Pneumonia” in Digital Chest Radiographs." International Journal of e-Collaboration 17, no. 1 (January 2021): 89–100. http://dx.doi.org/10.4018/ijec.2021010106.
Full textAbstract:
In recent years, convolutional neural networks had a wide impact in the fields of medical image processing. Image semantic segmentation and image classification have been the main challenges in this field. These two techniques have been seeing a lot of improvement in medical surgeries which are being carried out by robots and autonomous machines. This work will be working on a convolutional model to detect pneumonia in a given chest x-ray scan. In addition to the convolution model, the proposed model consists of deep separable convolution kernels which replace few convolutional layers; one main advantage is these take in a smaller number of parameters and filters. The described model will be more efficient, robust, and fine-tuned than previous models developed using convolutional neural networks. The authors also benchmarked the present model with the CheXnet model, which almost predicts over 16 abnormalities in the given chest-x-rays.
2
Dang, Lanxue, Peidong Pang, Xianyu Zuo, Yang Liu, and Jay Lee. "A Dual-Path Small Convolution Network for Hyperspectral Image Classification." Remote Sensing 13, no. 17 (August 27, 2021): 3411. http://dx.doi.org/10.3390/rs13173411.
Full textAbstract:
Convolutional neural network (CNN) has shown excellent performance in hyperspectral image (HSI) classification. However, the structure of the CNN models is complex, requiring many training parameters and floating-point operations (FLOPs). This is often inefficient and results in longer training and testing time. In addition, the label samples of hyperspectral data are limited, and a deep network often causes the over-fitting phenomenon. Hence, a dual-path small convolution (DPSC) module is proposed. It is composed of two 1 × 1 small convolutions with a residual path and a density path. It can effectively extract abstract features from HSI. A dual-path small convolution network (DPSCN) is constructed by stacking DPSC modules. Specifically, the proposed model uses a DPSC module to complete the extraction of spectral and spectral–spatial features successively. It then uses a global average pooling layer at the end of the model to replace the conventional fully connected layer to complete the final classification. In the implemented study, all convolutional layers of the proposed network, except the middle layer, use 1 × 1 small convolution, effectively reduced model parameters and increased the speed of feature extraction processes. DPSCN was compared with several current state-of-the-art models. The results on three benchmark HSI data sets demonstrated that the proposed model is of lower complexity, has stronger generalization ability, and has higher classification efficiency.
3
Xu, Hongyan, Xiu Su, Yi Wang, Huaiyu Cai, Kerang Cui, and Xiaodong Chen. "Automatic Bridge Crack Detection Using a Convolutional Neural Network." Applied Sciences 9, no. 14 (July 18, 2019): 2867. http://dx.doi.org/10.3390/app9142867.
Full textAbstract:
Concrete bridge crack detection is critical to guaranteeing transportation safety. The introduction of deep learning technology makes it possible to automatically and accurately detect cracks in bridges. We proposed an end-to-end crack detection model based on the convolutional neural network (CNN), taking the advantage of atrous convolution, Atrous Spatial Pyramid Pooling (ASPP) module and depthwise separable convolution. The atrous convolution obtains a larger receptive field without reducing the resolution. The ASPP module enables the network to extract multi-scale context information, while the depthwise separable convolution reduces computational complexity. The proposed model achieved a detection accuracy of 96.37% without pre-training. Experiments showed that, compared with traditional classification models, the proposed model has a better performance. Besides, the proposed model can be embedded in any convolutional network as an effective feature extraction structure.
4
Yan, Jing, Tingliang Liu, Xinyu Ye, Qianzhen Jing, and Yuannan Dai. "Rotating machinery fault diagnosis based on a novel lightweight convolutional neural network." PLOS ONE 16, no. 8 (August 26, 2021): e0256287. http://dx.doi.org/10.1371/journal.pone.0256287.
Full textAbstract:
The advancement of Industry 4.0 and Industrial Internet of Things (IIoT) has laid more emphasis on reducing the parameter amount and storage space of the model in addition to the automatic and accurate fault diagnosis. In this case, this paper proposes a lightweight convolutional neural network (LCNN) method for intelligent fault diagnosis of rotating machinery, which can largely satisfy the need of less parameter amount and storage space as well as high accuracy. First, light-weight convolution blocks are constructed through basic elements such as spatial separable convolutions with the aim to effectively reduce model parameters. Secondly, the LCNN model for the intelligent fault diagnosis is constructed via lightweight convolution blocks instead of the tradi-tional convolution operation. Finally, to address the “black box” problem, the entire network is visualized through Tensorboard and t-distribution stochastic neighbor embedding. The results demonstrate that when the number of lightweight convolutional blocks reaches 6, the diagnosis accuracy of the LCNN model exceeds 99.9%. And the proposed model has become the most robust with parameters significantly decreasing. Furthermore, the proposed LCNN model has realized accurate, automatic, and robust fault diagnosis of rotating machinery, which makes it more suitable for deployment under the IIoT context.
5
Wang, Wei, Yiyang Hu, Ting Zou, Hongmei Liu, Jin Wang, and Xin Wang. "A New Image Classification Approach via Improved MobileNet Models with Local Receptive Field Expansion in Shallow Layers." Computational Intelligence and Neuroscience 2020 (August 1, 2020): 1–10. http://dx.doi.org/10.1155/2020/8817849.
Full textAbstract:
Because deep neural networks (DNNs) are both memory-intensive and computation-intensive, they are difficult to apply to embedded systems with limited hardware resources. Therefore, DNN models need to be compressed and accelerated. By applying depthwise separable convolutions, MobileNet can decrease the number of parameters and computational complexity with less loss of classification precision. Based on MobileNet, 3 improved MobileNet models with local receptive field expansion in shallow layers, also called Dilated-MobileNet (Dilated Convolution MobileNet) models, are proposed, in which dilated convolutions are introduced into a specific convolutional layer of the MobileNet model. Without increasing the number of parameters, dilated convolutions are used to increase the receptive field of the convolution filters to obtain better classification accuracy. The experiments were performed on the Caltech-101, Caltech-256, and Tubingen animals with attribute datasets, respectively. The results show that Dilated-MobileNets can obtain up to 2% higher classification accuracy than MobileNet.
6
Ma, Tian, Xinlei Zhou, Jiayi Yang, Boyang Meng, Jiali Qian, Jiehui Zhang, and Gang Ge. "Dental Lesion Segmentation Using an Improved ICNet Network with Attention." Micromachines 13, no. 11 (November 7, 2022): 1920. http://dx.doi.org/10.3390/mi13111920.
Full textAbstract:
Precise segmentation of tooth lesions is critical to creation of an intelligent tooth lesion detection system. As a solution to the problem that tooth lesions are similar to normal tooth tissues and difficult to segment, an improved segmentation method of the image cascade network (ICNet) network is proposed to segment various lesion types, such as calculus, gingivitis, and tartar. First, the ICNet network model is used to achieve real-time segmentation of lesions. Second, the Convolutional Block Attention Module (CBAM) is integrated into the ICNet network structure, and large-size convolutions in the spatial attention module are replaced with layered dilated convolutions to enhance the relevant features while suppressing useless features and solve the problem of inaccurate lesion segmentations. Finally, part of the convolution in the network model is replaced with an asymmetric convolution to reduce the calculations added by the attention module. Experimental results show that compared with Fully Convolutional Networks (FCN), U-Net, SegNet, and other segmentation algorithms, our method has a significant improvement in the segmentation effect, and the image processing frequency is higher, which satisfies the real-time requirements of tooth lesion segmentation accuracy.
7
Leong, Mei Chee, Dilip K. Prasad, Yong Tsui Lee, and Feng Lin. "Semi-CNN Architecture for Effective Spatio-Temporal Learning in Action Recognition." Applied Sciences 10, no. 2 (January 12, 2020): 557. http://dx.doi.org/10.3390/app10020557.
Full textAbstract:
This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is to fuse the convolution layers from 2D and 3D CNNs to allow temporal encoding with fewer parameters than 3D CNNs. We adopt transfer learning from pre-trained 2D CNNs for spatial extraction, followed by temporal encoding, before connecting to 3D convolution layers at the top of the architecture. We construct our fusion architecture, semi-CNN, based on three popular models: VGG-16, ResNets and DenseNets, and compare the performance with their corresponding 3D models. Our empirical results evaluated on the action recognition dataset UCF-101 demonstrate that our fusion of 1D, 2D and 3D convolutions outperforms its 3D model of the same depth, with fewer parameters and reduces overfitting. Our semi-CNN architecture achieved an average of 16–30% boost in the top-1 accuracy when evaluated on an input video of 16 frames.
8
Liu, Zhizhe, Luo Sun, and Qian Zhang. "High Similarity Image Recognition and Classification Algorithm Based on Convolutional Neural Network." Computational Intelligence and Neuroscience 2022 (April 12, 2022): 1–10. http://dx.doi.org/10.1155/2022/2836486.
Full textAbstract:
Nowadays, the information processing capabilities and resource storage capabilities of computers have been greatly improved, which also provides support for the neural network technology. Convolutional neural networks have good characterization capabilities in computer vision tasks, such as image recognition technology. Aiming at the problem of high similarity image recognition and classification in a specific field, this paper proposes a high similarity image recognition and classification algorithm fused with convolutional neural networks. First, we extract the image texture features, train different types, and different resolution image sets and determine the optimal texture different parameter values. Second, we decompose the image into subimages according to the texture difference, extract the energy features of each subimage, and perform classification. Then, the input image feature vector is converted into a one-dimensional vector through the alternating 5-layer convolution and 3-layer pooling of convolutional neural networks. On this basis, different sizes of convolution kernels are used to extract different convolutions of the image features, and then use convolution to achieve the feature fusion of different dimensional convolutions. Finally, through the increase in the number of training and the increase in the amount of data, the network parameters are continuously optimized to improve the classification accuracy in the training set and in the test set. The actual accuracy of the weights is verified, and the convolutional neural network model with the highest classification accuracy is obtained. In the experiment, two image data sets of gems and apples are selected as the experimental data to classify and identify gems and determine the origin of apples. The experimental results show that the average identification accuracy of the algorithm is more than 90%.
9
Song, Xiaona, Haichao Liu, Lijun Wang, Song Wang, Yunyu Cao, Donglai Xu, and Shenfeng Zhang. "A Semantic Segmentation Method for Road Environment Images Based on Hybrid Convolutional Auto-Encoder." Traitement du Signal 39, no. 4 (August 31, 2022): 1235–45. http://dx.doi.org/10.18280/ts.390416.
Full textAbstract:
Deep convolutional neural networks (CNNs) have presented amazing performance in the task of semantic segmentation. However, the network model is complex, the training time is prolonged, the semantic segmentation accuracy is not high and the real-time performance is not good, so it is difficult to be directly used in the semantic segmentation of road environment images of autonomous vehicles. As one of the three models of deep learning, the auto-encoder (AE) has powerful data learning and feature extracting capabilities from the raw data itself. In this study, the network architecture of auto-encoder and convolutional auto-encoder (CAE) is improved, supervised learning auto-encoder and improved convolutional auto-encoder are proposed, and a hybrid convolutional auto-encoder model is constructed by combining them. It can extract low-dimensional abstract features of road environment images by using convolution layers and pooling layers in front of the network, and then supervised learning auto-encoder are used to enhance and express semantic segmentation features, and finally de-convolution layers and un-pooling layers are used to generate semantic segmentation results. The hybrid convolutional auto-encoder model proposed in this paper not only contains encoding and decoding parts which are used in the common semantic segmentation models, but also adds semantic feature enhancing and representing parts, so that the network which has fewer convolutional and pooling layers can still achieve better semantic segmentation effects. Compared to the semantic segmentation based on convolutional neural networks, the hybrid convolutional auto-encoder has fewer network layers, fewer network parameters, and simpler network training. We evaluated our proposed method on Camvid and Cityscapes, which are standard benchmarks for semantic segmentation, and it proved to have a better semantic segmentation effect and good real-time performance.
10
Peng, Wenli, Shenglai Zhen, Xin Chen, Qianjing Xiong, and Benli Yu. "Study on convolutional recurrent neural networks for speech enhancement in fiber-optic microphones." Journal of Physics: Conference Series 2246, no. 1 (April 1, 2022): 012084. http://dx.doi.org/10.1088/1742-6596/2246/1/012084.
Full textAbstract:
Abstract In this paper, several improved convolutional recurrent networks (CRN) are proposed, which can enhance the speech with non-additive distortion captured by fiber-optic microphones. Our preliminary study shows that the original CRN structure based on amplitude spectrum estimation is seriously distorted due to the loss of phase information. Therefore, we transform the network to run in time domain and gain 0.42 improvement on PESQ and 0.03 improvement on STOI. In addition, we integrate dilated convolution into CRN architecture, and adopt three different types of bottleneck modules, namely long short-term memory (LSTM), gated recurrent units (GRU) and dilated convolutions. The experimental results show that the model with dilated convolution in the encoder-decoder and the model with dilated convolution at bottleneck layer have the highest PESQ and STOI scores, respectively.
11
Zhou, Jianmin, Sen Gao, Jiahui Li, and Wenhao Xiong. "Bearing Life Prediction Method Based on Parallel Multichannel Recurrent Convolutional Neural Network." Shock and Vibration 2021 (October 13, 2021): 1–9. http://dx.doi.org/10.1155/2021/6142975.
Full textAbstract:
To extract the time-series characteristics of the original bearing signals and predict the remaining useful life (RUL) more effectively, a parallel multichannel recurrent convolutional neural network (PMCRCNN) is proposed for the prediction of RUL. Firstly, the time domain, frequency domain, and time-frequency domain features are extracted from the original signal. Then, the PMCRCNN model is constructed. The front of the model is the parallel multichannel convolution unit to learn and integrate the global and local features from the time-series data. The back of the model is the recurrent convolution layer to model the temporal dependence relationship under different degradation features. Normalized life values are used as labels to train the prediction model. Finally, the RUL was predicted by the trained neural network. The proposed method is verified by full life tests of bearing. The comparison with the existing prognostics approaches of convolutional neural network (CNN) and the recurrent convolutional neural network (RCNN) models proves that the proposed method (PMCRCNN) is effective and superior in improving the accuracy of RUL prediction.
12
Bongulwar, Deepali M., and S. N. Talbar. "Robust Convolutional Neural Network Model For Recognition of Fruits." Indian Journal of Science and Technology 14, no. 45 (December 5, 2021): 3318–34. http://dx.doi.org/10.17485/ijst/v14i45.1493.
Full text
13
Et. al., Ms K. N. Rode,. "Unsupervised CNN model for Sclerosis Detection." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 2 (April 10, 2021): 2577–83. http://dx.doi.org/10.17762/turcomat.v12i2.2223.
Full textAbstract:
Sclerosis detection using brain magnetic resonant imaging (MRI) im-ages is challenging task. With the promising results for variety of ap-plications in terms of classification accuracy using of deep neural net-work models, one can use such models for sclerosis detection. The fea-tures associated with sclerosis is important factor which is highlighted with contrast lesion in brain MRI images. The sclerosis classification initially can be considered as binary task in which the sclerosis seg-mentation can be avoided for reduced complexity of the model. The sclerosis lesion show considerable impact on the features extracted us-ing convolution process in convolution neural network models. The images are used to train the convolutional neural network composed of 35 layers for the classification of sclerosis and normal images of brain MRI. The 35 layers are composed of combination of convolutional lay-ers, Maxpooling layers and Upscaling layers. The results are com-pared with VGG16 model and results are found satisfactory and about 92% accuracy is seen for validation set.
14
He, Ping, Yong Li, Shoulong Chen, Hoghua Xu, Lei Zhu, and Lingyan Wang. "Core looseness fault identification model based on Mel spectrogram-CNN." Journal of Physics: Conference Series 2137, no. 1 (December 1, 2021): 012060. http://dx.doi.org/10.1088/1742-6596/2137/1/012060.
Full textAbstract:
Abstract In order to realize transformer voiceprint recognition, a transformer voiceprint recognition model based on Mel spectrum convolution neural network is proposed. Firstly, the transformer core looseness fault is simulated by setting different preloads, and the sound signals under different preloads are collected; Secondly, the sound signal is converted into a spectrogram that can be trained by convolutional neural network, and then the dimension is reduced by Mel filter bank to draw Mel spectrogram, which can generate spectrogram data sets under different preloads in batch; Finally, the data set is introduced into convolutional neural network for training, and the transformer voiceprint fault recognition model is obtained. The results show that the training accuracy of the proposed Mel spectrum convolution neural network transformer identification model is 99.91%, which can well identify the core loosening faults.
15
Yang, Chao-Peng, Jian-Qing Zhu, Tan Yan, Qiu-Ling Su, and Li-Xin Zheng. "Auxiliary Pneumonia Classification Algorithm Based on Pruning Compression." Computational and Mathematical Methods in Medicine 2022 (July 18, 2022): 1–12. http://dx.doi.org/10.1155/2022/8415187.
Full textAbstract:
Pneumonia infection is the leading cause of death in young children. The commonly used pneumonia detection method is that doctors diagnose through chest X-ray, and external factors easily interfere with the results. Assisting doctors in diagnosing pneumonia in patients based on deep learning methods can effectively eliminate similar problems. However, the complex network structure and redundant parameters of deep neural networks and the limited storage and computing resources of clinical medical hardware devices make it difficult for this method to use widely in clinical practice. Therefore, this paper studies a lightweight pneumonia classification network, CPGResNet50 (ResNet50 with custom channel pruning and ghost methods), based on ResNet50 pruning and compression to better meet the application requirements of clinical pneumonia auxiliary diagnosis with high precision and low memory. First, based on the hierarchical channel pruning method, the channel after the convolutional layer in the bottleneck part of the backbone network layer is used as the pruning object, and the pruning operation is performed after its normalization to obtain a network model with a high compression ratio. Second, the pruned convolutional layers are decomposed into original convolutions and cheap convolutions using the optimized convolution method. The feature maps generated by the two convolution parts are combined as the input to the next convolutional layer. Further, we conducted many experiments using pneumonia X-ray medical image data. The results show that the proposed method reduces the number of parameters of the ResNet50 network model from 23.7 M to 3.455 M when the pruning rate is 90%, a reduction is more than 85%, FIOPs dropped from 4.12G to 523.09 M, and the speed increased by more than 85%. The model training accuracy error remained within 1%. Therefore, the proposed method has a good performance in the auxiliary diagnosis of pneumonia and obtained good experimental results.
16
Chen, Zhan, Sicheng Li, Bing Yang, Qinghan Li, and Hong Liu. "Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (May 18, 2021): 1113–22. http://dx.doi.org/10.1609/aaai.v35i2.16197.
Full textAbstract:
Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.
17
Zaychenko, Yuriy, Maryam Naderan, and Galib Hamidov. "Hybrid convolution network for medical images processing and breast cancer detection." System research and information technologies, no. 2 (August 30, 2022): 85–93. http://dx.doi.org/10.20535/srit.2308-8893.2022.2.06.
Full textAbstract:
In this paper, the breast cancer detection problem using convolutional neural networks (CNN) is considered. The review of known works in this field is presented and analysed. Most of them rely only on feature extraction after the convolutions and use the precision of classification of malignant tumors as the main criterion. However, because of the huge number of parameters in the models, the time of computation is very large. A new structure of CNN is developed — a hybrid convolutional network consisting of convolutional encoder for features extraction and reduction of the complexity of the model and CNN for classification of tumors. As a result, it prevented overfitting the model and reduced training time. Further, while evaluating the performance of the convolutional model, it was suggested to consider recall and precision criteria instead of only accuracy like other works. The investigations of the suggested hybrid CNN were performed and compared with known results. After experiments, it was established the proposed hybrid convolutional network has shown high performance with sensitivity, precision, and accuracy of 93,50%, 91,60%, and 93%, respectively, and requires much less training time in the problem of breast cancer detection as compared with known works.
18
Lan, Weichao, and Liang Lan. "Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 9 (May 18, 2021): 8235–42. http://dx.doi.org/10.1609/aaai.v35i9.17002.
Full textAbstract:
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile phones). One popular way to reduce the memory cost of deep CNN model is to train binary CNN where the weights in convolution filters are either 1 or -1 and therefore each weight can be efficiently stored using a single bit. However, the compression ratio of existing binary CNN models is upper bounded by ∼ 32. To address this limitation, we propose a novel method to compress deep CNN model by stacking low-dimensional binary convolution filters. Our proposed method approximates a standard convolution filter by selecting and stacking filters from a set of low-dimensional binary convolution filters. This set of low-dimensional binary convolution filters is shared across all filters for a given convolution layer. Therefore, our method will achieve much larger compression ratio than binary CNN models. In order to train our proposed model, we have theoretically shown that our proposed model is equivalent to select and stack intermediate feature maps generated by low-dimensional binary filters. Therefore, our proposed model can be efficiently trained using the split-transform-merge strategy. We also provide detailed analysis of the memory and computation cost of our model in model inference. We compared the proposed method with other five popular model compression techniques on two benchmark datasets. Our experimental results have demonstrated that our proposed method achieves much higher compression ratio than existing methods while maintains comparable accuracy.
19
Ye, Mengqi, and Lijun Zhang. "Empirical Analysis of Financial Depth and Width Based on Convolutional Neural Network." Computational Intelligence and Neuroscience 2021 (December 2, 2021): 1–10. http://dx.doi.org/10.1155/2021/8650059.
Full textAbstract:
There are great differences in financial and economic development in different regions. In different time series and different regions, the effects of financial depth and width on economic development are also different. This paper selects neural network to establish the economic benefit model of financial depth and breadth, which can deeply explore the relationship between financial data and economic data. In order to determine the optimal convolutional neural network parameters, the optimal convolutional neural network parameters are determined through comparative simulation analysis. The convolutional neural network model based on the optimal parameters is applied to the empirical analysis of the effect of financial and economic development in X region. In order to obtain the optimal convolutional neural network parameters, different convolution layers, convolution core size, and convolution core number are compared and simulated. The convolutional neural network model with optimal parameters is used to simulate the financial and economic data of X region. The simulation results show that the density of financial personnel has a certain impact on economic development, so it is necessary to improve the comprehensive quality of financial personnel and promote regional economic development. Therefore, this paper seeks an effective method to study the effect of financial breadth and depth on economic development which can provide a feasible idea for the in-depth research method of financial and economic development.
20
Xianhao Shen, Xianhao Shen, Changhong Zhu Xianhao Shen, Yihao Zang Changhong Zhu, and Shaohua Niu Yihao Zang. "A Method for Detecting Abnormal Data of Network Nodes Based on Convolutional Neural Network." 電腦學刊 33, no. 3 (June 2022): 049–58. http://dx.doi.org/10.53106/199115992022063303004.
Full textAbstract:
<p>Abnormal data detection is an important step to ensure the accuracy and reliability of node data in wireless sensor networks. In this paper, a data classification method based on convolutional neural network is proposed to solve the problem of data anomaly detection in wireless sensor networks. First, Normal data and abnormal data generated after injection fault are normalized and mapped to gray image as input data of the convolutional neural network. Then, based on the classical convolution neural network, three new convolutional neural network models are designed by designing the parameters of the convolutional layer and the fully connected layer. This model solves the problem that the performance of traditional detection algorithm is easily affected by relevant threshold through self-learning data characteristics of convolution layer. The experimental results show that this method has better detection performance and higher reliability.</p> <p> </p>
21
Robinson, Enders A. "Seismic time‐invariant convolutional model." GEOPHYSICS 50, no. 12 (December 1985): 2742–51. http://dx.doi.org/10.1190/1.1441894.
Full textAbstract:
A layered‐earth seismic model is subdivided into two subsystems. The upper subsystem can have any sequence of reflection coefficients but the lower subsystem has a sequence of reflection coefficients which are small in magnitude and have the characteristics of random white noise. It is shown that if an arbitrary wavelet is the input to the lower lithologic section, the same wavelet convolved with the white sequence of reflection coefficients will be the reflected output. That is, a white sedimentary system passes a wavelet in reflection as a linear time‐invariant filter with impulse response given by the reflection coefficients. Thus, the small white lithologic section acts as an ideal reflecting window, producing perfect primary reflections with no multiple reflections and no transmission losses. The upper subsystem produces a minimum‐delay multiple‐reflection waveform. The seismic wavelet is the convolution of the source wavelet, the absorption effect, this multiple‐reflection waveform, and the instrument effect. Therefore, the seismic trace within the time gate corresponding to the lower subsystem is given by the convolution of the seismic wavelet with the white reflection coefficients of the lower subsystem. The linear time‐invariant seismic model used in predictive deconvolution has been derived. Furthermore, it is shown that any layered subsystem which has small reflection coefficients acts as a linear time‐invariant filter. This explains why time‐invariant deconvolution filters can be used within various time gates on a seismic trace which at first appearance might look like a continually time‐varying phenomenon.
22
Chen, Lei, Le Wu, Richang Hong, Kun Zhang, and Meng Wang. "Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (April 3, 2020): 27–34. http://dx.doi.org/10.1609/aaai.v34i01.5330.
Full textAbstract:
Graph Convolutional Networks~(GCNs) are state-of-the-art graph based representation learning models by iteratively stacking multiple layers of convolution aggregation operations and non-linear activation operations. Recently, in Collaborative Filtering~(CF) based Recommender Systems~(RS), by treating the user-item interaction behavior as a bipartite graph, some researchers model higher-layer collaborative signals with GCNs. These GCN based recommender models show superior performance compared to traditional works. However, these models suffer from training difficulty with non-linear activations for large user-item graphs. Besides, most GCN based models could not model deeper layers due to the over smoothing effect with the graph convolution operation. In this paper, we revisit GCN based CF models from two aspects. First, we empirically show that removing non-linearities would enhance recommendation performance, which is consistent with the theories in simple graph convolutional networks. Second, we propose a residual network structure that is specifically designed for CF with user-item interaction modeling, which alleviates the over smoothing problem in graph convolution aggregation operation with sparse user-item interaction data. The proposed model is a linear model and it is easy to train, scale to large datasets, and yield better efficiency and effectiveness on two real datasets. We publish the source code at https://github.com/newlei/LR-GCCF.
23
Zan, Tao, Hui Wang, Min Wang, Zhihao Liu, and Xiangsheng Gao. "Application of Multi-Dimension Input Convolutional Neural Network in Fault Diagnosis of Rolling Bearings." Applied Sciences 9, no. 13 (July 1, 2019): 2690. http://dx.doi.org/10.3390/app9132690.
Full textAbstract:
Aiming at the problem of poor robustness of the intelligent diagnostic model, a fault diagnosis model of rolling bearing based on a multi-dimension input convolutional neural network (MDI-CNN) is proposed. Compared with the traditional convolution neural network, the proposed model has multiple input layers. Therefore, it can fuse the original signal and processed signal—making full use of advantages of the convolutional neural networks to learn the original signal characteristics automatically, and also improving recognition accuracy and anti-jamming ability. The feasibility and validity of the proposed MDI-CNN are verified, and its advantages are proved by comparison with the other related models. Moreover, the robustness of the model is tested by adding the noise to the test set. Finally, the stability of the model is verified by two experiments. The experimental results show that the proposed model improves the recognition rate, robustness and convergence performance of the traditional convolution model and has good generalization ability.
24
Dong, Hongwei, Lamei Zhang, and Bin Zou. "PolSAR Image Classification with Lightweight 3D Convolutional Networks." Remote Sensing 12, no. 3 (January 26, 2020): 396. http://dx.doi.org/10.3390/rs12030396.
Full textAbstract:
Convolutional neural networks (CNNs) have become the state-of-the-art in optical image processing. Recently, CNNs have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. Unlike optical images, the unique phase information of PolSAR data expresses the structure information of objects. This special data representation makes 3D convolution which explicitly modeling the relationship between polarimetric channels perform better in the task of PolSAR image classification. However, the development of deep 3D-CNNs will cause a huge number of model parameters and expensive computational costs, which not only leads to the decrease of the interpretation speed during testing, but also greatly increases the risk of over-fitting. To alleviate this problem, a lightweight 3D-CNN framework that compresses 3D-CNNs from two aspects is proposed in this paper. Lightweight convolution operations, i.e., pseudo-3D and 3D-depthwise separable convolutions, are considered as low-latency replacements for vanilla 3D convolution. Further, fully connected layers are replaced by global average pooling to reduce the number of model parameters so as to save the memory. Under the specific classification task, the proposed methods can reduce up to 69.83% of the model parameters in convolution layers of the 3D-CNN as well as almost all the model parameters in fully connected layers, which ensures the fast PolSAR interpretation. Experiments on three PolSAR benchmark datasets, i.e., AIRSAR Flevoland, ESAR Oberpfaffenhofen, EMISAR Foulum, show that the proposed lightweight architectures can not only maintain but also slightly improve the accuracy under various criteria.
25
Son, Jeongtae, and Dongsup Kim. "Development of a graph convolutional neural network model for efficient prediction of protein-ligand binding affinities." PLOS ONE 16, no. 4 (April 8, 2021): e0249404. http://dx.doi.org/10.1371/journal.pone.0249404.
Full textAbstract:
Prediction of protein-ligand interactions is a critical step during the initial phase of drug discovery. We propose a novel deep-learning-based prediction model based on a graph convolutional neural network, named GraphBAR, for protein-ligand binding affinity. Graph convolutional neural networks reduce the computational time and resources that are normally required by the traditional convolutional neural network models. In this technique, the structure of a protein-ligand complex is represented as a graph of multiple adjacency matrices whose entries are affected by distances, and a feature matrix that describes the molecular properties of the atoms. We evaluated the predictive power of GraphBAR for protein-ligand binding affinities by using PDBbind datasets and proved the efficiency of the graph convolution. Given the computational efficiency of graph convolutional neural networks, we also performed data augmentation to improve the model performance. We found that data augmentation with docking simulation data could improve the prediction accuracy although the improvement seems not to be significant. The high prediction performance and speed of GraphBAR suggest that such networks can serve as valuable tools in drug discovery.
26
He, Qingfang, Guang Cheng, and Huimin Ju. "BCDnet: Parallel heterogeneous eight-class classification model of breast pathology." PLOS ONE 16, no. 7 (July 12, 2021): e0253764. http://dx.doi.org/10.1371/journal.pone.0253764.
Full textAbstract:
Breast cancer is the cancer with the highest incidence of malignant tumors in women, which seriously endangers women’s health. With the help of computer vision technology, it has important application value to automatically classify pathological tissue images to assist doctors in rapid and accurate diagnosis. Breast pathological tissue images have complex and diverse characteristics, and the medical data set of breast pathological tissue images is small, which makes it difficult to automatically classify breast pathological tissues. In recent years, most of the researches have focused on the simple binary classification of benign and malignant, which cannot meet the actual needs for classification of pathological tissues. Therefore, based on deep convolutional neural network, model ensembleing, transfer learning, feature fusion technology, this paper designs an eight-class classification breast pathology diagnosis model BCDnet. A user inputs the patient’s breast pathological tissue image, and the model can automatically determine what the disease is (Adenosis, Fibroadenoma, Tubular Adenoma, Phyllodes Tumor, Ductal Carcinoma, Lobular Carcinoma, Mucinous Carcinoma or Papillary Carcinoma). The model uses the VGG16 convolution base and Resnet50 convolution base as the parallel convolution base of the model. Two convolutional bases (VGG16 convolutional base and Resnet50 convolutional base) obtain breast tissue image features from different fields of view. After the information output by the fully connected layer of the two convolutional bases is fused, it is classified and output by the SoftMax function. The model experiment uses the publicly available BreaKHis data set. The number of samples of each class in the data set is extremely unevenly distributed. Compared with the binary classification, the number of samples in each class of the eight-class classification is also smaller. Therefore, the image segmentation method is used to expand the data set and the non-repeated random cropping method is used to balance the data set. Based on the balanced data set and the unbalanced data set, the BCDnet model, the pre-trained model Resnet50+ fine-tuning, and the pre-trained model VGG16+ fine-tuning are used for multiple comparison experiments. In the comparison experiment, the BCDnet model performed outstandingly, and the correct recognition rate of the eight-class classification model is higher than 98%. The results show that the model proposed in this paper and the method of improving the data set are reasonable and effective.
27
Jiang, Haiyang, Yaozong Pan, Jian Zhang, and Haitao Yang. "Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion." Symmetry 11, no. 6 (June 5, 2019): 761. http://dx.doi.org/10.3390/sym11060761.
Full textAbstract:
In this paper, our goal is to improve the recognition accuracy of battlefield target aggregation behavior while maintaining the low computational cost of spatio-temporal depth neural networks. To this end, we propose a novel 3D-CNN (3D Convolutional Neural Networks) model, which extends the idea of multi-scale feature fusion to the spatio-temporal domain, and enhances the feature extraction ability of the network by combining feature maps of different convolutional layers. In order to reduce the computational complexity of the network, we further improved the multi-fiber network, and finally established an architecture—3D convolution Two-Stream model based on multi-scale feature fusion. Extensive experimental results on the simulation data show that our network significantly boosts the efficiency of existing convolutional neural networks in the aggregation behavior recognition, achieving the most advanced performance on the dataset constructed in this paper.
28
Yang, Yadong, Chengji Xu, Feng Dong, and Xiaofeng Wang. "A New Multi-Scale Convolutional Model Based on Multiple Attention for Image Classification." Applied Sciences 10, no. 1 (December 20, 2019): 101. http://dx.doi.org/10.3390/app10010101.
Full textAbstract:
Computer vision systems are insensitive to the scale of objects in natural scenes, so it is important to study the multi-scale representation of features. Res2Net implements hierarchical multi-scale convolution in residual blocks, but its random grouping method affects the robustness and intuitive interpretability of the network. We propose a new multi-scale convolution model based on multiple attention. It introduces the attention mechanism into the structure of a Res2-block to better guide feature expression. First, we adopt channel attention to score channels and sort them in descending order of the feature’s importance (Channels-Sort). The sorted residual blocks are grouped and intra-block hierarchically convolved to form a single attention and multi-scale block (AMS-block). Then, we implement channel attention on the residual small blocks to constitute a dual attention and multi-scale block (DAMS-block). Introducing spatial attention before sorting the channels to form multi-attention multi-scale blocks(MAMS-block). A MAMS-convolutional neural network (CNN) is a series of multiple MAMS-blocks. It enables significant information to be expressed at more levels, and can also be easily grafted into different convolutional structures. Limited by hardware conditions, we only prove the validity of the proposed ideas through convolutional networks of the same magnitude. The experimental results show that the convolution model with an attention mechanism and multi-scale features is superior in image classification.
29
Zhao, Ping, Zhijie Fan*, Zhiwei Cao, and Xin Li. "Intrusion Detection Model Using Temporal Convolutional Network Blend Into Attention Mechanism." International Journal of Information Security and Privacy 16, no. 1 (January 2022): 1–20. http://dx.doi.org/10.4018/ijisp.290832.
Full textAbstract:
In order to improve the ability to detect network attacks, traditional intrusion detection models often used convolutional neural networks to encode spatial information or recurrent neural networks to obtain temporal features of the data. Some models combined the two methods to extract spatio-temporal features. However, these approaches used separate models and learned features insufficiently. This paper presented an improved model based on temporal convolutional networks (TCN) and attention mechanism. The causal and dilation convolution can capture the spatio-temporal dependencies of the data. The residual blocks allow the network to transfer information in a cross-layered manner, enabling in-depth network learning. Meanwhile, attention mechanism can enhance the model's attention to the relevant anomalous features of different attacks. Finally, this paper compared models results on the KDD CUP99 and UNSW-NB15 datasets. Besides, the authors apply the model to video surveillance network attack detection scenarios. The result shows that the model has advantages in evaluation metrics.
30
Zhang, Lishan, Lei Han, Yuzhen Meng, and Wenkui Zhao. "Multi-input Convolutional Neural Network Fault Diagnosis Algorithm Based on the Hydraulic Pump." Journal of Physics: Conference Series 2095, no. 1 (November 1, 2021): 012069. http://dx.doi.org/10.1088/1742-6596/2095/1/012069.
Full textAbstract:
Abstract Convolutional neural network used in fault diagnosis can effectively extract fault features in vibration signals. However, in the feature extraction of mechanical fault diagnosis, usually more than two feature signals including at least axial and radial vibration signals can be extracted. This paper proposes two multi-input convolutional neural network models based on the fault data of the aircraft hydraulic pump including axial and radial vibration. The first is the Independent Input Multi-input Convolutional Neural Network model. The two inputs are respectively used for convolution pooling operation with CNN, and are combined through the concatenate function before the fully connected layer, and then all frames are integrated and flattened by the flatten function. A one-dimensional array, finally enters the fully connected layer and outputs the result through the softmax function. The second is the Combined Input Multiinput Convolutional Neural Network, that is, combine two one-dimensional signals into a twodimensional signal in the input layer of the convolutional neural network and then perform convolution pooling, and finally output the result through the softmax function. The results show that the two models have good accuracy and stability, and the second one has a higher convergence and fitting efficiency than the first one.
31
Shen, Sheng, Honghui Yang, Xiaohui Yao, Junhao Li, Guanghui Xu, and Meiping Sheng. "Ship Type Classification by Convolutional Neural Networks with Auditory-Like Mechanisms." Sensors 20, no. 1 (January 1, 2020): 253. http://dx.doi.org/10.3390/s20010253.
Full textAbstract:
Ship type classification with radiated noise helps monitor the noise of shipping around the hydrophone deployment site. This paper introduces a convolutional neural network with several auditory-like mechanisms for ship type classification. The proposed model mainly includes a cochlea model and an auditory center model. In cochlea model, acoustic signal decomposition at basement membrane is implemented by time convolutional layer with auditory filters and dilated convolutions. The transformation of neural patterns at hair cells is modeled by a time frequency conversion layer to extract auditory features. In the auditory center model, auditory features are first selectively emphasized in a supervised manner. Then, spectro-temporal patterns are extracted by deep architecture with multistage auditory mechanisms. The whole model is optimized with an objective function of ship type classification to form the plasticity of the auditory system. The contributions compared with an auditory inspired convolutional neural network include the improvements in dilated convolutions, deep architecture and target layer. The proposed model can extract auditory features from a raw hydrophone signal and identify types of ships under different working conditions. The model achieved a classification accuracy of 87.2% on four ship types and ocean background noise.
32
Lu, Peng, Yaqin Zhao, and Yuan Xu. "A Two-Stream CNN Model with Adaptive Adjustment of Receptive Field Dedicated to Flame Region Detection." Symmetry 13, no. 3 (February 28, 2021): 397. http://dx.doi.org/10.3390/sym13030397.
Full textAbstract:
Convolutional neural networks (CNN) have yielded state-of-the-art performance in image segmentation. Their application in video surveillance systems can provide very useful information for extinguishing fire in time. The current studies mostly focused on CNN-based flame image classification and have achieved good accuracy. However, the research of CNN-based flame region detection is extremely scarce due to the bulky network structures and high hardware configuration requirements of the state-of-the-art CNN models. Therefore, this paper presents a two-stream convolutional neural network for flame region detection (TSCNNFlame). TSCNNFlame is a lightweight CNN architecture including a spatial stream and temporal stream for detecting flame pixels in video sequences captured by fixed cameras. The static features from the spatial stream and dynamic features from the temporal stream are fused by three convolutional layers to reduce the false positives. We replace the convolutional layer of CNN with the selective kernel (SK)-Shuffle block constructed by integrating the SK convolution into the deep convolutional layer of ShuffleNet V2. The SKnet blocks can adaptively adjust the size of one receptive field with the proportion of one region of interest (ROI) in it. The grouped convolution used in Shufflenet solves the problem in which the multi-branch structure of SKnet causes the network parameters to double with the number of branches. Therefore, the CNN network dedicated to flame region detection balances the efficiency and accuracy by the lightweight architecture, the temporal–spatial features fusion, and the advantages of the SK-Shuffle block. The experimental results, which are evaluated by multiple metrics and are analyzed from many angles, show that this method can achieve significant performance while reducing the running time.
33
Alessandro, Barducci. "Convolutional modelling of epidemics." Annals of Mathematics and Physics 5, no. 2 (December 3, 2022): 180–89. http://dx.doi.org/10.17352/amp.000063.
Full textAbstract:
Traditional deterministic modeling of epidemics is usually based on a linear system of differential equations in which compartment transitions are proportional to their population, implicitly assuming an exponential process for leaving a compartment as happens in radioactive decay. Nonetheless, this assumption is quite unrealistic since it permits a class transition such as the passage from illness to recovery that does not depend on the time an individual got infected. This trouble significantly affects the time evolution of epidemy computed by these models. This paper describes a new deterministic epidemic model in which transitions among different population classes are described by a convolutional law connecting the input and output fluxes of each class. The new model guarantees that class changes always take place according to a realistic timing, which is defined by the impulse response function of that transition, avoiding model output fluxes by the exponential decay typical of previous models. The model contains five population compartments and can take into consideration healthy carriers and recovered-to-susceptible transition. The paper provides a complete mathematical description of the convolutional model and presents three sets of simulations that show its performance. A comparison with predictions of the SIR model is given. Outcomes of simulation of the COVID-19 pandemic are discussed which predicts the truly observed time changes of the dynamic case-fatality rate. The new model foresees the possibility of successive epidemic waves as well as the asymptotic instauration of a quasi-stationary regime of lower infection circulation that prevents a definite stopping of the epidemy. We show the existence of a quadrature function that formally solves the system of equations of the convolutive and the SIR models and whose asymptotic limit roughly matches the epidemic basic reproduction number.
34
Li, Ruixue, Bo Yin, Yanping Cong, and Zehua Du. "Simultaneous Prediction of Soil Properties Using Multi_CNN Model." Sensors 20, no. 21 (November 3, 2020): 6271. http://dx.doi.org/10.3390/s20216271.
Full textAbstract:
Soil nutrient prediction based on near-infrared spectroscopy has become the main research direction for rapid acquisition of soil information. The development of deep learning has greatly improved the prediction accuracy of traditional modeling methods. In view of the low efficiency and low accuracy of current soil prediction models, this paper proposes a soil multi-attribute intelligent prediction method based on convolutional neural networks, by constructing a dual-stream convolutional neural network model Multi_CNN that combines one-dimensional convolution and two-dimensional convolution, the intelligent prediction of soil multi-attribute is realized. The model extracts the characteristics of soil attributes from spectral sequences and spectrograms respectively, and multiple attributes can be predicted simultaneously by feature fusion. The model is based on two different-scale soil near-infrared spectroscopy data sets for multi-attribute prediction. The experimental results show that the RP2 of the three attributes of Total Carbon, Total Nitrogen, and Alkaline Nitrogen on the small dataset are 0.94, 0.95, 0.87, respectively, and the RP2 of the attributes of Organic Carbon, Nitrogen, and Clay on the LUCAS dataset are, respectively, 0.95, 0.91, 0.83, And compared with traditional regression models and new prediction methods commonly used in soil nutrient prediction, the multi-task model proposed in this paper is more accurate.
35
Peng, Haoliang, and Yue Wu. "A Dynamic Convolutional Network-Based Model for Knowledge Graph Completion." Information 13, no. 3 (March 4, 2022): 133. http://dx.doi.org/10.3390/info13030133.
Full textAbstract:
Knowledge graph embedding can learn low-rank vector representations for knowledge graph entities and relations, and has been a main research topic for knowledge graph completion. Several recent works suggest that convolutional neural network (CNN)-based models can capture interactions between head and relation embeddings, and hence perform well on knowledge graph completion. However, previous convolutional network models have ignored the different contributions of different interaction features to the experimental results. In this paper, we propose a novel embedding model named DyConvNE for knowledge base completion. Our model DyConvNE uses a dynamic convolution kernel because the dynamic convolutional kernel can assign weights of varying importance to interaction features. We also propose a new method of negative sampling, which mines hard negative samples as additional negative samples for training. We have performed experiments on the data sets WN18RR and FB15k-237, and the results show that our method is better than several other benchmark algorithms for knowledge graph completion. In addition, we used a new test method when predicting the Hits@1 values of WN18RR and FB15k-237, named specific-relationship testing. This method gives about a 2% relative improvement over models that do not use this method in terms of Hits@1.
36
Zhou, Fen, Xuping Tu, Qingdong Wang, and Guosong Jiang. "Improved GCN Framework for Human Motion Recognition." Scientific Programming 2022 (May 9, 2022): 1–10. http://dx.doi.org/10.1155/2022/2721618.
Full textAbstract:
Human recognition models based on spatial-temporal graph convolutional neural networks have been gradually developed, and we present an improved spatial-temporal graph convolutional neural network to solve the problems of the high number of parameters and low accuracy of this type of model. The method mainly draws on the inception structure. First, the tensor rotation is added to the graph convolution layer to realize the conversion between graph node dimension and channel dimension and enhance the model’s ability to capture global information for small-scale tasks. Then the inception temporal convolution layer is added to build a multiscale temporal convolution filter to perceive temporal information under different time domains hierarchically from 4-time dimensions. It overcomes the shortcomings of temporal graph convolutional networks in the field of joint relevance of hidden layers and compensates for the information omission of small-scale graph tasks. It also limits the volume of parameters, decreases the arithmetic power, and speeds up the computation. In our experiments, we verify our model on the public dataset NTU RGB + D. Our method reduces the number of the model parameters by 50% and achieves an accuracy of 90% in the CS evaluation system and 94% in the CV evaluation system. The results show that our method not only has high recognition accuracy and good robustness in human behavior recognition applications but also has a small number of model parameters, which can effectively reduce the computational cost.
37
Zhang, Zhaohui, Xinxin Zhou, Xiaobo Zhang, Lizhi Wang, and Pengwei Wang. "A Model Based on Convolutional Neural Network for Online Transaction Fraud Detection." Security and Communication Networks 2018 (August 6, 2018): 1–9. http://dx.doi.org/10.1155/2018/5680264.
Full textAbstract:
Using wireless mobile terminals has become the mainstream of Internet transactions, which can verify the identity of users by passwords, fingerprints, sounds, and images. However, once these identity data are stolen, traditional information security methods will not avoid online transaction fraud. The existing convolutional neural network model for fraud detection needs to generate many derivative features. This paper proposes a fraud detection model based on the convolutional neural network in the field of online transactions, which constructs an input feature sequencing layer that implements the reorganization of raw transaction features to form different convolutional patterns. Its significance is that different feature combinations entering the convolution kernel will produce different derivative features. The advantage of this model lies in taking low dimensional and nonderivative online transaction data as the input. The whole network consists of a feature sequencing layer, four convolutional layers and pooling layers, and a fully connected layer. Verifying with online transaction data from a commercial bank, the experimental results show that the model achieves excellent fraud detection performance without derivative features. And its precision can be stabilized at around 91% and recall can be stabilized at around 94%, which increased by 26% and 2%, respectively, comparing with the existing CNN for fraud detection.
38
Guo, Shengnan, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. "Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 922–29. http://dx.doi.org/10.1609/aaai.v33i01.3301922.
Full textAbstract:
Forecasting the traffic flows is a critical issue for researchers and practitioners in the field of transportation. However, it is very challenging since the traffic flows usually show high nonlinearities and complex patterns. Most existing traffic flow prediction methods, lacking abilities of modeling the dynamic spatial-temporal correlations of traffic data, thus cannot yield satisfactory prediction results. In this paper, we propose a novel attention based spatial-temporal graph convolutional network (ASTGCN) model to solve traffic flow forecasting problem. ASTGCN mainly consists of three independent components to respectively model three temporal properties of traffic flows, i.e., recent, daily-periodic and weekly-periodic dependencies. More specifically, each component contains two major parts: 1) the spatial-temporal attention mechanism to effectively capture the dynamic spatialtemporal correlations in traffic data; 2) the spatial-temporal convolution which simultaneously employs graph convolutions to capture the spatial patterns and common standard convolutions to describe the temporal features. The output of the three components are weighted fused to generate the final prediction results. Experiments on two real-world datasets from the Caltrans Performance Measurement System (PeMS) demonstrate that the proposed ASTGCN model outperforms the state-of-the-art baselines.
39
Deng, Meng-Di, Rui-Sheng Jia, Hong-Mei Sun, and Xing-Li Zhang. "Super-resolution reconstruction of seismic section image via multi-scale convolution neural network." E3S Web of Conferences 303 (2021): 01058. http://dx.doi.org/10.1051/e3sconf/202130301058.
Full textAbstract:
The resolution of seismic section images can directly affect the subsequent interpretation of seismic data. In order to improve the spatial resolution of low-resolution seismic section images, a super-resolution reconstruction method based on multi-scale convolution is proposed. This method designs a multi-scale convolutional neural network to learn high-low resolution image feature pairs, and realizes mapping learning from low-resolution seismic section images to high-resolution seismic section images. This multi-scale convolutional neural network model consists of four convolutional layers and a sub-pixel convolutional layer. Convolution operations are used to learn abundant seismic section image features, and sub-pixel convolution layer is used to reconstruct high-resolution seismic section image. The experimental results show that the proposed method is superior to the comparison method in peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the total training time and reconstruction time, our method is about 22% less than the FSRCNN method and about 18% less than the ESPCN method.
40
Wang, Yaping, Jinbao Wang, Sheng Zhang, Di Xu, and Jianghua Ge. "Remaining Useful Life Prediction Model for Rolling Bearings Based on MFPE–MACNN." Entropy 24, no. 7 (June 30, 2022): 905. http://dx.doi.org/10.3390/e24070905.
Full textAbstract:
Aiming to resolve the problem of redundant information concerning rolling bearing degradation characteristics and to tackle the difficulty faced by convolutional deep learning models in learning feature information in complex time series, a prediction model for remaining useful life based on multiscale fusion permutation entropy (MFPE) and a multiscale convolutional attention neural network (MACNN) is proposed. The original signal of the rolling bearing was extracted and decomposed by resonance sparse decomposition to obtain the high-resonance and low-resonance components. The multiscale permutation entropy of the low-resonance component was calculated. Moreover, the locally linear-embedding algorithm was used for dimensionality reduction to remove redundant information. The multiscale convolution module was constructed to learn the feature information at different time scales. The attention module was used to fuse the feature information and input it into the remaining useful life prediction module for evaluation. The appropriate network structure and parameter configuration were determined, and a multiscale convolutional attention neural network was designed to determine the remaining useful life prediction model. The results show that the method demonstrates effectiveness and superiority in degrading the feature information representation and improving the remaining useful life prediction accuracy compared with other models.
41
Jiang, Lanlan. "Convolutional Neural Network-Based Cross-Media Semantic Matching and User Adaptive Satisfaction Analysis Model." Computational Intelligence and Neuroscience 2022 (April 30, 2022): 1–12. http://dx.doi.org/10.1155/2022/4244675.
Full textAbstract:
In this paper, an in-depth study of cross-media semantic matching and user adaptive satisfaction analysis model is carried out based on the convolutional neural network. Based on the existing convolutional neural network, this paper uses rich information. The spatial correlation of cross-media semantic matching further improves the classification accuracy of hyperspectral images and reduces the classification time under user adaptive satisfaction complexity. Aiming at the problem that it is difficult for the current hyperspectral image classification method based on convolutional neural network to capture the spatial pose characteristics of objects, the problem is that principal component analysis ignores some vital information when retaining a few components. This paper proposes a polymorphism based on extension Attribute Profile Feature (EMAP) Stereo Capsule Network Model for Hyperspectral Image Classification. To ensure the model has good generalization performance, a new remote sensing image Pan sharpening algorithm based on convolutional neural network is proposed, which increases the model’s width to extract the feature information of the image and uses dilated instead of traditional convolution. The experimental results show that the algorithm has good generalization while ensuring self-adaptive satisfaction.
42
Wan, Renzhuo, Chengde Tian, Wei Zhang, Wendi Deng, and Fan Yang. "A Multivariate Temporal Convolutional Attention Network for Time-Series Forecasting." Electronics 11, no. 10 (May 10, 2022): 1516. http://dx.doi.org/10.3390/electronics11101516.
Full textAbstract:
Multivariate time-series forecasting is one of the crucial and persistent challenges in time-series forecasting tasks. As a kind of data with multivariate correlation and volatility, multivariate time series impose highly nonlinear time characteristics on the forecasting model. In this paper, a new multivariate time-series forecasting model, multivariate temporal convolutional attention network (MTCAN), based on a self-attentive mechanism is proposed. MTCAN is based on the Convolution Neural Network (CNN) model, using 1D dilated convolution as the basic unit to construct asymmetric blocks, and then, the feature extraction is performed by the self-attention mechanism to finally obtain the prediction results. The input and output lengths of this network can be determined flexibly. The validation of the method is carried out with three different multivariate time-series datasets. The reliability and accuracy of the prediction results are compared with Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Long Short-Term Memory (ConvLSTM), and Temporal Convolutional Network (TCN). The prediction results show that the model proposed in this paper has significantly improved prediction accuracy and generalization.
43
Lian, Zuozheng, Haizhen Wang, and Qianjun Zhang. "An Image Deblurring Method Using Improved U-Net Model." Mobile Information Systems 2022 (July 31, 2022): 1–11. http://dx.doi.org/10.1155/2022/6394788.
Full textAbstract:
Deblurring methods in dynamic scenes are a challenging problem. Recently, significant progress has been made for image deblurring methods based on deep learning. However, these methods usually stack ordinary convolutional layers or increase convolution kernel size, resulting in limited receptive fields, an unsatisfying deblurring effect, and a heavy computational burden. Therefore, we propose an improved U-Net (U-shaped Convolutional Neural Network) model to restore the blurred images. We first design the model structure, which mainly includes depth-wise separable convolution, residual depth-wise separable convolution, wavelet transform, inverse wavelet transform, and a DMRFC (dense multireceptive field channel) module. Next, a depth-wise separable convolution is designed, which reduces model calculations and the number of parameters when compared with the standard convolution. A residual depth-wise separable convolution is designed, which allows for propagation of detailed information from different layers when compared with standard convolution and a standard residual block. The wavelet transform realizes downsampling by separating the contextual and texture information of the image. It also reduces model training difficulty. The inverse wavelet transform realizes upsampling, which reduces the loss of image information. Finally, by combining an extensional receptive field and channel attention mechanism, a DMRFC module is proposed to extract detailed image information, which further improves the reconstructed image quality via inverse wavelet transform. Experiments on the public dataset GOPRO show that the image deblurring method in this paper has higher-quality visual effects, while the PSNR (peak signal-to-noise ratio) rises to 30.83 and SSIM (structural similarity) rises to 0.948. Fewer model parameters and a shorter recovery time are needed, which provides a more lightweight image deblurring method.
44
Wan, Renzhuo, Shuping Mei, Jun Wang, Min Liu, and Fan Yang. "Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting." Electronics 8, no. 8 (August 7, 2019): 876. http://dx.doi.org/10.3390/electronics8080876.
Full textAbstract:
Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To address such concerns, various deep learning models based on Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) methods are proposed. To improve the prediction accuracy and minimize the multivariate time series data dependence for aperiodic data, in this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model. In this model, multi-variable time series prediction is constructed as a sequence-to-sequence scenario for non-periodic datasets. The multichannel residual blocks in parallel with asymmetric structure based on deep convolution neural network is proposed. The results are compared with rich competitive algorithms of long short term memory (LSTM), convolutional LSTM (ConvLSTM), Temporal Convolution Network (TCN) and Multivariate Attention LSTM-FCN (MALSTM-FCN), which indicate significant improvement of prediction accuracy, robust and generalization of our model.
45
Zhu, Yunlong. "Research on News Text Classification Based on Deep Learning Convolutional Neural Network." Wireless Communications and Mobile Computing 2021 (December 8, 2021): 1–6. http://dx.doi.org/10.1155/2021/1508150.
Full textAbstract:
Aiming at the problems of low classification accuracy and low efficiency of existing news text classification methods, a new method of news text classification based on deep learning convolutional neural network is proposed. Determine the weight of the news text data through the VSM (Viable System Model) vector space model, calculate the information gain of mutual information, and determine the characteristics of the news text data; on this basis, use the hash algorithm to encode the news text data to calculate any news. The spacing between the text data realizes the feature preprocessing of the news text data; this article analyzes the basic structure of the deep learning convolutional neural network, uses the convolutional layer in the convolutional neural network to determine the change value of the convolution kernel, trains the news text data, builds a news text classifier of deep learning convolutional neural network, and completes news text classification. The experimental results show that the deep learning convolutional neural network can improve the accuracy and speed of news text classification, which is feasible.
46
Yang, Yadong, Xiaofeng Wang, and Hengzheng Zhang. "Local Importance Representation Convolutional Neural Network for Fine-Grained Image Classification." Symmetry 10, no. 10 (October 11, 2018): 479. http://dx.doi.org/10.3390/sym10100479.
Full textAbstract:
Compared with ordinary image classification tasks, fine-grained image classification is closer to real-life scenes. Its key point is how to find the local areas with sufficient discrimination and perform effective feature learning. Based on a bilinear convolutional neural network (B-CNN), this paper designs a local importance representation convolutional neural network (LIR-CNN) model, which can be divided into three parts. Firstly, the super-pixel segmentation convolution method is used for the input layer of the model. It allows the model to receive images of different sizes and fully considers the complex geometric deformation of the images. Then, we replaced the standard convolution of B-CNN with the proposed local importance representation convolution. It can score each local area of the image using learning to distinguish their importance. Finally, channelwise convolution is proposed and it plays an important role in balancing lightweight network and classification accuracy. Experimental results on the benchmark datasets (e.g., CUB-200-2011, FGVC-Aircraft, and Stanford Cars) showed that the LIR-CNN model had good performance in fine-grained image classification tasks.
47
Lawrence, Tom, and Li Zhang. "IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices." Sensors 19, no. 24 (December 14, 2019): 5541. http://dx.doi.org/10.3390/s19245541.
Full textAbstract:
Two main approaches exist when deploying a Convolutional Neural Network (CNN) on resource-constrained IoT devices: either scale a large model down or use a small model designed specifically for resource-constrained environments. Small architectures typically trade accuracy for computational cost by performing convolutions as depth-wise convolutions rather than standard convolutions like in large networks. Large models focus primarily on state-of-the-art performance and often struggle to scale down sufficiently. We propose a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models. IoTNet trades accuracy with computational cost differently from existing methods by factorizing standard 3 × 3 convolutions into pairs of 1 × 3 and 3 × 1 standard convolutions, rather than performing depth-wise convolutions. We benchmark IoTNet against state-of-the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource-constrained environments. We compare model accuracy and the number of floating-point operations (FLOPs) performed as a measure of efficiency. We report state-of-the-art accuracy improvement over MobileNetV2 on CIFAR-10 of 13.43% with 39% fewer FLOPs, over ShuffleNet on Street View House Numbers (SVHN) of 6.49% with 31.8% fewer FLOPs and over MobileNet on German Traffic Sign Recognition Benchmark (GTSRB) of 5% with 0.38% fewer FLOPs.
48
陳鵬, 陳鵬, Jiancheng Zhao Peng Chen, and Xiaosheng Yu Jiancheng Zhao. "LighterKGCN: A Recommender System Model based on Bi-layer Graph Convolutional Networks." 網際網路技術學刊 23, no. 3 (May 2022): 621–29. http://dx.doi.org/10.53106/160792642022052303020.
Full textAbstract:
<p>Recommender systems have been extensively utilized to meet users’ personalized needs. Collaborative filtering is one of the most classic algorithms in the recommendation field. However, it has problems such as cold start and data sparsity. In that case, knowledge graphs and graph convolutional networks have been introduced by scholars into recommender systems to solve the above problems. However, the current graph convolutional networks fail to give full play to the advantages of graph convolution since they are employed either in the embedding representations of users and commodity entities, or in the embedding representations between entities of the knowledge graphs. Therefore, LighterKGCN, a recommender system model based on bi-layer graph convolutional networks was proposed in accordance with the KGCN model and the LightGCN model. In the first layer of GCN, the model first learned the embedding representations of users and commodity entities on the user-commodity entity interaction graph. Then, the attained user embedding and commodity embedding were used as the data source for the second layer of GCN. In the second layer, the entity v and its neighborhoods were calculated using the hybrid aggregation function proposed in this paper. The result was taken as the new entity v. According to tests on three public datasets and comparison results with the KGCN, LighterKGCN improved by 0.52% and 51.16% in terms of AUC and F1 performances, respectively on the dataset of MovieLens-20M; LighterKGCN improved by 0.67% and 45.0% in terms of AUC and F1 performances, respectively on the dataset of Yelp2018; and the number was 0.67% and 36.35% in AUC and F1 performances, respectively on the dataset of Last.FM.</p> <p> </p>
49
Lee, Seonggu, and Jitae Shin. "Hybrid Model of Convolutional LSTM and CNN to Predict Particulate Matter." International Journal of Information and Electronics Engineering 9, no. 1 (March 2019): 34–38. http://dx.doi.org/10.18178/ijiee.2019.9.1.701.
Full text
50
Shen Song, Shen Song, Cong Zhang Shen Song, and Xinyuan You Cong Zhang. "Decoupling Temporal Convolutional Networks Model in Sound Event Detection and Localization." 網際網路技術學刊 24, no. 1 (January 2023): 089–99. http://dx.doi.org/10.53106/160792642023012401009.
Full textAbstract:
<p>Sound event detection is sensitive to the network depth, and the increase of the network depth will lead to a decrease in the event detection ability. However, event localization has a deeper requirement for the network depth. In this paper, the accuracy of the joint task of event detection and localization is improved by decoupling SELD-TCN. The joint task is reflected in the early fusion of primary features and the enhancement of the generalization ability of the sound event detection branch as the DOA branch mask, while the advanced feature extraction and recognition of the two branches are carried out in different ways separately. The primary features extracted by resnet16-dilated instead of CNN-Pool. The SED branch adopts linear temporal convolution to realize sound event detection by imitating the linear classifier, and ED-TCN is used for the localization detection branch. The joint training of the DOA branch and the SED branch will affect each other badly. Using the most appropriate way for both branches and masking the DOA branch with the SED branch can improve the performance of both. In the TUT Sound Events 2019 dataset, the DOA error achieved an error effect of 6.73, 8.8 and 30.7 with no overlapping source data, with two and three overlapping sources, respectively. The SED accuracy has been significantly improved, and the DOA error has been significantly reduced.</p> <p> </p>