VGG16 Network Research Articles

DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation

Plant diseases threaten agricultural sustainability by reducing crop yields. Rapid and accurate disease identification is crucial for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of automated systems for disease detection. This study focuses on enhancing the classification of diseases and estimating their severity in coffee leaf images. To do so, we propose a novel approach as the preprocessing step for the classification in which enhanced multivariance product representation (EMPR) is used to decompose the considered image into components, a new image is constructed using some of those components, and the contrast of the new image is enhanced by applying high-dimensional model representation (HDMR) to highlight the diseased parts of the leaves. Popular convolutional neural network (CNN) architectures, including AlexNet, VGG16, and ResNet50, are evaluated. Results show that VGG16 achieves the highest classification accuracy of approximately 96%, while all models perform well in predicting disease severity levels, with accuracies exceeding 85%. Notably, the ResNet50 model achieves accuracy levels surpassing 90%. This research contributes to the advancement of automated crop health management systems.

Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism

Northern corn leaf blight (NCLB) is caused by a fungus and can be susceptible to the disease throughout the growing period of corn, posing a significant impact on corn yield. Aiming at the problems of under-segmentation, over-segmentation, and low segmentation accuracy in the traditional segmentation model of northern corn leaf blight, this study proposes a segmentation method based on an improved U-Net network model. By introducing a convolutional layer and maximum pooling layer to a VGG19 network, the channel attention module and spatial attention module (CBAM) are fused, and the squeeze excitation (SE) attention mechanism is combined. This enhances image feature decoding, integrates feature maps of each layer, strengthens the feature extraction process, expands the sensory fields and aggregates context information, and reduces the loss of location and dense semantic information caused by the pooling operation. Findings from the study show that the proposed NCLB-Net has significantly improved the MIoU and PA indexes, reaching 92.43% and 94.71%, respectively. Compared with the traditional methods, U-Net, SETR, DAnet, OCnet, PSPNet, etc., the MIoU is improved by 20.81%, 16.10%, 9.79%, 5.27%, and 11.06%, and the PA is improved by 11.49%, 8.18%, 9.54%, 13.11%, and 6.26%, respectively.

Enhanced Magnetic Resonance Imaging-Based Brain Tumor Classification with a Hybrid Swin Transformer and ResNet50V2 Model

Brain tumors can be serious; consequently, rapid and accurate detection is crucial. Nevertheless, a variety of obstacles, such as poor imaging resolution, doubts over the accuracy of data, a lack of diverse tumor classes and stages, and the possibility of misunderstanding, present challenges to achieve an accurate and final diagnosis. Effective brain cancer detection is crucial for patients’ safety and health. Deep learning systems provide the capability to assist radiologists in quickly and accurately detecting diagnoses. This study presents an innovative deep learning approach that utilizes the Swin Transformer. The suggested method entails integrating the Swin Transformer with the pretrained deep learning model Resnet50V2, called (SwT+Resnet50V2). The objective of this modification is to decrease memory utilization, enhance classification accuracy, and reduce training complexity. The self-attention mechanism of the Swin Transformer identifies distant relationships and captures the overall context. Resnet 50V2 improves both accuracy and training speed by extracting adaptive features from the Swin Transformer’s dependencies. We evaluate the proposed framework using two publicly accessible brain magnetic resonance imaging (MRI) datasets, each including two and four distinct classes, respectively. Employing data augmentation and transfer learning techniques enhances model performance, leading to more dependable and cost-effective training. The suggested model achieves an impressive accuracy of 99.9% on the binary-labeled dataset and 96.8% on the four-labeled dataset, outperforming the VGG16, MobileNetV2, Resnet50V2, EfficientNetV2B3, ConvNeXtTiny, and convolutional neural network (CNN) algorithms used for comparison. This demonstrates that the Swin transducer, when combined with Resnet50V2, is capable of accurately diagnosing brain tumors. This method leverages the combination of SwT+Resnet50V2 to create an innovative diagnostic tool. Radiologists have the potential to accelerate and improve the detection of brain tumors, leading to improved patient outcomes and reduced risks.

Coupling design features of material surface treatment for ceramic products based on ResNet

Abstract Ceramic products is one of the important carriers of various civilizations, reflecting the lifestyle, aesthetic concepts, and technological level of society at that time. In order to study the surface treatment design features of ceramic craft products, this article analyzed the ceramic features through computer vision technology and used residual neural networks to detect the surface treatment features of ceramic craft products. The extracted texture features were classified to study and analyze the coupling features of different glazes, colors, and shapes on the formation of different textures. This study used ResNeXt50-SSD, which combined ResNeXt50 and SSD (Single Shot MultiBox Detector) algorithms, to compare feature detection with LeNet-5, VGG-16, and MobileNetV2 network models. From the experimental findings, it can be concluded that ResNeXt50-SSD was the most effective for feature recognition of ceramic craft products, with precision, recall, and mAP of 94.3, 92.1, and 89.5%, respectively. Therefore, the combination of ResNeXt50 and SSD algorithms is an effective method for detecting surface treatment features of ceramic craft products.

Research on Target Image Classification in Low-Light Night Vision.

In extremely dark conditions, low-light imaging may offer spectators a rich visual experience, which is important for both military and civic applications. However, the images taken in ultra-micro light environments usually have inherent defects such as extremely low brightness and contrast, a high noise level, and serious loss of scene details and colors, which leads to great challenges in the research of low-light image and object detection and classification. The low-light night vision image used as the study object in this work has an excessively dim overall picture and very little information about the screen's features. Three algorithms, HE, AHE, and CLAHE, were used to enhance and highlight the image. The effectiveness of these image enhancement methods is evaluated using metrics such as the peak signal-to-noise ratio and mean square error, and CLAHE was selected after comparison. The target image includes vehicles, people, license plates, and objects. The gray-level co-occurrence matrix (GLCM) was used to extract the texture features of the enhanced images, and the extracted image texture features were used as input to construct a backpropagation (BP) neural network classification model. Then, low-light image classification models were developed based on VGG16 and ResNet50 convolutional neural networks combined with low-light image enhancement algorithms. The experimental results show that the overall classification accuracy of the VGG16 convolutional neural network model is 92.1%. Compared with the BP and ResNet50 neural network models, the classification accuracy was increased by 4.5% and 2.3%, respectively, demonstrating its effectiveness in classifying low-light night vision targets.

Facial expression recognition based on convolutional network attention mechanism

Aiming at the problems of large number of parameters and weak recognition ability in expression recognition, a method of facial expression recognition based on convolutional network is proposed. An improved residual module is introduced to reduce the number of parameters while enhancing the attention to the expression area; the channel-space attention mechanism is used to realize the weight distribution of different dimensions and positions of the expression area extracted by the network, focusing on the subtle difference feature information in the key points of the expression; the detail module is used to further extract the deep feature information. In order to obtain higher accuracy, a joint loss function is introduced to increase the out-of-class distance and reduce the intra-class distance to improve the accuracy of expression recognition. This paper applies this network to the datasets FER2013 and CK+. The experimental results show that the average recognition rate of this algorithm is respectively and 63.91%，97.98%the number of parameters is 11.34 M. Compared with VGG network, residual network, etc., this model not only improves the recognition rate but also reduces the redundant parameters.

A Machine Learning and Deep Learning-Based Account Code Classification Model for Sustainable Accounting Practices

Accounting account codes are created within a specific logic framework to systematically and accurately record a company’s financial transactions. Currently, accounting reports are processed manually, which increases the likelihood of errors and slows down the process. This study aims to use image processing techniques to predict cash codes in accounting reports, automate accounting processes, improve accuracy, and save time. Deep learning embeddings from Inception V3, SqueezeNet, VGG-19, VGG-16, Painters, and DeepLoc networks were utilized in the feature extraction phase. A total of six learning algorithms, namely Logistic Regression, Gradient Boosting, Neural Network, kNN, Naive Bayes, and Stochastic Gradient Descent were employed to classify the images. The highest accuracy rate of 99.2% was achieved with the combination of the Inception V3 feature extractor and the Neural Network classifier. The results demonstrate that image processing methods significantly reduce error rates in accounting records, accelerate processes, and support sustainable accounting practices. This indicates that image processing techniques have substantial potential to contribute to digital transformation in accounting, helping businesses achieve their sustainability goals.

An efficient CNN accelerator for pattern-compressed sparse neural networks on FPGA

Currently, the sparsity of weights and activations are mainly utilized to improve the energy efficiency and computational performance of CNN accelerators. However, the irregular sparsity of weights and activations can lead to problems such as mapping access conflict and imbalanced workload, which poses great challenges to the efficient computation of sparse networks. To address those problems, this paper proposes a CNN accelerator for pattern-compressed sparse neural networks on FPGA to achieve efficient inference acceleration. It mainly includes three parts: first, we propose a convolutional kernel grouping fusion method to achieve a balanced workload of weights. Second, we propose an activation hash mapping conflict reduction method to drastically reduce the mapping access conflict rate. Finally, we further propose a hierarchical mapping computing architecture to achieve efficient processing of mapping access conflicts and balanced adaptation of weight loads. To verify the effectiveness of the method proposed in this paper, our accelerator is designed and implemented on the Zynq UltraScale+ MPSoC ZCU102 evaluation board and evaluated by running VGG16 and ResNet50 networks. The experimental results show that the method proposed in this paper can reduce the mapping conflicts by more than 97 % and improve the utilization rate of processing element (PE) by 1.67×. Furthermore, the accelerator implemented in this paper can achieve 393.2 GOPs throughput, 1.40–3.25× computational performance, and 1.11–7.34× energy efficiency improvement.

Deep learning classification performance for diagnosing condylar osteoarthritis in patients with dentofacial deformities using panoramic temporomandibular joint projection images.

The present study aimed to assess the consistencies and performances of deep learning (DL) models in the diagnosis of condylar osteoarthritis (OA) among patients with dentofacial deformities using panoramic temporomandibular joint (TMJ) projection images. A total of 68 TMJs with or without condylar OA in dentofacial deformity patients were tested to verify the consistencies and performances of DL models created using 252 TMJs with or without OA in TMJ disorder and dentofacial deformity patients; these models were used to diagnose OA on conventional panoramic (Con-Pa) images and open (Open-TMJ) and closed (Closed-TMJ) mouth TMJ projection images. The GoogLeNet and VGG-16 networks were used to create the DL models. For comparison, two dental residents with < 1year of experience interpreting radiographs evaluated the same condyle data that had been used to test the DL models. On Open-TMJ images, the DL models showed moderate to very good consistency, whereas the residents' demonstrated fair consistency on all images. The areas under the curve (AUCs) of both DL models on Con-Pa (0.84 for GoogLeNet and 0.75 for VGG-16) and Open-TMJ images (0.89 for both models) were significantly higher than the residents' AUCs (p < 0.01). The AUCs of the DL models on Open-TMJ images (0.89 for both models) were higher than the AUCs on Closed-TMJ images (0.72 for both models). The DL models created in this study could help residents to interpret Con-Pa and Open-TMJ images in the diagnosis of condylar OA.

HCPrune: A Hierarchical Classification Pruning Method Based on Receptive Field Size

Abstract Model pruning, as an optimisation algorithm for convolutional neural network (CNN) models, can effectively compress and accelerate various complex CNN models. Recent network pruning algorithms usually focus on removing unimportant and redundant convolutional kernels or channels in the network. This paper propose a hierarchical pruning algorithm, HCPrune, which classifies and then prunes the convolutional layers of a CNN model to improve the model prediction accuracy while reducing the number of parameters and FLOPs. In this paper, the CNN convolutional layers are divided in terms of the size relationship between the receptive field of each layer of the network and the resolution of the input image, and use the VGG and Resnet series of networks based on some popular pruning methods to conduct experiments on the CIFAR10 and CIFAR100 datasets and ensure that the same number of parameters and FLOPs compared with the basic pruning methods. The VGG16 network improves the accuracy by 0.42% in CIFAR10 and 0.47% in CIFAR100, and the ResNet164 improves the accuracy by about 0.2% in the same configuration.

Differential diagnosis between low-risk and high-risk thymoma: Comparison of diagnostic performance of radiologists with and without deep learning model.

There are few CT-based deep learning (DL) studies on thymoma according to the World Health Organization classification. To develop a CT-based DL model to distinguish between low-risk and high-risk thymoma and to compare the diagnostic performance of radiologists with and without the DL model. 159 patients with 160 thymomas were included. A fine-tuning VGG16 network model with Adam optimizer was used, followed by k-fold cross validation. The dataset consisted of three axial slices, including the maximum tumor size from the CT volume data. The data were augmented 50 times by rotation, zoom, shear, and horizontal/vertical flip. Three independent networks for the CT dataset were considered, and the result was determined by voting. Three radiologists independently diagnosed thymomas with and without the model. The area under the curve (AUC) of the diagnostic performance was compared using receiver operating characteristic analysis. Accuracy of the DL model was 71.3%. Diagnostic performance of the radiologists was as follows: AUC and accuracy without the DL model, 0.61-0.68 and 61.9%-69.3%; and with the DL model, 0.66-0.69 and 68.1%-70.0%, respectively. AUC of the diagnostic performance showed no significant differences between radiologists with and without the DL model. The DL model tended to increase the diagnostic accuracy, but AUC was not significantly improved. Diagnostic performance of the DL was comparable to that of radiologists. The DL model assistance tended to increase diagnostic accuracy.

Intelligent extraction of salient objects from fuzzy distorted images based on multi-scale convolution

ABSTRACT To solve the problem of how to obtain important information from fuzzy distorted images, an intelligent method for extracting salient objects from fuzzy distorted images based on multi-scale convolution is proposed. A multi-scale deformation feature convolution network is established to extract the salient features of fuzzy distorted images. Among them, the multi-scale convolution network VGG-16 extracts the shallow features of the fuzzy distortion image through the convolution layer operation, uses the multi-scale convolution kernel to extract the fuzzy distortion image in parallel, and introduces the self-attention mechanism to make the extracted features more relevant, Input the fused features into the proposed area extraction network, Through the target area detection network, the proposed target area of the fuzzy distortion image is classified and position regression is performed to obtain the final salient target of the fuzzy distortion image. The experimental results show that this method can accurately recognize the contour of salient objects, and extract salient objects from fuzzy distorted images; The extracted salient objects have high accuracy, low mean square error and similarity of 92.9% with the original image; For the salient target extraction in various scenarios, it shows high advantages.

Flow style-aware network for arbitrary style transfer

Researchers have recently proposed arbitrary style transfer methods based on various model frameworks. Although all of them have achieved good results, they still face the problems of insufficient stylization, artifacts and inadequate retention of content structure. In order to solve these problems, we propose a flow style-aware network (FSANet) for arbitrary style transfer, which combines a VGG network and a flow network. FSANet consists of a flow style transfer module (FSTM), a dynamic regulation attention module (DRAM), and a style feature interaction module (SFIM). The flow style transfer module uses the reversible residue block features of the flow network to create a sample feature containing the target content and style. To adapt the FSTM to VGG networks, we design the dynamic regulation attention module and exploit the sample features both at the channel and pixel levels. The style feature interaction module computes a style tensor that optimizes the fused features. Extensive qualitative and quantitative experiments demonstrate that our proposed FSANet can effectively avoid artifacts and enhance the preservation of content details while migrating style features.

CLASSIFICATION OF ACUTE LYMPHOBLASTIC LEUKEMIA CELLS USING ARTIFICIAL INTELLIGENCE

Due to the morphological similarity between immature lymphoblasts (cancerous cells) to lymphocytes (non-cancerous cells), detecting Acute Lymphoblastic Leukemia poses a significant challenge for pathologists. These cells, which exhibit a similar pattern, can lead to various errors during the diagnosis of the disease. In this study, the cancerous and non-cancerous cells were classified using 3 different artificial intelligence approaches. In the first approach, the classification process was carried out by training Convolutional Neural Networks in 4 different architectures. In the second approach, a hybrid approach was proposed by combining the convolution layer of the CNN model as the feature extractor with the Support Vector Machine, Naive Bayes and Random Forest algorithms as the classifier. The classification processes were carried out by training the proposed second approach. In the third approach, the classification process was performed using transfer learning process and ResNet50 and VGG16 networks. In all experiments, the effects of hyper-parameter and dataset changes on model performance were also examined. The results obtained by these three approaches were compared using the Accuracy, Precision, Recall, F-score, and AUC performance measures. It was determined that the most successful results were obtained with the 1st approach using the Dataset3.

Efficient Convolutional Neural Networks Utilizing Fine-Grained Fast Fourier Transforms

Convolutional Neural Networks (CNNs) are among the most prevalent deep learning techniques employed across various domains. The computational complexity of CNNs is largely attributed to the convolution operations. These operations are computationally demanding and significantly impact overall model performance. Traditional CNN implementations convert convolutions into matrix operations via the im2col (image to column) technique, facilitating parallelization through advanced BLAS libraries. This study identifies and investigates a significant yet intricate pattern of data redundancy within the matrix-based representation of convolutions, a pattern that, while complex, presents opportunities for optimization. Through meticulous analysis of the redundancy inherent in the im2col approach, this paper introduces a mathematically succinct matrix representation for convolution, leading to the development of an optimized FFT-based convolution with finer FFT granularity. Benchmarking demonstrates that our approach achieves an average speedup of 14 times and a maximum speedup of 17 times compared to the regular FFT convolution. Similarly, it outperforms the Im2col+GEMM approach from NVIDIA’s cuDNN library, achieving an average speedup of three times and a maximum speedup of five times. Our FineGrained FFT convolution approach, when integrated into Caffe, a widely used deep learning framework, leads to significant performance gains. Evaluations using synthetic CNNs designed for real-world applications show an average speedup of 1.67 times. Furthermore, a modified VGG network variant achieves a speedup of 1.25 times.

Deep Learning and MRI Biomarkers for Precise Lung Cancer Cell Detection and Diagnosis

Aim This research work aimed to combine different AI methods to create a modular diagnosis system for lung cancer, including Convolutional Neural Network (CNN), K-Nearest Neighbors (KNN), VGG16, and Recurrent Neural Network (RNN) on MRI biomarkers. Models have then been evaluated and compared in their effectiveness in detecting cancer, using a meticulously selected dataset containing 2045 MRI images, with emphasis being put on documenting the benefits of the multimodal approach for attacking the complexities of the disease. Background Lung cancer remains the most common cause of cancer death in the world, partly because of the challenges in diagnosis and the late stage of presentation. Although Magnetic Resonance Imaging (MRI) has become a critical modality in the identification and staging of lung cancer, too often, its effectiveness is curtailed by the interpretative variance among radiologists. Recent advances in machine learning hold great promise for augmenting the analysis of MRI and perhaps even increasing diagnostic accuracy with the start of timely treatment. In this work, the integration of advanced machine learning models with MRI biomarkers to solve these problems has been investigated. Objective The purpose of the present paper was to assess the effectiveness of integrating various machine-learning models with MRI biomarkers for lung cancer diagnostics, such as CNN, KNN, VGG16, and RNN. The dataset involved 2,045 MRI images, and the performances of the models were investigated by comparing their performance metrics to determine the best configuration of interconnection while underpinning the necessity of this multimodal approach for accurate diagnoses and, consequently, better patient outcomes. Methods For this study, we used 2045 MRI images, with 70% for training and 30% for validation. We used four machine-learning models to work on the photos: CNN, KNN, VGG16, and RNN. Systematic performance measures were included in the study: accuracy, recall, precision, and F1 score. The confusion matrices of this study compared the diagnostic power of every model to comprehend the pragmatic use of the models in a real-world predictive capability. Results The scores for the model were found to be better with the convolutional neural network in terms of recall, accuracy in measures tested, precision, and F1. The rest of the models, KNN, VGG16, and RNN, performed decently but were slightly lower in performance than CNN. The in-depth analysis through confusion matrices thus established the predictive reliability of the models in revealing immense insight into the capability of identifying true positives and minimizing false negatives in enhancing the diagnostic accuracy of lung cancer detection. Conclusion The findings obtained have shown further support and great potential for integrating advanced machine learning models with MRI biomarkers to improve lung cancer diagnosis. The high performance of CNN, high sensitivity and specificity of the KNN model, and robustness of results obtained from VGG16 and RNN models have pointed to the potential feasibility of AI in the accurate detection of cancer. Our work has shown strong support for this multimodal diagnostic approach, which might impact future practice in oncology through the integration of AI to improve treatment strategies and patient outcomes in medical imaging.

Robust filter pruning guided by deep frequency-features for edge intelligence

With the popularity of mobile applications, smart terminals require the deployment of lightweight deep neural networks (DNNs). However, those lightweight DNNs deployed on resource-constrained edge devices, have serious security vulnerabilities to adversarial examples. Pruning methods have been widely used to obtain lightweight DNNs, which mainly focus on improving classification accuracy, but ignore robustness. To this end, we present a Fourier space-based robust pruning algorithm (FSRP). We find that a robust network pays more attention to the low-frequency region of the adversarial examples’ feature maps, but ignores the high-frequency region. According to this finding, we design a filter robust indicator, a ratio of low-frequency components to high-frequency components of the feature map, to guide the pruning process. With this new robust pruning criterion, we adopt a strategy of local pruning that removes the filters with low robustness layer by layer in the model. Extensive experiments on CIFAR10/CIFAR100 and ImageNet show that the robust pruning accuracy is significantly improved under the FSRP robust pruning criterion. On CIFAR10, a pruning ratio of 90% on the VGG16 network still shows a 14.1% improvement in robust accuracy under auto attacks (AA).

Research on Lightweight Method of Insulator Target Detection Based on Improved SSD.

Aiming at the problems of a large volume, slow processing speed, and difficult deployment in the edge terminal, this paper proposes a lightweight insulator detection algorithm based on an improved SSD. Firstly, the original feature extraction network VGG-16 is replaced by a lightweight Ghost Module network to initially achieve the lightweight model. A Feature Pyramid structure and Feature Pyramid Network (FPN+PAN) are integrated into the Neck part and a Simplified Spatial Pyramid Pooling Fast (SimSPPF) module is introduced to realize the integration of local features and global features. Secondly, multiple Spatial and Channel Squeeze-and-Excitation (scSE) attention mechanisms are introduced in the Neck part to make the model pay more attention to the channels containing important feature information. The original six detection heads are reduced to four to improve the inference speed of the network. In order to improve the recognition performance of occluded and overlapping targets, DIoU-NMS was used to replace the original non-maximum suppression (NMS). Furthermore, the channel pruning strategy is used to reduce the unimportant weight matrix of the model, and the knowledge distillation strategy is used to fine-adjust the network model after pruning, so as to ensure the detection accuracy. The experimental results show that the parameter number of the proposed model is reduced from 26.15 M to 0.61 M, the computational load is reduced from 118.95 G to 1.49 G, and the mAP is increased from 96.8% to 98%. Compared with other models, the proposed model not only guarantees the detection accuracy of the algorithm, but also greatly reduces the model volume, which provides support for the realization of visible light insulator target detection based on edge intelligence.

A Hybrid VGG 19 and Capsule Network Based Deep Learning Model for Lung Cancer Diagnosis using CT S can Images

Objectives: Lung cancer is one of the most prevalent causes of carcinoma-related fatalities globally; precise and effective diagnostic instruments are desperately needed. Researchers and physicians continue to encounter difficulties when aiming to employ deep learning models in healthcare environments for recognizing lung cancer and to achieve higher sensitivity and accuracy on large data sets, despite several advancements in this field. Our study builds upon an extensive review of existing lung cancer detection methods, highlighting their strengths and weaknesses. The performance of this model deteriorates when there are variances in Lung CT image features such as rotation, tiling, and other aberrant image orientations. This study aims to address the issues associated with variations in lung CT images. Methods: A hybrid deep learning model that blends the potency of CNNs with the cutting-edge design of capsule networks is proposed. Inspired by recent advancements, our model integrates the VGG19 and Capsule Network architectures to address orientation-related challenges often encountered in traditional CNN-based approaches. The creation, training, and assessment of this hybrid model for lung nodule identification and categorization are our main research goals. Findings: We anticipate that our research has yielded several valuable outcomes, including improved nodule classification accuracy of 99.20%, reduced false positive rates, and minimized training times. Novelty: This research employing a hybrid deep learning model that combines the capabilities of the VGG-19 and capsule network could lead to more widespread utilization in cancer diagnosis by enhancing early lung cancer detection and developing the field of medical image analysis. The shortcomings of convolutional neural networks are addressed with Capsule Network. Leveraging the knowledge and insights gained from lung cancer detection, our research also investigates the potential applicability of our methodology to identify other types of medical image classification such as breast and ovarian cancer. Keywords: Computed Tomography, Lung cancer, Deep Learning, CNN, VGG19, Capsule Network

The assessment of wemaps audit requirements based on deep learning

ABSTRACT As a specialized map product, Wemaps must comply with relevant laws and regulations. Map audit plays a crucial role in ensuring map quality by preventing the production and dissemination of problem maps, as well as safeguarding national sovereignty, security, and interests. The user base for Wemaps is diverse, encompassing various types of maps, vast amounts of map data, and high expectations for timely dissemination. However, the current map audit process is inefficient and burdensome, failing to meet the specific needs of Wemaps audits. The key to solving this problem lies in the ability to automate and rapidly assess the audit requirements of Wemaps, approving those that require audit and promptly releasing those that do not. This study aims to establish an automated Wemaps audit assessment model using convolutional neural networks and transfer learning methods. By doing so, the burden of map audit can be reduced, and dissemination efficiency can be improved. The main contributions of this study are as follows: (1) Establishment of a dataset for assessing Wemaps audit requirements. (2) Utilization of VGG16 and ResNet50 neural network models for assessing Wemaps audit requirements; (3) Development of an optimal Wemaps audit assessment model through various experiments and training methods. (4) Analysis of factors influencing audit assessments based on measurement indicators and visualized results of the model. The experiments demonstrate that this method achieves high accuracy and can provide assessment services for public map audit requirements.