检索结果-内蒙古大学图书馆

GRATDet:Smart Contract Vulnerability Detector Based on Graph Representation and Transformer

Computers, Materials & Continua 2023年第8期76卷 1439-1462页

作者： Peng Gong Wenzhong Yang Liejun Wang Fuyuan Wei KeZiErBieKe HaiLaTi Yuanyuan Liao College of Information Science and Engineering Xinjiang UniversityUrumqi830000China Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Xinjiang UniversityUrumqi830000China Key Laboratory of Multilingual Information Technology in Xinjiang Uygur Autonomous Region Xinjiang UniversityUrumqi830000China

Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future *** current vulnerability detection methods for contracts are either based on fixed expert rules,which are inefficient,or rely on simplistic deep learning techniques that do not fully leverage contract semantic ***,there is ample room for improvement in terms of detection *** solve these problems,this paper proposes a vulnerability detector based on deep learning techniques,graph representation,and Transformer,called *** method first performs swapping,insertion,and symbolization operations for contract functions,increasing the amount of small sample *** line of code is then treated as a basic semantic element,and information such as control and data relationships is extracted to construct a new representation in the form of a Line Graph(LG),which shows more structural features that differ from the serialized presentation of the ***,the node information and edge information of the graph are jointly learned using an improved Transformer-GP model to extract information globally and locally,and the fused features are used for vulnerability *** effectiveness of the method in reentrancy vulnerability detection is verified in experiments,where the F1 score reaches 95.16%,exceeding stateof-the-art methods.

关键词： Vulnerability detection smart contract graph representation deep learning source code

来源：评论

学校读者我要写书评

暂无评论

Research on cancer rapid diagnosis technology based on adaptive channel attention mechanism and two-dimensional spectral fusion

引用

Microchemical Journal 2025年 213卷

作者： Liu, Wei Chang, Chenjie Li, Jiahe Lv, Xiaoyi Liu, Yang Chen, Chen Chen, Cheng College of Software Xinjiang University Urumqi 830046 China School of Computer Science and Technology Xinjiang University Urumqi 830046 China Xinjiang Cloud Computing Application Laboratory Xinjiang Cloud Computing Engineering Technology Research Center Karamay 834000 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi 830046 China

With the widespread use of Artificial Intelligence (AI) in biomedicine, integrating infrared and Raman spectra with biological information offers new prospects for enhanced disease diagnosis. For these two types of data, more information can be extracted using multimodal data fusion compared to single modality, but existing studies tend to only fuse one-dimensional spectral data, ignoring the richer information of the spectra when they are converted to two-dimensional images. In this study, we propose a rapid diagnostic method for cancer, which first converts one-dimensional (1D) Raman and Infrared spectra into two-dimensional (2D) spectral images using Short-Time Fourier Transform (STFT), respectively. Then the features are fused by our designed Adaptive Graph Channel Attention Spacial Cross-Attention Fusion Module (ASCFM). This fusion module innovatively uses the adaptive graph channel attention mechanism to strengthen the model's ability to capture the key information of different spectral features, and utilizes the spatial attention fusion module and the cross-attention module for spatial information extraction and fusion. The output fused features effectively avoid feature information loss through this multimodal feature extraction and fusion, which greatly improves the performance of the model. In this study, Gradient-weighted Class Activation Mapping is also used to make the decision-making process of the neural network more interpretable. The results show that the accuracy of 2D Raman spectral images fused with 2D infrared spectral images by ASCFM followed by ResidualNetwork (ResNet) for diagnosis of lung cancer and glioma datasets is 98.88 % and 96.38 %, which suggests that it is a highly promising adjunctive technique for cancer diagnosis. © 2025

关键词： Auxiliary diagnostic technology Deep learning Infrared spectroscopy Lung cancer Multimodal fusion Raman spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Small target detection algorithm for flapping wing UAV based on improved YOLOv8 2

Small target detection algorithm for flapping wing UAV based...

引用

2nd International Symposium on Computer Applications and Information Systems, ISCAIS 2023

作者： Ma, Chen Du, Ketao Hamdulla, Askar School of Information Science and Engineering Xinjiang University Urumqi830046 China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang Urumqi China

ISBN: (纸本)9781510666665

This paper proposes an algorithm based on an improved version of YOLOv8l, which is designed for small target detection on flapping wing drones. By adding a small object detection layer and introducing Multi-head self-attention (MHSA), the algorithm effectively reduces interference from irrelevant backgrounds and enhances the network’s feature extraction performance. Experimental results on both the flapping wing dataset and the VisDrone dataset demonstrate that compared with the baseline YOLOv8l algorithm, the improved algorithm shows a 4.1% and 3.3% improvement in the mAP@.5 and mAP@.5:.95 indicators, respectively, and a 5.9% and 4% improvement on the VisDrone dataset. Particularly noteworthy is the improved algorithm’s performance on the mAP@.5 index, which achieved 50.1% on the VisDrone dataset, proving its robustness and exceptional performance in small target detection. These results illustrate the algorithm’s effectiveness and practicality, making it a valuable tool for flapping wing UAV vision applications. © 2023 SPIE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Slice Position-shifting and Multi-scale Inter-frame Proportional fusion Network for video-based pedestrian re-identification 2

Slice Position-shifting and Multi-scale Inter-frame Proporti...

引用

2nd International Symposium on Computer Applications and Information Systems, ISCAIS 2023

作者： Du, Ketao Ma, Chen Hamdulla, Askar School of Information Science and Engineering Xinjiang University Urumqi830046 China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang Urumqi China

ISBN: (纸本)9781510666665

Different from image-based pedestrian re-identification, video-based pedestrian re-identification has more available information because of more temporal information. However, previous methods are unable to extract detailed features adequately. Although the previous methods adopted the row slicing method to extract the detailed features of the image, the slicing method was too simple and the detailed features extracted were too few. We propose a slice position shifting module (SPM), which adopts a variety of ways to slice the image, to extract the feature of each image patches separately. The feature interaction is carried out by making each patches of the image generate position-shifting. How to make time clues in pedestrian re-identification data set useful is also the research focus in this field. We propose a multi-scale inter-frame proportional fusion module (MIPM) to make the features of frame t fully fuse with the front and back frames, so as to extract more the temporal clues in the data set. We will form the above two modules into Slice position-shifting and Multi-scale inter-frame proportional fusion network(SMnet) .Full experiments on the MARS dataset show that our algorithm is very useful and can reach the leading level. © 2023 SPIE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Attention-based Dual-Branch Network for Micro-Expression Recognition with Global-Local Feature Fusion 18

Attention-based Dual-Branch Network for Micro-Expression Rec...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Qi, Yupeng Ibrayim, Mayire Hamdulla, Askar Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China

ISBN: (纸本)9798350364132

Micro-expression(ME) is an uncontrollable muscle movement that appears on the face when people try to hide or inhibit their real emotions, which has the problems of short duration, small movement amplitude and uneven distribution. In order to solve the problem of localization and asymmetry in the distribution of ME features, this paper proposes a new two-branch attention network to recognize MEs, which utilizes the attention mechanism to capture global and local ME features. The network is mainly divided into three parts: data preprocessing, ME feature learning and feature fusion classification. First, the data preprocessing first extracts the ME optical flow features and then divides them into four regions, which are used as inputs to the two-branch network respectively. Second, the two-branch network uses the Inception-MSFE global multi-scale feature extraction network incorporating the attention mechanism (CBAM) and the Swin Transformer-based local feature extraction network for feature learning, respectively. Finally, MEs are predicted by fusing global and local features of MEs. Experimental validation is carried out on three datasets, CASME II, SAMM, and SMIC, which proves that Acc, UAR, and UF1 are 0.797, 0.702, and 0.698 on the SAMM dataset, respectively;Acc, UAR, and UF1 are 0.734, 0.723, and 0.729 on SMIC, respectively;and on the CASME II dataset, Acc, UAR and UF1 are 0.865, 0.872, and 0.889, respectively, which are competitive with other state-of-the-art methods. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Conditional Generative Adversarial Defogging Algorithm Based on Polarization Characteristics 33

Conditional Generative Adversarial Defogging Algorithm Based...

引用

第33届中国控制与决策会议

作者： Jingjing Zhang Kangsheng Bao Xin Zhang Fudong Nian Teng Li Yuzhou Zeng Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education (Anhui university) Key Laboratory of Polarized Light Imaging and Detection Technology in Anhui Province Hefei No.6 High School Hefei University

ISBN: (纸本)9781665431293

To overcome image degradation under the conditions of haze,and fog,a method using conditional generative adversarial defogging algorithm based on polarization characteristic is *** original images with different polarization angles were obtained from the original image,and then the polarization images were characterized using Stokes *** the relationship between Stokes vector and polarization image,each polarization image with different angles is input into the same network to extract *** the same time,the enhanced network is used to extract the characteristics of the fog area in the polarization image,and the polarization information is extracted by layer jump connection,which is fused with the image features of different *** constructing the loss function and obtaining the optimal solution,the fog-free image is finally *** results show that a clear image can be reconstructed in fog situations by using conditional generative adversarial network-based on polarization characteristics,and the structural similarity is improved by about 10%,the peak signal to noise ratio is increased by about 0.5.

关键词： polarization characteristics conditional generative adversarial network image processing image defogging feature fusion enhanced network

来源：评论

学校读者我要写书评

暂无评论

End-to-end Speech Enhancement Using Self-Attention Generative Adversarial Networks 6

End-to-end Speech Enhancement Using Self-Attention Generativ...

引用

6th International Symposium on Computer and Information processing Technology, ISCIPT 2021

作者： Cao, Zhonghui Huang, Zhihua Xinjaing University College of Information Science and Engineering Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Urumqi830001 China

ISBN: (纸本)9781665441377

Generative adversarial networks (GAN) achieve a good level of success in the speech enhancement (SE) task in recent years. However, traditional GAN for SE generates enhanced speech only as a function of local points, such that the model has difficulity in capturing long-range dependency and non-local information. In this paper, a model named self-attention GAN (ASEGAN) is proposed to estabilish connections between every sample and the rest samples in the time domain. Attention mechanism is used to model long-range dependency modeling for SE tasks. Armed with self-attention, the generator can generate the enhanced speech in which fine details at every sample are carefully coordinated with fine details in distant portions of the speech. Moreover, the discriminator can also more accurately enforce constraints on the global speech structure, thus the quality of enhanced speech by generator is better. Experimental results demonstrate that the proposed approach outperforms the competing methods measured by objective quality and speech intelligibility. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Lightweight UAV Visual Obstacle Avoidance Algorithm Based on Improved YOLOv8

引用

Computers, Materials & Continua 2024年第11期81卷 2607-2627页

作者： Zongdong Du Xuefeng Feng Feng Li Qinglong Xian Zhenhong Jia College of Computer Science and Technology Xinjiang UniversityUrumqi830046China Signal Detection and Processing Autonomous Region Key Laboratory Xinjiang UniversityUrumqi830046China Xinjiang Uygur Autonomous Region Research Institute of Measurement and Testing Urumqi830000China

The importance of unmanned aerial vehicle(UAV)obstacle avoidance algorithms lies in their ability to ensure flight safety and collision avoidance,thereby protecting people and *** propose UAD-YOLOv8,a lightweight YOLOv8-based obstacle detection algorithm optimized for UAV obstacle *** algorithm enhances the detection capability for small and irregular obstacles by removing the P5 feature layer and introducing deformable convolution v2(DCNv2)to optimize the cross stage partial bottleneck with 2 convolutions and fusion(C2f)***,it reduces the model’s parameter count and computational load by constructing the unite ghost and depth-wise separable convolution(UGDConv)series of lightweight convolutions and a lightweight detection *** on this,we designed a visual obstacle avoidance algorithm that can improve the obstacle avoidance performance of UAVs in different *** particular,we propose an adaptive distance detection algorithm based on obstacle attributes to solve the ranging problem for multiple types and irregular obstacles to further enhance the UAV’s obstacle avoidance *** verify the effectiveness of the algorithm,the UAV obstacle detection(UAD)dataset was *** experimental results show that UAD-YOLOv8 improves mAP50 by 3.4%and reduces GFLOPs by 34.5%compared to YOLOv8n while reducing the number of parameters by 77.4%and the model size by 73%.These improvements significantly enhance the UAV’s obstacle avoidance performance in complex environments,demonstrating its wide range of applications.

关键词： Unmanned aerial vehicle obstacle detection obstacle avoidance algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of multi-classification method of skin cancer based on dermoscopic image 21

Application of multi-classification method of skin cancer ba...

引用

2nd International Symposium on Artificial Intelligence for Medicine Sciences, ISAIMS 2021

作者： Chen, Qian Li, Min Chen, Cheng Chen, Chen Lv, Xiaoyi College of Software Key Laboratory of Software Engineering Technology Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China College of Information Science and Engineering Xinjiang University Urumqi China

ISBN: (纸本)9781450395588

As a kind of cancer with high incidence, skin cancer seriously threatens people's life and health. Early detection, early diagnosis, and early treatment are one of the effective ways to increase the survival rate of patients with skin diseases. Therefore, this paper used the ResNet50 model as a feature extractor based on deep learning, and combined machine learning algorithms to explore the heterogeneity among multi-type of skin cancer, and tried to construct the best performance computer-aided diagnosis model. The research first used preprocessing techniques such as hair noise removal and data enhancement, and then achieved a classification accuracy of 90.497% on the public data set of ISIC2019. The proposed model effectively relieves the huge work pressure of dermatologists, and provides a reference for the better use of dermoscopic images for intelligent diagnosis and classification of skin cancer. © 2021 ACM.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Weak Change detection of Wide field Foggy Video Image 24

Weak Change Detection of Wide field Foggy Video Image

引用

4th International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2024

作者： Li, Wen Jia, Zhenhong Song, Sensen Huang, Xiaohui Wang, Jiajia Zhou, Gang Shi, Fei School of Computer Science and Technology Xinjiang University Urumqi Xinjiang China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi Xinjiang China

ISBN: (纸本)9798400710247

Hawk-eye devices are often used in surveillance and security, and the video images collected by them have a wide field of view. Under foggy conditions, the video images captured by eagle-eye surveillance have low contrast and details are easily lost. In order to solve these problems, this paper proposes a change detection algorithm for foggy wide field video images based on the Discrete Wavelet Transform (DWT) image fusion and FCM clustering algorithm. Firstly, the improved neighborhood ratio operator and the most value mean pixel ratio operator are used to generate the disparity map, and then the DWT is used to fuse the disparity map, and after obtaining the fused disparity map, the soft threshold function and the FCM clustering algorithm are used to carry out the coarse classification and fine classification respectively, and obtain the final change detection result map. © 2024 Copyright held by the owner/author(s).

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：