检索结果-内蒙古大学图书馆

A special image encryption strategy based on a novel digital chaotic system and binary block compressed sensing for fixed-point DSP

引用

NONLINEAR DYNAMICS 2025年第9期113卷 10535-10558页

作者： Dou, Yuqiang Yue, Shuang Zhang, Xinke Fan, Haiju Li, Ming Zhang, Mingzhu Henan normal Univ Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang 453007 Henan Peoples R China

The paper introduced an image encryption strategy that uses a novel digital chaotic system and block compressed sensing (BCS). It is better suited for fixed-point digital signal processors (DSP). Firstly, the digital logistic chaotic system and the digital Chebyshev chaotic systems are combined to create a novel digital chaotic system. After that, a binary measurement matrix is created using the suggested novel digital chaotic system. Next, the obtained images are processed in blocks and the image is compressed sensing by the measurement matrix. Finally, re-encrypting the cipher images by diffusion processing over a finite domain. The Projected Landwebe algorithm and wiener filter are used to speed up the decryption process and improve the quality of image decryption. Simulation tests and performance analysis demonstrate the strong unpredictability of the proposed digital chaotic system, when the computer word length is 32, the Lyapunov exponent is about 20. It can be used to generate an image encryption scheme that is resistant to noise and exhaustion attacks and yields superior image recovery quality. When the sampling rate is 0.25, the average PSNR value and MSSIM value of the recovered image are 28.1180 dB and 0.87904, and the average information entropy of the encrypted image is 7.9991.

关键词： Image encryption The novel digital chaotic system Binary measurement matrix Block compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Community Hiding Based on Safety Index in Social Networks

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2025年 1-15页

作者： Huang, Mengke Li, Yongbo Wang, Yanwei Liu, Dong Henan Normal Univ Coll Comp & Informat Engn Xinxiang 453007 Henan Peoples R China Key Lab Artificial Intelligence & Personalized Lea Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & assessment Xinxiang Henan Peoples R China

Community detection algorithms have become a valuable tool for analyzing complex social networks. It assists scholars in comprehending network topology intuitively and finding hidden human relations in society network. On the contrary, the community hidden problem is raised because some special organizations need to cooperate in social networks while avoiding discovery by community detection algorithms. To solve this problem, a new safety-based community hiding algorithm is advanced in this paper, which hides the target community by disrupting a limited number of links. First, a safety gain function was designed to find the appropriate link by measuring the denseness of the community. Subsequently, we conducted extensive experiments using eight datasets and five classical community detection algorithms, comparing our method with the latest community hiding algorithms. The experimental results confirm that our proposed algorithm is more efficient than previous community hiding algorithms.

关键词： Community hiding Community detection Community deception Social network Complex network

来源：评论

学校读者我要写书评

暂无评论

MANet: A Multiview Attention Network for Automatic ICD Coding 13th

MANet: A Multiview Attention Network for Automatic ICD Codin...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Shen, Hualei Wang, Haizhu Shangguan, Guoqing Li, Dong Henan Normal Univ Coll Comp & Informat Engn Xinxiang Henan Peoples R China Key Lab Artificial Intelligence & Personalized Le Xinxiang Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang Henan Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Automatically assigning multiple International Classification of Diseases (ICD) codes to a clinical note is challenging due to the unstructured and verbose nature of medical records. Currently, most methods employ deep neural networks to learn the representation of clinical notes from a single perspective. These single-view-based methods overlook the exploitation and fusion of multiview features to enhance the precision of ICD coding. In this paper, we propose a new Multiview Attention Network (MANet) to extract and fuse multiview features for ICD coding. MANet includes a specially designed multiview attention scheme to extract and fuse coarse, global, and local features from clinical notes. Additionally, a novel cascaded multilayer perceptron (MLP) block and a multiscale convolution block are designed to extract global and local features, respectively. Self-attention and cross-attention are integrated to effectively fuse these multiview features, generating more informative and discriminative representations. Extensive experiments conducted on the popular MIMIC-III and MIMIC-IV-ICD9 datasets demonstrate the superiority of our proposed MANet over state-of-the-art methods. On MIMIC-III, MANet achieves a Macro-AUC of 0.953, Micro-AUC of 0.993, Macro-F1 of 0.135, Micro-F1 of 0.596, precision at top 8 (P@8) of 0.773, and precision at top 15 (P@15) of 0.617. On MIMIC-IV-ICD9, MANet achieves a Macro-AUC of 0.968, Micro-AUC of 0.996, Macro-F1 of 0.146, Micro-F1 of 0.614, P@8 of 0.698, and P@15 of 0.526.

关键词： Automatic ICD coding Multiview features fusion Multiview attention

来源：评论

学校读者我要写书评

暂无评论

MFAR-Net: Multi-level feature interaction and Dual-Dimension adaptive reinforcement network for breast lesion segmentation in ultrasound images

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 272卷

作者： Liu, Guoqi Dong, Shaocong Zhou, Yanan Yao, Sheng Liu, Dong Henan Normal Univ Coll Comp & Informat Engn Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & assessment Xinxiang 453007 Henan Peoples R China

Objective: Precise segmentation of breast ultrasound images is essential for early breast cancer screening. Convolutional neural networks (CNNs) have made great progress in lesion segmentation in breast ultrasound images. These methods still have three limitations: (1) They lack the ability to model global information;(2) The importance of interaction between different scale features is not sufficiently emphasized;(3) The abilities of feature fusion and lesion region correction in the decoding process are ignored. Methods: Considering the above problems, we propose a Multi-level feature interaction and Dual-Dimension adaptive reinforcement network (MFAR-Net). Our design is as follows: (1) Introduce transformer as a global context-aided encoding branch (GCA) to establish long-term dependencies;(2) The multi-level feature interaction (MFI) module uses the feature interaction of different receptive fields to capture detailed information and alleviate the influence of grid;(3) Dual-dimension adaptive reinforcement (DAR) enhances and corrects the original features in both spatial and channel dimension, providing a reliable premise for subsequent supplementary detailed information. Main results: Extensive experiments results on four public ultrasound datasets show that the proposed MFAR-Net outperforms other state-of-the-art (SOTA) methods. Furthermore, compared with the suboptimal method, we significantly improve the Dice metrics by 2.68% on the BUSImalignant datasets, showing strong competitiveness. Significance: (1) The segmentation accuracy of breast lesions is further improved under the premise of a small number of parameters;(2) The ability to adapt to other ultrasonic images is maintained, and our network has strong robustness and good generalization performance.

关键词： Breast lesion Convolutional neural network Parallel dual encoder architecture Transformer

来源：评论

学校读者我要写书评

暂无评论

An image encryption algorithm based on a novel 1D chaotic map and compressive sensing

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第16期80卷 24437-24454页

作者： Dou, Yuqiang Li, Ming Henan Normal Univ Big Data Engn Lab Teaching Resources & Assessment Xinxiang 453007 Henan Peoples R China

A new image encryption algorithm is presented based on a novel chaotic map and compressive sensing with excellent performance. At first, the sparse coefficient matrix is acquired by discrete wavelet transform (DWT) of the original image. Secondly, the SHA-512 hash value of the original image are regarded as the initial values of two novel 1D chaotic maps to generate two chaotic sequences. Furthermore, the measurement matrix is generated by one of the two chaotic maps. Next, the measurement result is scrambled based on bit-plane operations by another chaotic sequence. At last, the diffusion and rotation operations are carried out on the shuffled matrix to improve the security index of the proposed algorithm. It is indicated through the analyses of simulation experiment that the presented encryption algorithm is effective to resist statistical attacks, plaintext attacks and brute-force attacks and has good compression effect and robustness.

关键词： Image encryption Compressive sensing Novel 1D chaotic map Bit-level operation

来源：评论

学校读者我要写书评

暂无评论

A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function

引用

IEEE ACCESS 2020年 8卷 64783-64798页

作者： Liu, Guoqi Li, Xusheng Chang, Baofang Dong, Yifei Henan Normal Univ Coll Comp & Informat Engn Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang 453007 Henan Peoples R China

Superpixel is an essential tool for computer vision. In practice, classic superpixel algorithms do not exhibit good boundary adherence with fewer superpixels, which will greatly hamper further analysis. To remedy the defect, a superpixel boundary optimization framework is proposed in this paper. There are three steps in the framework. Firstly, based on the proposed information measure function, the under-segmented superpixels generated by classic superpixel algorithms are screened out. Secondly, with the two invariant centroids method, these under-segmented superpixels are re-segmented to improve the accuracy in boundary adherence. Finally, smaller superpixels are merged to maintain the same number with initial superpixels. Quantitative evaluations on the BSDS500 exhibit that the performance of the classic superpixel algorithms is improved by employing the framework, especially on the condition of fewer superpixels.

关键词： Superpixel boundary optimization framework information measure function weighted directed graph

来源：评论

学校读者我要写书评

暂无评论

DLS: A Link Prediction Method Based on Network Local Structure for Predicting Drug-Protein Interactions

引用

FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY 2020年 8卷 330页

作者： Wang, Wei Lv, Hehe Zhao, Yuan Liu, Dong Wang, Yongqing Zhang, Yu Henan Normal Univ Coll Comp & Informat Engn Dept Comp Sci & Technol Xinxiang Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang Henan Peoples R China

The studies on drug-protein interactions (DPIs) had significant for drug repositioning, drug discovery, and clinical medicine. The biochemical experimentation (in vitro) requires a long time and high cost to be confirmed because it is difficult to estimate. Therefore, a feasible solution is to predict DPIs efficiently with computers. We propose a link prediction method based on drug-protein interaction (DPI) local structural similarity (DLS) for predicting the DPIs. The DLS method combines link prediction and binary network structure to predict DPIs. The ten-fold cross-validation method was applied in the experiment. After comparing the predictive capability of DLS with the improved similarity-based network prediction method, the results of DLS on the test set are significantly better. Moreover, several candidate proteins were predicted for three approved drugs, namely captopril, desferrioxamine and losartan, and these predictions are further validated by the literature. In addition, the combination of the Common Neighborhood (CN) method and the DLS method provides a new idea for the integrated application of the link prediction method.

关键词： drug-protein interactions network analysis link prediction DPI local structural similarity network local structure

来源：评论

学校读者我要写书评

暂无评论

Multiview framework using a 3D residual network for pulmonary micronodule malignancy risk classification

引用

BIO-MEDICAL MATERIALS AND ENGINEERING 2020年第4期31卷 253-267页

作者： Yang, Yujie Zhang, Qianqian Henan Normal Univ Inst Comp & Informat Engn Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang Henan Peoples R China

BACKGROUND: Pulmonary micronodules account for 80% of all lung nodules. Generally, pulmonary micronodules in the early stages can be detected on thoracic computed tomography (CT) scans. Early diagnosis is crucial for improving the patient's survival rate. OBJECTIVE: This paper aims to estimate the malignancy risk of pulmonary micronodules and potentially improve the survival rate. METHODS: We extract 3D features of the CT images to obtain richer characteristics. Because superior performance can be achieved by having deep layers, we apply a 3D residual network (3D-ResNet) to classify the pulmonary micronodule. We construct a framework by using three parallel ResNets whose inputs are CT images in different regions of interest, i.e., the multiview of the image. To further evaluate the applicability of the framework, we make a five-category classification and achieve good performance. RESULTS: By fusing different characteristics from three views, we achieve the area under the receiver operating characteristic curve (AUC) of 0.9681. Based on the results of the experiments, our 3D-ResNet has a better performance than 3D-VGG and 3D-Inception in terms of precision (the increase rates are 13.7% and 7.4%), AUC (the increase rates are 15.8% and 5.3%), and accuracy (the increase rates are 14.3% and 4.5%). Meanwhile, the recall performance is close to that of the 3D-Inception network. CONCLUSION: Overall, the framework we propose has applicability and feasibility in pulmonary micronodule classification.

关键词： Pulmonary micronodule computed tomography (CT) multiview three-dimensional residual network (3D-ResNet)

来源：评论

学校读者我要写书评

暂无评论

Predicting DNA binding protein-drug interactions based on network similarity

引用

BMC BIOINFORMATICS 2020年第1期21卷 1-13页

作者： Wang, Wei Lv, Hehe Zhao, Yuan Henan Normal Univ Dept Comp Sci & Technol Coll Comp & Informat Engn Xinxiang 453007 Henan Peoples R China Big Data Engn Lab Teaching Resources & Assessment Xinxiang Henan Peoples R China

Background The study of DNA binding protein (DBP)-drug interactions can open a breakthrough for the treatment of genetic diseases and cancers. Currently, network-based methods are widely used for protein-drug interaction prediction, and many hidden relationships can be found through network analysis. We proposed a DCA (drug-cluster association) model for predicting DBP-drug interactions. The clusters are some similarities in the drug-binding site trimmers with their physicochemical properties. First, DBPs-drug binding sites are extracted from scPDB database. Second, each binding site is represented as a trimer which is obtained by sliding the window in the binding sites. Third, the trimers are clustered based on the physicochemical properties. Fourth, we build the network by generating the interaction matrix for representing the DCA network. Fifth, three link prediction methods are detected in the network. Finally, the common neighbor (CN) method is selected to predict drug-cluster associations in the DBP-drug network model. Result This network shows that drugs tend to bind to positively charged sites and the binding process is more likely to occur inside the DBPs. The results of the link prediction indicate that the CN method has better prediction performance than the PA and JA methods. The DBP-drug network prediction model is generated by using the CN method which predicted more accurately drug-trimer interactions and DBP-drug interactions. Such as, we found that Erythromycin (ERY) can establish an interaction relationship with HTH-type transcriptional repressor, which is fitted well with silico DBP-drug prediction. Conclusion The drug and protein bindings are local events. The binding of the drug-DBPs binding site represents this local binding event, which helps to understand the mechanism of DBP-drug interactions.

关键词： DNA binding protein Amino acid trimer Cluster Network

来源：评论

学校读者我要写书评

暂无评论

Cooperative edge offloading strategy for sensory data with delay and energy constraints

引用

WIRELESS NETWORKS 2023年第8期29卷 3469-3478页

作者： Yuan, Peiyan Shao, Saike Zhang, Junna Zhao, Xiaoyan Henan Normal Univ Sch Comp & Informat Engn Xinxiang Henan Peoples R China Big Data Engn Lab Teaching Resources Xinxiang Henan Peoples R China

In this study, we investigate the edge offloading of sensory data in the internet of things. Multiple edge servers cooperatively offloading all or part of the sensory data initially sent to a cloud center, which improves users' experience. In the process of cooperative offloading, the transmission of sensory data and information exchange among edge servers will consume system resources, resulting in a cost of cooperation. How to maximize the offloading ratio of sensing data while maintaining a low collaboration cost is a challenge. This study first formulates a joint optimization problem of the sensing data offloading ratio and cooperative ratio satisfying the constraints of network delay and system energy consumption. Subsequently, a distributed alternating direction method of multipliers (ADMM) via constraint projection and variable splitting is proposed to solve the problem. The numerical results show that the proposed method greatly improves network delay and energy consumption compared to the fairness cooperation algorithm.

关键词： Collaborative edge computing data offloading Network delay System energy consumption Distributed ADMM

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：