检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Wang, Zhen Deng, Zhong-Hua Wang, Jie Lin, Wei-Xun Fu, Xiao-Wei Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Imaging Processing and Intelligent Control Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Guangdong Shenzhen518055 China Lambda Company Jiangsu Changzhou213100 China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China

To improve the performance of the NOx sensor, a combined model based on the electrochemical model and the diffusion model is developed for the NOx pumping cell of the NOx sensor. Considering that a small amount of oxygen enters the third chamber and part of NO is decomposed in the second chamber, the electrochemical model simultaneously considers the reactions of NO and oxygen at cathode, and the diffusion model additionally considers the diffusion of oxygen and the decomposition of NO. To validate the model at different gas concentrations, the sensor is mounted on the designed test rig. Then, the simulation results are compared with experimental data from the test rig and good agreement is obtained. In addition, three key parameters of the model of the NOx pumping cell are analyzed. The values and changing trends of these three parameters are given in the paper. © 2022, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Image Dust Storm Synthetic Method Based on Optical Model 3rd

Image Dust Storm Synthetic Method Based on Optical Model

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Huang, Jiayan Li, Zuoyong Wang, Chuansheng College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China

ISBN: (纸本)9783030624620

To address the problem that the dusty image dataset is small and difficult to collect, this paper presents a synthetic method for generating dusty image based on a classical optical model. The proposed method first learns the physical process of generating dusty image according to the classical optical model. Then, the transmission map is estimated and combined with the presupposed dust storm color map as inputs for obtaining a synthetic dusty image. Finally, considering the impact of image scene depth on the synthesis of dusty image, the proposed method selects an appropriate value of input parameter to obtain final synthetic dusty image. Experimental results on an image dataset captured in clear weather show that the synthetic dusty images obtained by the proposed method can be used as a good substitute for real dusty images. © 2020, Springer Nature Switzerland AG.

关键词： Storms

来源：评论

学校读者我要写书评

暂无评论

An Anomalous Traffic Detection Approach for the Private Network Based on Self-learning Model 1

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Han, Weijie Xue, Jingfeng Zhang, Fuquan Zhang, Yingfeng School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Space Information Space Engineering University Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China Equipment Development Department Beijing100071 China

ISBN: (数字)9783030622237

ISBN: (纸本)9783030622220

Although being isolated from the external network, the private network is still faced with some security threats, such as violations communications, malware attacks, and illegal operations. It is an attractive approach to recognize these security threats by discovering the underlying anomalous traffic. By studying the anomalous traffic detection technologies, an anomalous traffic detection approach is developed by capturing and analyzing the network packets, detecting the anomaly traffic that occurs in the network, and then detects anomalous behaviors of the network timely. In order to enhance its effectiveness and efficiency, a self-learning model is proposed and deployed in the detection approach. Finally, we conduct necessary evaluations about the proposed approach. The test results show that the approach can reach a good effect for detecting the unknown anomalous traffic. © 2020, Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Occlusion Scene Classification via Cascade Supervised Contrastive Learning

TechRxiv

引用

TechRxiv 2022年

作者： Xu, Jianming Li, Yunfei He, Li Li, Jun The Guangdong Provincial Key Laboratory of Urbanization and Geosimulation Center of Integrated Geographic Information Analysis School of Geography and Planning Sun Yatsen University Guangzhou510275 China The School of Computer Science China University of Geosciences Wuhan430078 China The Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan430078 China The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China

Recent occlusion scene classification focuses on extracting occlusion-invariant features by considering class separability, unsupervised learning, and generalization ability, separately. Considering them together is profitable to address real-world occlusion problem. In this work, we propose cascade supervised contrastive learning to accommodate those considerations simultaneously. First, the pretext task uses rectangles to occlude the original images. Second, we use the siamese residual network to extract the features of original images, and pretext task augmented images. Third, compute the cascade supervised contrastive loss of the intermediate layers and final layer of the network. By optimizing the cascade supervised contrastive loss, the network can learn pretext-task invariant features. Besides, the pretext task-invariant features can adapt to the downstream occlusion-invariant feature extraction task due to the outstanding generalization ability of contrastive learning. Finally, a multilayer perceptron is used to perform scene classification on the extracted features. The proposed method is validated on two simulated datasets and tends to achieve performance improvement compared with typical unsupervised occlusion scene classification methods. The first application of contrastive learning for remote sensing image occlusion scene classification is the innovative contribution of this paper. This method can achieve accurate remote sensing scene classification with any degree and type of occlusion. © 2022, CC BY-NC-SA.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Restoration-enhanced reversible information steganography network for CT images in the Internet of Medical Things

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Chen, Kai Chen, Yang Coatrieux, Gouenou Wu, Jiasong Coatrieux, Jean-Louis School of Cyber Science and Engineering Southeast University Nanjing210096 China Southeast University Nanjing210096 China IMT Atlantique Inserm LaTIM UMR1101 Brest29000 France Laboratoire Traitement du Signal et de L'Image Université de Rennes 1 RennesF-35000 France Centre de Recherche en Information Biomédicale Sino-francais Rennes35042 France National Institute for Health and Medical Research RennesF-35000 France Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Ministry of Education Nanjing210096 China Ministry of Education Nanjing210096 China

Smart health and emotional care powered by the Internet of Medical Things (IoMT) are revolutionizing the healthcare industry by adopting several technologies related to multimodal physiological data collection, communication, intelligent automation, and efficient manufacturing. The security of medical images containing private patient information distributed in IoMT is of paramount importance in social communication, and guaranteeing their reliability has attracted widespread attention. Some existing medical image steganography methods fail to guarantee the original image's integrity, authenticity, and lossless restoration. To solve this problem, a restoration-enhanced reversible adaptive information steganography network, MediSR-Net, is proposed. Specifically, MediSR-Net consists of an analysis module and an encoding module. The image degradation-restoration strategy is exploited by the analysis module to improve the effectiveness of information embedding and perceptual field to reduce the error of pixel prediction. An information distillation and attention machine-based approach are adopted to achieve degradation-restoration of CT medical images at any scale and focus more on the degradation-restoration effect with small magnification factors. The encoding module is responsible for the embedding and extraction of privacy information. Ten state-of-the-art are compared with the MediSR-Net method concerning steganographic effect, embedding rate, distortion analysis, and prediction error. The qualitative and quantitative results demonstrate the effectiveness and superiority of MediSR-Net. © 1963-2012 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Time Series Anomaly Detection under Data Contamination

Unsupervised Time Series Anomaly Detection under Data Contam...

引用

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Xiaohui Lin Zuoyong Li Xunhua Huang Xinwei Chen Haoyi Fan College of Computer and Data Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China School of Computer Science and Technology Harbin University of Science and Technology Harbin China Fujian Engineering and Research Center of New Chinese Lacquer Materials Minjiang University Fuzhou China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Unsupervised learning utilizes unlabeled data to alleviate the reliance on large amounts of labeled data, and it has made great progress in time series anomaly detection. However, there are still some thorny issues unsolved, especially the incapability to maintain the robustness of the model when the time series dataset is contaminated. In this work, we propose an unsupervised time series anomaly detection method on data contamination, named distribution alignment autoencoder (DAAE), in which a temporal sliding reward function combines the adversarial distribution alignment to mine the contaminated data. Specifically, the dimensionality reduction and reconstruction of the time series are implemented by an autoencoder. Next, using two discriminators, the latent features obtained by dimensionality reduction are mapped to the Gaussian distribution, and the high-confidence normal time series are generated by sampling noise from the Gaussian distribution. Then, we compute the mean square error between high-confidence normal samples and the training data. Finally, we feed the error values to the temporal sliding reward function to mine the contaminated training samples. Experimental results compared with baselines on public datasets demonstrate the effectiveness of DAAE.

关键词： Training Dimensionality reduction Time series analysis Training data Mean square error methods Gaussian distribution Robustness

来源：评论

学校读者我要写书评

暂无评论

Asymmetry Total Variation and Framelet Regularized Nonconvex Low-Rank Tensor Completion

SSRN

引用

SSRN 2022年

作者： Chen, Yongyong Zhao, Xiaojia Xu, Tingting Zeng, Haijin Xu, Yanhui Chen, Junxing The School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen518055 China Image Processing and Interpretation Imec Research Group Ghent University Belgium Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China The College of Medicine and Biological Information Engineering Northeastern University Shenyang110004 China

The low-rank tensor representation has shown enormous potential and advantages in diverse applications. However, (1) due to the inherent limitations of the low-rank tensor model, the tensor nuclear norm is utilized yet as a biased estimate of the tensor rank, which limits the image recovery performance. (2) most current low-rank approximation-based methods focus on the preservation of global information, while ignoring the local details preservation such as the spatial piece-wise smoothness and sharp edges. To overcome he above obstacles, we propose a novel asymmetry three-dimensional total variation and framelet regularized nonconvex low-rank tensor completion (ATV-FNTC) model, which integrates the nonconvex penalty function and asymmetric three-dimensional total variation into one unified model. Specifically, ATV-FNTC introduces one nonconvex penalty function as a tighter regularizer to approximate the tensor rank. Different from existing methods, the asymmetric three-dimensional total variation regularization is developed to achieve more accurate recovery of detailed information and flexibly control the smoothing strength of different dimensions of tensor data. Furthermore, we design an iterative algorithm to solve the nonconvex ATV-FNTC model by the alternating direction methods of multipliers. Experimental results reveal the superiority of the proposed method compared with several state-of-the-art methods when handling different completion tasks. © 2022, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Improved Security for Android System based on Multi-Chaotic Maps using a Novel Image Encryption Algorithm

引用

International Journal of Performability Engineering 2019年第6期15卷 1692-1701页

作者： Jiao, Ge Li, Lang Zou, Yi College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

Aimed at the unsatisfactory effect of security in mobile cloud computing, we propose a novel image encryption algorithm by using the Improved Fruit Fly Optimization Algorithm-Artificial Bee Colony (hereafter referred to as IFOA-ABC). First, the feature of task scheduling function in mobile cloud computing is described to set up the task scheduling function;second, the population of fruit fly optimization algorithm is initialized by using orthogonal array and quantitative techniques, and the boundary of fruit fly optimization algorithm is processed, the step size in search is adjusted dynamically, and the artificial bee colony algorithm is used to help fruit fly optimization algorithm develop the global optimal solution;in the simulation experiment, the IFOA-ABC algorithm has obvious advantages over other intelligent algorithms in the comparison of four indicators of mobile cloud task scheduling, which means that the proposed algorithm can effectively improve the privacy and efficiency of cloud computing scheduling. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improved hybrid query tree anti-collision algorithm 8th

Improved hybrid query tree anti-collision algorithm

引用

8th International Conference on computer Engineering and Networks, CENet 2018

作者： Deng, Hongwei Li, Lang Liang, Xiaoman School of Computer Science and Technology Hengyang Normal University HengyangHunan421002 China School of Information Science and Engineering Central South University ChangshaHunan410083 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9783030146795

An improved algorithm based on the hybrid query tree (HQT) algorithm is proposed in this work. Tags are categorized according to the combined information of the highest bit of collision and second-highest bit of collision. Then, these tags are used to decide the postponement of several delayed-response time slots, to diminish the collision probability. The performance analysis results show that this algorithm is superior to the query tree (QT) and HQT algorithms. It reduces the query time and system communication traffic and improves the tag identification efficiency. © Springer Nature Switzerland AG 2020.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Syndrome Classification Based on Multi-Graph Attention Network

Syndrome Classification Based on Multi-Graph Attention Netwo...

引用

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Jishun Ma Weikai Lu Changen Zhou Shenghua Teng Zuoyong Li College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China School of Electronic Electrical Engineering and Physics Fujian University of Technology Fuzhou China Research Base of Traditional Chinese Medicine Syndrome Fujian University of Traditional Chinese Medicine Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China

Syndrome classification is an important step in Traditional Chinese Medicine (TCM) for diagnosis and treatment. In this paper, we propose a multi-graph attention network (MGAT) based method to simulate TCM doctors to infer the syndromes. Specifically, the complex relationships between symptoms and state elements are aggregated using graph attention networks (GAT) and syndromes are classified by a multilayer perceptron (MLP). To verify the effectiveness of the model, extensive experiments are conducted on the Treatise on Febrile Diseases dataset. The experimental results show that the proposed method outperforms several typical methods in terms of accuracy, precision, recall, and F1-score. The MGAT model has high accuracy in syndrome classification and has practical application value.

关键词： Computational modeling Education Medical services Multilayer perceptrons Feature extraction computer aided diagnosis information technology

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：