检索结果-内蒙古大学图书馆

Improved DDoS Detection Utilizing Deep Neural Networks and Feedforward Neural Networks as autoencoder

FUTURE INTERNET 2022年第8期14卷 240-240页

作者： Yaser, Ahmed Latif Mousa, Hamdy M. Hussein, Mahmoud Menoufia Univ Fac Comp & Informat Comp Sci Dept Shibin Al Kawm 32511 Egypt Univ Baghdad Coll Adm & Econ Dept Informat Syst POB 10071 Baghdad Iraq

Software-defined networking (SDN) is an innovative network paradigm, offering substantial control of network operation through a network's architecture. SDN is an ideal platform for implementing projects involving distributed applications, security solutions, and decentralized network administration in a multitenant data center environment due to its programmability. As its usage rapidly expands, network security threats are becoming more frequent, leading SDN security to be of significant concern. Machine-learning (ML) techniques for intrusion detection of DDoS attacks in SDN networks utilize standard datasets and fail to cover all classification aspects, resulting in under-coverage of attack diversity. This paper proposes a hybrid technique to recognize denial-of-service (DDoS) attacks that combine deep learning and feedforward neural networks as autoencoders. Two datasets were analyzed for the training and testing model, first statically and then iteratively. The auto-encoding model is constructed by stacking the input layer and hidden layer of self-encoding models' layer by layer, with each self-encoding model using a hidden layer. To evaluate our model, we use a three-part data split (train, test, and validate) rather than the common two-part split (train and test). The resulting proposed model achieved a higher accuracy for the static dataset, where for ISCX-IDS-2012 dataset, accuracy reached a high of 99.35% in training, 99.3% in validation and 99.99% in precision, recall, and F1-score. for the UNSW2018 dataset, the accuracy reached a high of 99.95% in training, 0.99.94% in validation, and 99.99% in precision, recall, and F1-score. In addition, the model achieved great results with a dynamic dataset (using an emulator), reaching a high of 97.68% in accuracy.

关键词： autoencoder denial-of-service (DDoS) deep neural network DDoS detection software-defined network (SDN)

来源：评论

学校读者我要写书评

暂无评论

Increasing Frequency of Anomalous Precipitation Events in Japan Detected by a Deep Learning autoencoder

引用

EARTHS FUTURE 2022年第4期10卷

作者： Murakmai, H. Delworth, T. L. Cooke, W. F. Kapnick, S. B. Hsu, P. -C. Univ Corp Atmospher Res Cooperat Programs Adv Earth Syst Sci Boulder CO 80307 USA NOAA Geophys Fluid Dynam Lab Princeton NJ USA Princeton Univ Atmospher & Ocean Sci Program Princeton NJ 08544 USA JP Morgan Chase & Co New York NY USA Nanjing Univ Informat Sci & Technol Key Lab Meteorol Disaster Minist Educ Nanjing Peoples R China

The frequency of large-scale anomalous precipitation events associated with heavy precipitation has been increasing in Japan. However, it is unclear if the increase is due to anthropogenic warming or internal variability. Also, it is challenging to develop an objective methodology to identify anomalous events because of the large variety of anomalous precipitation cases. In this study, we applied a deep learning technique to objectively detect anomalous precipitation events in Japan for both observations and simulations using high-resolution climate models. The results show that the observed increases in anomalous heavy precipitation events in Western Japan during 1977-2015 were not made only by internal variability but the increases in anthropogenic forcing played an important role. Such events will continue to increase in frequency this century. The increases are attributable to the increasing frequency of tropical cyclones and enhanced frontal rainbands near Japan. These results highlight the mitigation challenge posed by the increasing occurrence of unprecedented precipitation events in the future.

关键词： deep learning autoencoder extreme event tropical cyclone Japan Baiu

来源：评论

学校读者我要写书评

暂无评论

Generating Spectrum Images from Different Types - Visible, Thermal, and Infrared Based on autoencoder Architecture (GVTI-AE)

引用

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS 2022年第1期22卷 p1-13页

作者： Jameel, Samer Kais Majidpour, Jafar Univ Raparin Dept Comp Sci Rania Iraq

Recently, numerous challenging problems have existed for transforming different image types (thermal infrared (TIR), visible spectrum, and near-infrared (NIR)). Other types of cameras may lack the ability and features of certain types of frequently-used cameras that produce different types of images. Based on camera features, different applications might emerge from observing a scenario under specific conditions (darkness, fog, night, day, and artificial light). We need to jump from one field to another to understand the scenario better. This paper proposes a fully automatic model (GVTI-AE) to manipulate the transformation into different types of vibrant, realistic images using the autoencoder method, which requires neither pre-nor post-processing or any user input. The experiments carried out using the GVTI-AE model showed that the perceptually realistic results produced in the widely available datasets (Tecnocampus Hand Image Database, Carl dataset, and IRIS Thermal/Visible Face Database).

关键词： Transforming images autoencoder unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

ABFL: An autoencoder based practical approach for software fault localization

引用

INFORMATION SCIENCES 2020年 510卷 108-121页

作者： Peng, Zhendong Xiao, Xi Hu, Guangwu Sangaiah, Arun Kumar Atiquzzaman, Mohammed Xia, Shutao Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Shenzhen Inst Informat Technol Sch Comp Sci Shenzhen Peoples R China VIT Sch Comp Sci & Engn Vellore 632014 Tamil Nadu India Univ Oklahoma Sch Comp Sci Norman OK 73019 USA

Fault localization is essential to software debugging. Despite existing techniques, such as mutation analysis, development history and bug reports, have made great contributions to fault localization, the challenge of infeasibility still exits in practice due to expense of mutation analysis, lacking of development history and bug reports. To improve accuracy and feasibility in fault code locating, in this paper, we propose ABFL, an autoencoder Based practical approach for Fault Localization. ABFL first introduces an autoencoder to extract 32 features from software static source code. Then it employs Spectrum Based Fault Localization (SBFL) techniques to calculate 14 types of scores, which are taken as another group of features in software running time. Finally, relying on the constructed ranking model, ABFL integrates two groups of features together and precisely locates faulty statements in code. The executed extensive experiments on the Defects4J repository show that our approach is superior to the state-of-the-art SBFL techniques, ranking the faulty statement at the 1st, 3rd, and 5th positions with 49, 94, and 123 faults, respectively. (C) 2019 Published by Elsevier Inc.

关键词： Fault localization Debugging SBFL autoencoder

来源：评论

学校读者我要写书评

暂无评论

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2020年第6期E103D卷 1419-1422页

作者： Shen, Fengli Lu, Zhe-Ming Zhejiang Univ Sch Aeronaut & Astronaut Hangzhou 310027 Peoples R China

This Letter proposes a autoencoder model supervised by semantic similarity for zero-shot learning. With the help of semantic similarity vectors of seen and unseen classes and the classification branch, our experimental results on two datasets are 7.3% and 4% better than the state-of-the-art on conventional zero-shot learning in terms of the averaged top-1 accuracy.

关键词： zero-shot learning autoencoder image classification

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Stacked Denoising autoencoder for Handling Missing Data in Healthcare Big Data

引用

IEEE ACCESS 2020年 8卷 104933-104943页

作者： Kim, Joo-Chang Chung, Kyungyong Kyonggi Univ Dept Comp Sci Suwon 16227 South Korea Kyonggi Univ Div Comp Sci & Engn Suwon 16227 South Korea

Supply and demand increase in response to healthcare trends. Moreover, personal health records (PHRs) are being managed by individuals. Such records are collected using different avenues and vary considerably in terms of their type and scope depending on the particular circumstances. As a result, some data may be missing, which has a negative effect on the data analysis, and such data should, therefore, be replaced with appropriate values. In this study, a method for estimating missing data using a multi-modal autoencoder applied to the field of healthcare big data is proposed. The proposed method uses a stacked denoising autoencoder to estimate the missing data that occur during the data collection and processing stages. autoencoders are neural networks that output value of x(boolean AND) similar to an input value of x. In the present study, data from the Korean National Health Nutrition Examination Survey (KNHNES), conducted by the Korea Centers for Disease Control and Prevention (KCDC), are used. As representative healthcare data from South Korea, they contain a large number of parameters identical to those used in the PHRs. Based on this, models can be generated to estimate missing data occurring in PHRs. Furthermore, PHRs involve a multi-modality that allows the data to be collected from multiple sources for a single object. Therefore, the stacked denoising autoencoder applied is configured under a multi-modal setting. Through pre-processing, a set of data without missing value in KNHNES is designed. In the data set based learning, a label is set as original data, and an autoencoder input is set as noised input that additionally has as many random zero numbers as noise factor. In this way, the autoencoder learns in the way of making the zero-based noise value similar to the original label value. When the amount of missing data in a dataset reaches approximately 25%, the accuracy of the proposed method using a multi-modal stacked denoising autoencoder is 0.9217,

关键词： Medical services Big Data Noise reduction Machine learning Data models Computational modeling Estimation autoencoder data pre-processing data estimation data imputation health big data multi-modal missing data machine learning

来源：评论

学校读者我要写书评

暂无评论

Breast Histopathological Image Classification Method Based on autoencoder and Siamese Framework

引用

INFORMATION 2022年第3期13卷 107-107页

作者： Liu, Min He, Yu Wu, Minghu Zeng, Chunyan Hubei Univ Technol Sch Elect & Elect Engn Wuhan 430068 Peoples R China

The automated classification of breast cancer histopathological images is one of the important tasks in computer-aided diagnosis systems (CADs). Due to the characteristics of small inter-class and large intra-class variances in breast cancer histopathological images, extracting features for breast cancer classification is difficult. To address this problem, an improved autoencoder (AE) network using a Siamese framework that can learn the effective features from histopathological images for CAD breast cancer classification tasks was designed. First, the inputted image is processed at multiple scales using a Gaussian pyramid to obtain multi-scale features. Second, in the feature extraction stage, a Siamese framework is used to constrain the pre-trained AE so that the extracted features have smaller intra-class variance and larger inter-class variance. Experimental results show that the proposed method classification accuracy was as high as 97.8% on the BreakHis dataset. Compared with commonly used algorithms in breast cancer histopathological classification, this method has superior, faster performance.

关键词： histopathological image classification autoencoder Siamese network multi-scale input

来源：评论

学校读者我要写书评

暂无评论

Non-destructive online seal integrity inspection utilizing autoencoder-based electrical capacitance tomography for product packaging assurance

引用

FOOD PACKAGING AND SHELF LIFE 2022年 33卷

作者： Pan, Jieming Yang, Zaifeng Yap, Stephanie Hui Kit Zhang, Xiangyu Xu, Zefeng Li, Yida Luo, Yuxuan Zamburg, Evgeny Liu, En-Xiao Tham, Chen-Khong Thean, Aaron Voon-Yew Natl Univ Singapore Dept Elect & Comp Engn 4 Engn Dr 3 Singapore 117583 Singapore ASTAR Inst High Performance Comp IHPC Singapore Singapore

Good quality packaging prevents contamination, secures preservation, and increases the ease of transportation in food and medical industries. One particular weakness of the package lies in the seal region where contents can be unintentionally incorporated, which disrupts the sealing process and compromises the structure and durability of the seal. To validate the seal quality effectively at high speed, a non-destructive high-resolution inspection approach combining enhanced sensors and reconstruction techniques is required. As the seal is flat and defects are minuscule, sensors have to be placed along the contour of the seal to achieve sufficient sensitivity. However, such conformal sensor placement poses new challenges to the ill-posed traditional tomography reconstruction. To overcome the limitation of sensing angle projections, imbalance in pixel representation and physical mea-surements, and asymmetric geometry of the sensed region, we propose a high-speed supervised autoencoder reconstruction approach. In this paper, our approach achieves high reconstruction image quality of irregular seal regions despite conformal sensor placement. While overcoming the limitations faced in traditional tomography, our model can be seamlessly integrated into the production line for real-time defect detection without affecting production speed and effectively minimizing manufacturing wastage and downtime.

关键词： Electrical capacitance tomography autoencoder Neural network Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Optimization of real-time wireless sensor based big data with deep autoencoder network: a tourism sector application with distributed computing

引用

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES 2020年第6期28卷 3137-3153页

作者： Aksoy, Bekir Kose, Utku Isparta Univ Appl Sci Fac Engn Dept Mechatron Engn Isparta Turkey Suleyman Demirel Univ Fac Engn Dept Comp Engn Isparta Turkey

Internet usage has increased rapidly with the development of information communication technologies. The increase in internet usage led to the growth of data volumes on the internet and the emergence of the big data concept. Therefore, it has become even more important to analyze the data and make it meaningful. In this study, 690 million queries and approximately 5.9 quadrillion data collected daily from different servers were recorded on the Redis servers by using real-time big data analysis method and load balance structure for a company operating in the tourism sector. Here, wireless networks were used as a triggering factor to gather data from visitors of the hotels and the analysis was supported with an optimization approach through the deep autoencoder network. According to the data density gathered from the structure developed with distributed computing and the API software in C# language, server group numbers were increased to list the most affordable hotel in the desired times. Thanks to the developed architecture and software, response times of the servers were significantly reduced. In detail, it was seen that the HAProxy responded 11 times faster than NetScaler as the new architecture responded 1160 times faster than the old one. Also, the HashSet system in the newly developed architecture responded 18 times faster than the List system and as general, the new architecture was found to be 9 times faster than the old architecture.

关键词： Big data Redis wireless sensors autoencoder distributed computing tourism

来源：评论

学校读者我要写书评

暂无评论

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

引用

SN APPLIED SCIENCES 2020年第2期2卷 152页

作者： Ali, Hazrat Ullah, Ahsan Iqbal, Talha Khattak, Shahid COMSATS Univ Islamabad Dept Elect & Comp Engn Abbottabad Campus Abbottabad Pakistan Natl Univ Ireland Lambe Inst Translat Res Galway Ireland

Automatic recognition of Urdu handwritten digits and characters, is a challenging task. It has applications in postal address reading, bank's cheque processing, and digitization and preservation of handwritten manuscripts from old ages. While there exists a significant work for automatic recognition of handwritten English characters and other major languages of the world, the work done for Urdu language is extremely insufficient. This paper has two goals. Firstly, we introduce a pioneer dataset for handwritten digits and characters of Urdu, containing samples from more than 900 individuals. Secondly, we report results for automatic recognition of handwritten digits and characters as achieved by using deep auto-encoder network and convolutional neural network. More specifically, we use a two-layer and a three-layer deep autoencoder network and convolutional neural network and evaluate the two frameworks in terms of recognition accuracy. The proposed framework of deep autoencoder can successfully recognize digits and characters with an accuracy of 97% for digits only, 81% for characters only and 82% for both digits and characters simultaneously. In comparison, the framework of convolutional neural network has accuracy of 96.7% for digits only, 86.5% for characters only and 82.7% for both digits and characters simultaneously. These frameworks can serve as baselines for future research on Urdu handwritten text.

关键词： autoencoder Convolutional neural network Urdu Text recognition

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：