检索结果-内蒙古大学图书馆

2nd international conference on Security with Intelligent computing and Big-data Services (SICBS)

作者： Yang, Changsong Tao, Xiaoling Xidian Univ State Key Lab Integrated Serv Networks ISN Xian 710071 Shaanxi Peoples R China Guilin Univ Elect Technol Guangxi Coll & Univ Key Lab Cloud Comp & Complex Guilin 541004 Peoples R China

ISBN: (纸本)9783030169466;9783030169459

Cloud storage service, one of the most important services in the cloud computing, can offer high-quality storage service for tenants. By employing the cloud storage service, the resource-constraint data owners can outsource their data to the remote cloud server to reduce the heavy storage burden. Due to the attractive advantages, there are an increasing number of data owners prefer to embrace the cloud storage service. However, the data owners will lose the direct control over their outsourced data, and they can not directly execute operations over their outsourced data, such as data deletion operation. That will make outsourced data deletion become a crucial security problem: the selfish cloud server may not honestly perform the data deletion operation for economic interests, and then returns error results to mislead the data owners. Although a series of solutions have been proposed to solve this problem, most of them can be described as "one-bit-return" protocol: the storage server removes the data and then returns a one-bit deletion reply, and the data owners have to trust the deletion reply because they can not verify it conveniently. In this paper, we put forward a new publicly verifiable data deletion scheme with efficient tracking for cloud storage. In our novel scheme, the remote cloud server executes the data deletion operation and returns a deletion proof. If the remote cloud server maliciously reserves the data backups, the data owner can easily detect the malicious data reservation by verifying the returned deletion proof. Besides, we utilize the primitive of Merkle Hash Tree to solve the problem of public verifiability in data deletion. Furthermore, our scheme can realize efficient data leakage source tracking when the data are leaked, which can prevent the data owner and the cloud server from exposing the data designedly to slander each other. Finally, we prove that our novel scheme can satisfy the desired security properties.

关键词： Cloud storage data deletion Public verification Efficient tracking Merkle Hash Tree

来源：评论

学校读者我要写书评

暂无评论

Multi-label classification of fundus images based on graph convolutional network

引用

BMC MEDICAL INFORMATICS And DECISION MAKING 2021年第SUPPL 2期21卷 82-82页

作者： Cheng, Yinlin Ma, Mengnan Li, Xingyu Zhou, Yi Sun Yat Sen Univ Sch Biomed Engn 132 Waihuan East Rd Guangzhou 510006 Peoples R China Sun Yat Sen Univ Zhongshan Sch Med Dept Med Informat 74 Zhongshan 2nd Rd Guangzhou 510080 Peoples R China Sun Yat Sen Univ Zhongshan Sch Med 74 Zhongshan 2nd Rd Guangzhou 510080 Peoples R China Sun Yat Sen Univ Minist Educ Key Lab Trop Dis Control 74 Zhongshan 2nd Rd Guangzhou 510080 Peoples R China

Background: Diabetic Retinopathy (DR) is the most common and serious microvascular complication in the diabetic population. Using computer-aided diagnosis from the fundus images has become a method of detecting retinal diseases, but the detection of multiple lesions is still a difficult point in current research. Methods: This study proposed a multi-label classification method based on the graph convolutional network (GCN), so as to detect 8 types of fundus lesions in color fundus images. We collected 7459 fundus images (1887 left eyes, 1966 right eyes) from 2282 patients (1283 women, 999 men), and labeled 8 types of lesions, laser scars, drusen, cup disc ratio (C/D > 0.6), hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates. We constructed a specialized corpus of the related fundus lesions. A multi-label classification algorithm for fundus images was proposed based on the corpus, and the collected data were trained. Results: The average overall F1 Score (OF1) and the average per-class F1 Score (CF1) of the model were 0.808 and 0.792 respectively. The area under the ROC curve (AUC) of our proposed model reached 0.986, 0.954, 0.946, 0.957, 0.952, 0.889, 0.937 and 0.926 for detecting laser scars, drusen, cup disc ratio, hemorrhages, retinal arteriosclerosis, microaneurysms, hard exudates and soft exudates, respectively. Conclusions: Our results demonstrated that our proposed model can detect a variety of lesions in the color images of the fundus, which lays a foundation for assisting doctors in diagnosis and makes it possible to carry out rapid and efficient large-scale screening of fundus lesions.

关键词： Diabetic retinopathy Fundus images GCN Multi-label

来源：评论

学校读者我要写书评

暂无评论

Modified Quick Fuzzy Hypersphere Neural Network for Pattern Classification Using Supervised Clustering 2nd

Modified Quick Fuzzy Hypersphere Neural Network for Pattern ...

引用

2nd international conference on soft computing and Signal Processing, ICSCSP 2019

作者： Mane, D.T. Kshirsagar, J.P. Kulkarni, U.V. Department of Computer Science & Engineering S. G. G. S. I. E. & T. NandedMaharashtra431606 India Department of Computer Engineering Rajarshi Shahu College of Engineering PuneMaharashtra411033 India

ISBN: (纸本)9789811524745

Defining methods which map the features present in the input to a binomial class output is the core objective of pattern classification. The Modified Quick Fuzzy Hypersphere Neural Network (MQFHSNN) algorithm proposed is an extension of the existing Class-Specific Fuzzy Hypersphere Neural Network (CSFHSNN). Its membership function has been modified such that it outperforms the existing algorithms in the field of pattern classification. Fuzzy set hyperspheres are employed by MQFHSNN for pattern clustering and classes are represented by a combination of fuzzy set hypersphere. By using class labels for forming the clusters, the presented model gives 100% accuracy on the training data. The core contributors to facilitate learning in MQFHSNN are: creation of hyperspheres based on measurements provided by interclass and intraclass distance techniques as well as decision of patterns of individual classes by the fuzzy membership function. The proposed model is put into test on four standard datasets and the results obtained are more superior to the existing models. This leads us to the conclusion that MQFHSNN is being used for improvising model accuracy in pattern classification. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy-Neuro-Based Clinical Decision Support System For Disease Diagnosis Using Symptom Severity 1

引用

2nd international conference on soft computing and Signal Processing, ICSCSP 2019

作者： Tandra, Sulochana Gupta, Deepa Amudha, J. Sharma, Kshitij Department of Computer Science and Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Paralaxiom Technologies Private Limited Bengaluru India

ISBN: (数字)9789811524752

ISBN: (纸本)9789811524745

Faster and accurate disease diagnosis is the need of the day. Various diagnostic tools are available to assist medical practitioners in the form of clinical decision support system (CDSS) and many more. This paper proposes to develop a CDSS that can assist medical practitioners with diagnostic decisions in general internal medicine for common diseases like malaria, typhoid, dengue which when ignored can cause epidemics. The proposed system aims at multi-disease diagnosis. Symptoms along with their severity are the input to the system. Most probable disease along with medication is the output of the system. The proposed system is modeled on neuro-fuzzy technique called adaptive neuro-fuzzy inference system (ANFIS) for disease diagnosis. Gaussian membership function is used as the fuzzifier, and custom defuzzifier is used to defuzzify the output. A rule-based system is used for medication and laboratory test recommendations. The proposed medical decision support system can aid medical practitioners in making better, effective, and faster diagnostic decisions, thereby helping in increasing the in-patient count and quality of medical care. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Modeling the Propagation of soft Errors in Programs 19

Modeling the Propagation of Soft Errors in Programs

引用

2nd international conference on Computer science and software Engineering (CSSE)

作者： Xue, Lixing Zhang, Zhan Zou, Decheng Harbin Inst Technol China Sch Comp Sci & Technol Harbin Peoples R China

ISBN: (纸本)9781450371728

Due to the continuous growth of transistors in processors, the cloud computing paradigm and increasingly complex environment, soft errors, which are a category of typical transient errors, have become an urgent challenge in ground-level systems. To handle these errors, making clear the error propagation is the key step. As programs become large, we cannot employ traditional fault injection campaigns to monitor every possible error. This paper proposes a method to study and model the propagation of soft errors within a program. Based on dynamic instructions traced in an error-free program execution, the ACE analysis classifies soft errors in architectural registers into benign ones and non-benign ones. The benign errors are considered to be derated in the propagation. Then we build a crash model and an improved DDG to analyze the propagation of each non-benign error and to predict its consequence ( crash or silent data corruption). If the error is considered to cause a crash, the crash latency and the propagation path are also predicted. The method can be used to predict outcomes of programs under soft errors as well as occurrence of correct outputs, silent data corruptions or crashes. Extensive fault-injection experiments are provided to validate the proposed method from multiple perspectives.

关键词： soft error Error propagation Crash Silent data corruption Correct output Architecturally correct execution Dynamic dependency graph Crash latency Propagation path

来源：评论

学校读者我要写书评

暂无评论

Estimating Median in the Multi-sourced Heterogeneous data Set: A distributed implementation 2

Estimating Median in the Multi-sourced Heterogeneous Data Se...

引用

2019 2nd international Symposium on Big data and Applied Statistics, ISBDAS 2019

作者： Gao, Tian Zhao, Yanyu Deng, Xinyi Li, Wenze Li, Hongjun Zhao, Xin Beijing Normal University No 18 Jinfeng Road Tangjiawan Zhuhai Zhuhai China

The continuous running of enterprise applications produces a huge volume of business data that reside in different storage and system environments and owned by different companies or organizations, which forms a typical distributed, multi-sourced heterogeneous dataset. The multi-sourced heterogeneous data set provides big potential values for official statistics. While the median is a commonly used indicator in official statistics, it is not a trivial task to estimate the median in the distributed computing environment of multi-sourced heterogeneous data set due to its mathematical nature. In this paper, we proposed a distributed method to estimate the median value for the multi-sourced heterogeneous data set. Mainly considering the different size of multi-sourced data set and unevenly distribution of their data values, we first improve the traditional interpolation based median estimation method for the multi-sourced heterogeneous data set. Then, we propose distributed implementation for the proposed median estimation method based on web service technology. Finally, we evaluate the accuracy and performance of proposed method through experimental study. CCS Concepts Information systems data management systems Information integration Mediators and data integration. © Published under licence by IOP Publishing Ltd.

关键词： data integration

来源：评论

学校读者我要写书评

暂无评论

An Encryption Method Based on "zipper" Stochastic Dynamic Hashing 2

An Encryption Method Based on "zipper" Stochastic Dynamic Ha...

引用

2020 2nd international conference on Electronic Engineering and Informatics, EEI 2020

作者： Feng, Guanghui Zhang, Chunfu Si, Yujuan Lang, Liuqi School of Computing Zhuhai College of Jilin University Zhuhai China School of Public Basic and Applied Statistics Zhuhai College of Jilin University Zhuhai China School of Computer Science and Technology Jilin University Changchun China School of Electronics Zhuhai College of Jilin University Zhuhai China

This paper studies the theoretical problems and implementation methods of stream ciphers, discusses some deficiencies of conventional stream cipher algorithms, designs methods and rules for random Dynamic Hash Mapping and Bits Scrambling, applies nonlinear feedback shift register (NLFSR) technology, and a new stream cipher method with higher security strength and suitable for encryption of short information is proposed. The purpose is to apply the proposed new method of stream cipher to obtain higher encryption strength and code uniformity, and make some theories and algorithms in the research results have beneficial effects on information security in the era of big data. © Published under licence by IOP Publishing Ltd.

关键词： Security of data

来源：评论

学校读者我要写书评

暂无评论

Instance Segmentation of Densely Packed Cells Using a Hybrid Model of U-Net and Mask R-CNN 19th

Instance Segmentation of Densely Packed Cells Using a Hybrid...

引用

19th international conference on Artificial Intelligence and soft computing, ICAISC 2020

作者： Konopczyński, Tomasz Heiman, Ron Woźnicki, Piotr Gniewek, Pawel Duvernoy, Marie-Cécilia Hallatschek, Oskar Hesser, Jürgen Department of Data Analysis and Modeling in Medicine Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Heidelberg Germany Departments of Physics and Integrative Biology University of California BerkeleyCA94720 United States Faculty of Medicine Medical University of Warsaw Warsaw Poland Tooploox Ltd. Wroclaw Poland

ISBN: (纸本)9783030614003

In malignant tumors and microbial infections, cells are commonly growing under confinement due to rapid proliferation in limited space. Nonetheless, this effect is poorly documented despite influencing drug efficiency. Studying budding yeast grown in space-limited micro-environments is a great tool to investigate this effect, conditioned on a robust cell instance segmentation. Due to confinement, cells become densely packed, impairing traditional segmentation methods. To tackle that problem, we show the performance of Mask-RCNN based methods on our dataset of budding yeast populations in a space-limited environment. We compare a number of methods, which include the pure Mask R-CNN, the 1st and 2nd place solution of the 2018 Kaggle data science Bowl and a watershed ensemble variant of Mask R-CNN and U-Net. Additionally, we propose a Hybrid model that combines a semantic and an instance segmentation module in a sequential way. In the latter, the encoder-decoder architecture used for semantic segmentation produces a segmentation probability map, which is concatenated with the input image and then fed into the Mask R-CNN network in order to achieve the final instance segmentation result. Consequently, this model is able to efficiently share and reuse information at different levels between the two network modules. Our experiments demonstrate that the proposed model performs best and achieves a mean Average Precision (mAP) of 0.724 and a Dice coefficient of 0.9284 on our dataset. © 2020, Springer Nature Switzerland AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Drop-Out in Higher Institution Using data Mining Techniques 2

Predicting Student Drop-Out in Higher Institution Using Data...

引用

2nd international conference of Mathematics, Statistics and computing Technology 2019, ICMSCT 2019

作者： Wan Yaacob, W.F. Mohd Sobri, N. Nasir, S.A. Md Wan Yaacob, W.F. Norshahidi, N.D. Wan Husin, W.Z. Faculty of Computer and Mathematical Sciences Universiti Teknologi MARA Cawangan Kelantan Bukit Ilmu Machang Kelantan18500 Malaysia Business Datalytics Research Group Universiti Teknologi MARA Cawangan Kelantan Kampus Kota Bharu Lembah Sireh Kota Bharu Kelantan15050 Malaysia

The increasing number of students dropping out is a major concern of higher educational institutions as it gives a great impact not only cost to the students but also a waste of public funds. Thus, it is imperative to understand which students are at risk of dropping out and what are the factors that contribute to higher dropout rates. This can be done using educational data mining. In this paper, we described the uses of data mining techniques to predict student dropout of Computer science undergraduate students after 3 years of enrolment in Universiti Teknologi MARA. The experimental results showed an achievable reliable classification accuracy from the selected algorithm in predicting dropouts. Decision tree, logistic regression, random forest, K-nearest neighbour and neural network algorithm were compared to propose the best model. The results showed that some of the machines learning algorithms are able to establish effective predictive models from student retention data. The Logistic Regression model was found to be the best learners to predict the dropout students with identified potential subject causes. In addition, we also presented some findings related to data exploration. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Sensors and biosorption for better reuse of wastewater 2nd

Sensors and biosorption for better reuse of wastewater

引用

2nd international conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2019

作者： Rocher, Javier Basterrechea, Daniel A. Fawzy, Manal Lloret, Jaime Omar, Mohamed Y. Instituto de Investigación para la Gestión Integrada de zonas Costeras Universitat Politècnica de València Gandia Spain Environmental Sciences Department Faculty of Science Alexandria University Alexandria Egypt Basics and Applied Sciences Department College of Engineering and Technology Arab Academy for Science Technology and Maritime Transport Alexandria Egypt

ISBN: (纸本)9783030366636

Water is an increasingly scarce resource today due to natural and anthropic factors. Therefore, wastewater treatment and reuse is an important parameter of sustainable development. The necessity of reuse wastewater especially for irrigation becomes evident. Innovative wastewater monitoring and treatment methodologies are finding application as technologies improve. The most talented technological advances include: innovative monitoring techniques based on new sensors, computerized telemetry devices, and innovative data analysis tools. Research on sensor and alarming systems is advancing rapidly. Likewise, new methods for wastewater treatment are continually introduced, including the use dead plants biomass for heavy metals removal from wastewater. In this paper, the use of sensors for monitoring and the application of biosorption techniques for wastewater recycling are discussed and evaluated. We propose biosorption for removing heavy metals from wastewater. Sensors are used before and after the biosorption for check the quality of water and the proper functioning of the biosorption process. © Springer Nature Switzerland AG 2020.

关键词： Water quality

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：