检索结果-内蒙古大学图书馆

4th international conference on Intelligent Systems and Pattern Recognition, ISPR 2024

作者： Nafchi, Amin Ghasemi Cheriet, Mohamed Department of System Engineering Ecole de technologie supérieure Montreal Canada

ISBN: (纸本)9783031821523

Various degradations available in historical document images pose challenges to automatic document restoration methods. Recent strides in deep learning and generative adversarial networks (GANs) for document analysis encounter challenges in generalization and practical application. Due to the absence of boundary-related supervision, conventional convolutional approaches often struggle to extract stroke edges from documents undergoing binarization consistently. In this study, we present a GAN-based robust end-to-end system to restore heavily damaged document images and tackle the problem of inaccurate stroke edge extraction. In the proposed framework, there is a single generator along with two discriminators. this approach leverages object and contour data concurrently, enhancing binarization results. the auxiliary discriminator is crucial in ensuring the accurate prediction of stroke edges. the solution consistently outperforms state-of-the-art techniques on DIBCO datasets from 2017 and 2018, proving its ability to recover a damaged document image. the results obtained across a diverse set of degradations showcase the flexibility of the proposed approach, making it applicable to various document restoration applications. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Rapid data Stream Application Development Framework 4

Rapid Data Stream Application Development Framework

引用

4th international conference on data and software engineering (icodse)

作者： Tanujaya, Wilhelmus Andrian Candra, Muhammad Zuhri Catur Akbar, Saiful Inst Teknol Bandung Sekolah Tekn Elektro & Informat Bandung Indonesia

ISBN: (纸本)9781538614495

Developers of data stream processing application have to write a lot of codes even for a simple functionality, and, to make it worse, tend to rewrite their codes when developing different applications. these developers also need to recompile the code even for simple changes. In this paper, we present a configurable data stream application framework, which will help developers in developing data stream applications by reducing the amount of codes written to develop a data stream processing application. In this framework, we introduce a Domain Specific Language (DSL) for defining and configuring the data stream application. Our framework provides many basic stream processing functionalities, such as passing the data from data source to processing classes, filtering, windowing the data, as well as sending the data to data collectors. Most configurations related to these functionalities can be easily changed using the DSL without the need to recompile the code. the framework was tested using two case studies, where for each of them we developed data stream applications with and without the framework. the case studies show the increased productivity in terms of the number of lines of code and the number of files written for each respective application.

关键词： application framework data stream configuration Apache Flink

来源：评论

学校读者我要写书评

暂无评论

An Online Intrusion Detection Method using Adaptive Multi-Level Classifier Network and PCA-Guided Model Reuse Mechanism 25

An Online Intrusion Detection Method using Adaptive Multi-Le...

引用

Proceedings of the 2025 4th international conference on Cryptography, Network Security and Communication Technology

作者： Haizhaoyang Huang Hongpo Zhang School of Cyber Science and Engineering Zhengzhou University Zhengzhou Henan China

ISBN: (纸本)9798400712623

the network era caused the network security concerns to escalate dramatically, and network intrusion detection is shown as an important technology to guarantee network security. During the past few years, artificial intelligence technology has improved remarkably, and also involve advances from various studies, which started to adapt deep learning with intrusion detection models and obtained some salient detection results. However, the Internet is a developing environment, concept drift will unavoidably be produced which may result in model degeneration. Meanwhile, to tackle these difficulties, we propose an online adaptive intrusion detection method and the key point is a model reuse mechanism and an adaptive multi-level classifier network. the reuse of model exploits the principal component analysis to identify the most similar historical distribution to the current data and adopts different strategies with respect to different degree of drift to reduce the computational overhead avoid the model retraining. Adaptive multi-level classifier network consists of several classifiers with different depth layer. these classifiers dynamically adapt their adaptive weights based on their classification losses, and the final classification is calculating the weighted output of multiple layers. Experiments conducted on CIC-IDS2017 and UNSW-NB15 datasets and demonstrate that the proposed method achieves an average accuracy of 97.69% and 95.96%, respectively, which superior to that of state-of-the-art methods:

关键词： Concept drift

来源：评论

学校读者我要写书评

暂无评论

Designing Dashboard Visualization for Heterogeneous Stakeholders (Case Study: ITB Central Library) 4

Designing Dashboard Visualization for Heterogeneous Stakehol...

引用

4th international conference on data and software engineering (icodse)

作者： Orlando, Tjan Marco Sunindyo, Wikan Danar Inst Teknol Bandung Sekolah Tekn Elektro & Informat Informat Engn Ganesha 10 Bandung 40132 Indonesia Inst Teknol Bandung Knowledge & Software Engn Res Grp Ganesha 10 Bandung 40132 Indonesia

ISBN: (纸本)9781538614495

One of the media that can be used to visualize data and the results of its analysis is dashboard. Currently in the dashboard development there have been many methodologies that can be used as a reference. However, the existing methodology does not specify the steps necessary to ensure that the dashboard development is able to accommodate heterogeneous stakeholders, in which each stakeholder has different needs and activities. In ITB central library, there has been adequate data storage method, in the form of database. However, ITB central library does not yet have a dashboard as a medium that can support the use of data by heterogeneous stakeholders. this research aims to develop dashboard of ITB central library for heterogeneous stakeholders. the dashboard is expected to support data utilization by stakeholders, both for analytical and administrative purposes. In this research also conducted a study related to dashboard development methodology, for further modification to show in detail dashboard development steps to accommodate heterogeneous stakeholders. Evaluation of dashboard implementation result is conducted empirically, involving sample from stakeholder of ITB central library. the evaluation uses two existing standardized usability questionnaire, System Usability Scale (SUS) and the Usability Metric for User Experience (UMUX). In the evaluation, it is also compiled comments from all evaluation participants to find out how far the dashboard can meet the needs of each stakeholder involved.

关键词： dashboard methodology stakeholder heterogenous

来源：评论

学校读者我要写书评

暂无评论

Semi-Automated data Publishing Tool for Advancing the Indonesian Open Government data Maturity Level Case Study: Badan Pusat Statistik Indonesia 4

Semi-Automated Data Publishing Tool for Advancing The Indone...

引用

4th international conference on data and software engineering (icodse)

作者： Nusapati, Chairuni Aulia Sunindyo, Wikan Danar Inst Teknol Bandung Sch Elect Engn & Informat Bandung Indonesia

ISBN: (纸本)9781538614495

Open Government data (OGD) refers to the data produced or commissioned by the government or the government-controlled entities that can be freely used, reused, and redistributed by anyone. In Indonesia, the creation and use of OGD have been supported by the government since 2011. However, in contrary, the maturity level of the OGD published on the publishing sites is quite low, scoring only one up to three stars out of the maximum five stars according to the global Five Star Open data standard. this paper describes a solution for the problem in the form of a semi-automated publishing tool that could be used to advance the current OGD maturity level in Indonesia. Government agencies, represented by their administrators, could use the tool to process their existing data into the more mature ones. the tool would take government data in the form of Excel and CSV files, or in other words 2-star and 3-star respectively, and process them into the maximum 5-star data in various formats. the main framework of the tool is developed based on an existing framework, extended to give more detailed steps and match to the case study at the Badan Pusat Statistik Indonesia (Indonesian Central Bureau of Statistics). Based on the evaluation, the tool can level up the existing data's maturity level from 2-star and 3-star to the maximum 5-star based on the Five Star Open data Standard. this promising result encourages the authors to develop the tool even further in another research and the authors have also provided some possible further development based on the result of this work.

关键词： open government data open government semi-automated data publishing tool

来源：评论

学校读者我要写书评

暂无评论

Graph Analysis on ATCS data in Road Network for Congestion Detection 4

Graph Analysis on ATCS Data in Road Network for Congestion D...

引用

4th international conference on data and software engineering (icodse)

作者： Ramdlani, Apip Saptawati, G. A. Putri Asnar, Yudistira Inst Teknol Bandung Sch Elect Engn & Informat Bandung Indonesia

ISBN: (纸本)9781538614495

this research is development a framework for detecting congestion on the urban road network. ATCS (Area Traffic Control System) data in Bandung city with traffic volume are used in congestion detection process. Traffic flow data is collected by vehicles detector located at crossroads within 15 minutes. To compute spatial correlation, graph modelling are used in the adjacency matrix. Assuming the location of the detector as the vertices and the direction of the vehicle as the edge, the graph modeled with vehicle's detector location and the flow direction at nine locations on road nework. the adjacency matrix used consists of 3 matrices in each period of time, which describes the order of spatial distances traveled by vehicle at the intersection location. To calculate spatial correlation, the autocorrelation function and the cross-correlation function which are derived from Pearson's simple correlation is used to looking influence at each location on road network. the result of calculation of spatial correlation, shows the existence of seasonal pattern on the autocorrelation results even though the value scale is getting smaller as it increases time lags. this provides that the process of calculating cross-correlation functions and it can be concluded that the volume of vehicles at each location that are connected in the road network can be known by making observations in the time series of previous seasonal periods. the conclusion that can be formulated that graph modeling is needed to simplify the spatial correlation calculation process by performing the graph representation into a matrix. the Simpson rules on cross-correlation results, can be detected congestion at intersection locations on the road network to find the most critically locations causing congestion on the road network at time periods.

关键词： graph analysis area traffic control system road network traffic flow critical section level of service

来源：评论

学校读者我要写书评

暂无评论

Proceedings of 2017 international conference on data and software engineering, icodse 2017

Proceedings of 2017 International Conference on Data and Sof...

引用

4th international conference on data and software engineering, icodse 2017

ISBN: (纸本)9781538614495

the proceedings contain 55 papers. the topics discussed include: a classification of sequential patterns for numerical and time series multiple source data - a preliminary application on extreme weather prediction;a statistical and rule-based spelling and grammar checker for Indonesian text;anomaly detection using random forest: a performance revisited;an extensible tool for spatial clustering;aspect-sentiment classification in opinion mining using the combination of rule-based and machine learning;cells identification of acute myeloid leukemia AML M0 and AML M1 using k-nearest neighbour based on morphological images;classification and clustering to identify spoken dialects in Indonesian;comparison of optimal path finding techniques for minimal diagnosis in mapping repair;spatio-temporal mining to identify potential traffic congestion based on transportation mode;enhancing clustering quality of fuzzy geographically weighted clustering using ant colony optimization;graph clustering using Dirichlet process mixture model;and imputation of missing value using dynamic Bayesian network for multivariate time series data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

international conference ON software engineering FOR TELECOMMUNICATION SWITCHING SYSTEMS, 4th, 1981.

引用

IEE conference Publication 1981年第198期

作者： Anon

Proceedings includes 39 papers concentrating on the use of computer software and microprocessors in the operation of modern advanced switching systems, particularly automatic telephone exchanges. Topics considered include: private exchanges, automatic telephone systems, computer programming, programming languages, automata theory, quality assurance and control, data transmission and processing, telecommunication systems, and automatic testing. Technical and professional papers from this conference are indexed with the conference code no. 00288 in the Ei engineering Meetings (TM) database produced by engineering Information, Inc.

关键词： TELEPHONE EXCHANGES

来源：评论

学校读者我要写书评

暂无评论

Hiding data in Indexed Images

Hiding Data in Indexed Images

引用

2013 IEEE 4th international conference on software engineering and Service Science

作者： WANG Haibo FEI Ruchun School of electrical and information engineering Liaoning Institute of Science and Technology

ISBN: (纸本)9781467349970

In this paper,a method for hiding data is proposed based on color table expansion technique for indexed *** the same time the security and the hiding capacity are analyzed in great *** analytic results show that this method has very strong security and very high hiding *** data can be hidden in a stego-image which has exactly the same visual effect as the original *** the correct key is used,these confidential data can be recovered from the stego-image without *** addition,due to the use of random numbers,the statistical properties of the confidential data are completely overshadowed,and the stego-image is independent of those confidential data.

关键词： data Hiding,Cover Image,Stego-image,Statistical Property,Hiding Capacity

来源：评论

学校读者我要写书评

暂无评论

the data Protection of MapReduce Using Homomorphic Encryption

The Data Protection of MapReduce Using Homomorphic Encryptio...

引用

2013 IEEE 4th international conference on software engineering and Service Science

作者： Xu Chen Qiming Huang Department of Computer and Communication University of Science and Technology

ISBN: (纸本)9781467349970

MapReduce is a programming model which can handle big data efficiently,but the security of intermediate data of MapReduce is not well protected,and the operations on ciphertexts were not *** achieve a trustworthy MapReduce,there is a need to both protect the data,as well as to allow specific types of computations to be carried out on encrypted intermediate *** encryption solutions can protect the data from being divulged,but they can’t be used to compute on encrypt data,however a novel encryption scheme,called fully homomorphic encryption（FHE）,could compute over encrypted data without decrypting *** this paper,we propose a modified framework of MapReduce using homomorphic encryption,in order to gain both the confidentiality of data,as well as the ability of computing on them.

关键词： MapReduce homomorphic data security

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：