检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Rückel, Timon Sedlmeir, Johannes Hofmann, Peter University of Bayreuth Bayreuth Germany FIM Research Center University of Bayreuth Bayreuth Germany Project Group Business & Information Systems Engineering of the Fraunhofer FIT Bayreuth Germany

Federated machine learning (FL) allows to collectively train models on sensitive data as only the clients’ models and not their training data need to be shared. However, despite the attention that research on FL has drawn, the concept still lacks broad adoption in practice. One of the key reasons is the great challenge to implement FL systems that simultaneously achieve fairness, integrity, and privacy preservation for all participating clients. To contribute to solving this issue, our paper suggests a FL system that incorporates blockchain technology, local differential privacy, and zero-knowledge proofs. Our implementation of a proof-of-concept with multiple linear regression illustrates that these state-of-the-art technologies can be combined to a FL system that aligns economic incentives, trust, and confidentiality requirements in a scalable and transparent *** Codes 68T01, 68M14 © 2021, CC BY-NC-ND.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Systematically combining process simulation and empirical data in support of decision analysis in software development 02

Systematically combining process simulation and empirical da...

引用

14th International Conference on software engineering and Knowledge engineering, SEKE '02

作者： Rus, Ioana Biffl, Stefan Halling, Michael Fraunhofer Center Maryland 4321 Hartwick Rd. Ste. 500 College Park MD 20740 United States Institute for Software Technology Vienna University of Technology Karlsplatz 13 A-1040 Vienna Austria Systems Engineering and Automation Johannes Kepler University Linz Altenbergerstr. 69 A-4040 Linz Austria

ISBN: (纸本)1581135564

Decision-making is a complex and important task in software engineering. The current state-of-the-practice is rather non-systematic as it typically relies upon personal experience without using explicit models. Empirical studies can help but are to some extent context dependent and costly to conduct. Typically it is not efficient or even possible to conduct empirical studies for a large number of context parameter variations. We propose to build on a set of systematic empirical studies to fill gaps in context variable space with simulation: (a) Simulation can use the empirical results from different contexts and apply them to a planning situation as appropriate. (b) The analysis of simulation results can point out situations and factors for which conducting empirical studies would be most worthwhile. This paper presents a general decision model, a simulation framework, and examples for different decisions to use V&V activities in software development (e.g., under which conditions is a V&V activity, such as a re-inspection, worthwhile) to demonstrate practical applications of the general model. Copyright 2000 ACM.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic establishment and maintenance of valid traceability in automotive development processes

Semi-automatic establishment and maintenance of valid tracea...

引用

International Workshop on software engineering for Embedded systems (SEES)

作者： Markus Fockel Jörg Holtmann Jan Meyer Project Group Mechatronic Systems Design Fraunhofer IPT Paderborn Germany Software Engineering Group Heinz Nixdorf Institute & s-lab - Software Quality Lab University of Paderborn Paderborn Germany Hella KGaA Hueck & Co. Lippstadt Germany

The functionality realized by software in modern cars is increasing and as a result the development artifacts of automotive systems are getting more complex. The existence of traceability along these artifacts is essential, since it allows to monitor the product development from the initial requirements to the final code. However, traceability is established and maintained mostly manually, which is time-consuming and error-prone. A further crucial problem is the assurance of the validity of the trace links, that is, the linked elements are indeed related to each other. In this paper we present a semiautomatic approach to create, check, and update trace links between artifacts along an automotive development process.

关键词： Analytical models Unified modeling language Automotive engineering Computer architecture Switches Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

Energy Anomaly Detection in Industrial Applications with Long Short-term Memory-based Autoencoders

引用

Procedia CIRP 2021年 104卷 182-187页

作者： Can Kaymakci Simon Wenninger Alexander Sauer Fraunhofer Institute for Manufacturing Engineering and Automation IPA Nobelstrasse 12 70569 Stuttgart Germany Institute for Energy Efficiency in Production University of Stuttgart FIM Research Center University of Applied Sciences Augsburg Project Group Business & Information Systems Engineering of the Fraunhofer FIT Universitätsstr. 12 Augsburg 86159 Germany

With the goal of reducing energy costs, carbon emissions, and achieving cleaner production, manufacturing companies aim to reduce their energy consumption. In manufacturing companies, a considerable amount of energy is wasted due to plant-, process- and human-related faults. Tools and methods for detecting anomalies are widely used for fraud detection in finance or intrusion detection in cybersecurity. When it comes to anomaly detection of malicious energy consumption, the residential building sector is leading. Industrial applications are not being addressed by now. In this paper, an end-to-end solution of an anomaly detection system is presented that uses the concept of a Long Short-term Memory based Autoencoder (LSTM-AE) as an unsupervised learning model that detects anomalies without labeling the data beforehand.

关键词： Anomaly detection Long-Short-Term-Memory Autoencoder Energy consumption AI in manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

Ernst Denert Award for software engineering 2022 1

引用

1000年

作者： Eric Bodden Michael Felderer Wilhelm Hasselbring Paula Herber Heiko Koziolek Carola Lilienthal Florian Matthes Lutz Prechelt Bernhard Rumpe Ina Schaefer

来源：评论

学校读者我要写书评

暂无评论

Professional Knowledge Management 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Klaus-Dieter Althoff Andreas Dengel Thomas Roth-Berghofer Ralph Bergmann Markus Nick

ISBN: (数字)9783540316206

ISBN: (纸本)9783540304654

Professional knowledge management is imperative for the success of enterprises. One decisive factor for the success of knowledge management projects is the coordination of elements such as corporate culture, enterprise organization, - man resource management, as well as information and communication techn- ogy. The proper alignment and balancing of these factors are currently little understood—especially the role of information technology, which is often - garded only as an implementation tool, though it can be a catalyst by making new knowledge management solutions possible. This conference brought together representativesfrom practical and research ?elds for discussing experiences, professional applications, and visions through presentations, workshops, tutorials, and an accompanying industry exhibition. The main focus of the conference was the realization of knowledge mana- ment strategies with the aid of innovative information technology solutions, such as intelligent access to organizational memories, or integration of business processes and knowledge management. Also of interest were holistic/integrative approaches to knowledge management that deal with issues raised by the in- gration of people, organizations, and information technology.

关键词： Artificial Intelligence Information Storage and Retrieval Information systems Applications (incl. Internet) Computer Appl. in Administrative Data Processing Computers and Education

来源：评论

学校读者我要写书评

暂无评论

Multimodal Detection of Tonic–Clonic Seizures Based on 3D Acceleration and Heart Rate Data from an In-Ear Sensor 25th

Multimodal Detection of Tonic–Clonic Seizures Based on 3D A...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Henze, Jasmin Houta, Salima Surges, Rainer Kreuzer, Johannes Bisgin, Pinar Fraunhofer Institute for Software and Systems Engineering Emil-Figge-Straße 91 Dortmund44227 Germany University of Bremen Bibliotheksstraße 1 Bremen28359 Germany Department of Epileptology University of Bonn Medical Center Venusberg-Campus 1 Bonn53127 Germany Cosinuss GmbH Kistlerhofstr. 60 München81379 Germany

ISBN: (纸本)9783030687625

Patients with epilepsy suffer from recurrently occurring seizures. To improve diagnosis and treatment as well as to increase patients’ safety and quality of life, it is of great interest to develop reliable methods for automated seizure detection. In this work, we evaluate a first trial of a multimodal approach combining 3D acceleration and heart rate data acquired with a mobile In-Ear sensor as part of the project EPItect. For the detection of tonic–clonic seizures (TCS), we train different classification models (Naïve Bayes, K-Nearest-Neighbor, linear Support Vector Machine and Adaboost.M1) and evaluate cost-sensitive learning as a measure to address the problem of highly imbalanced data. To assess the performance of our multimodal approach, we compare it to a unimodal approach, which only uses the acceleration data. Experiments show that our method leads to a higher sensitivity, lower detection latency and lower false alarm rate compared to the unimodal method. © 2021, Springer Nature Switzerland AG.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Hierarchische Eignungsprüfung von externen (Open) Data Sets für unternehmensinterne Analytics- und Machine-Learning-Projekte

引用

HMD Praxis der Wirtschaftsinformatik 2022年第1期60卷 144-161页

作者： Kaiser, Matthias Stirnweiß, Dominic Wederhake, Lars Project Group Business and Information Systems Engineering Fraunhofer Institute for Applied Information Technology FIT Augsburg Deutschland Adesso SE Dortmund Deutschland FIM Research Center University of Bayreuth Bayreuth Deutschland redium GmbH Augsburg Deutschland

Unternehmen erkennen zunehmend die Bedeutung evidenzbasierter Entscheidungen. Insbesondere die zunehmende Nutzung unternehmensexterner und offener Datensätze (Open Data) fördert die Möglichkeiten evidenzbasierter Entscheidungen. Dabei basieren evidenzbasierte Entscheidungen mit diesen Datensätzen immer häufiger auf Analysen, welche mittels maschineller Lernverfahren bzw. Machine Learning (ML) vorbereitet oder durchgeführt werden. Weil der Inhalt und die Qualität und damit der Nutzen eines Datensatzes für solche Analyseverfahren im Vorfeld ungewiss ist, stellt die Auswahl und die Beschaffung von geeigneten Daten unabhängig vom ML-Verfahren eine Kernherausforderung dar. Dieser Beitrag stellt deshalb zum Zwecke der Effizienz ein hierarchisches Vorgehen vor. Mit diesem können schemabasierte Datensätze strukturiert und effektiv dahingehend überprüft werden, ob deren Qualität und inhaltliche Fit für einen bestimmten Anwendungsfall (z. B. eine wiederkehrende Entscheidungssituation) ausreichend ist. Im Beitrag beschreiben wir einen Anwendungsfall aus dem Bereich der datengestützten Energieverbrauchsprognose für Wohngebäude, bei dem der Aufwand für die Datensatzauswahl reduziert werden konnte.

关键词：

来源：评论

学校读者我要写书评

暂无评论

You Can’t Manage What You Can’t Define: The Success of Blockchain projects Beyond the Iron Triangle 42

You Can’t Manage What You Can’t Define: The Success of Blo...

引用

42nd International Conference on Information systems: Building Sustainability and Resilience with IS: A Call for Action, ICIS 2021 TREOs

作者： Guggenberger, Tobias Stoetzer, Jens-Christian Theisinger, Lukas Amend, Julia Urbach, Nils Project Group Business Information Systems Engineering The Fraunhofer FIT Wittelsbacherring 10 Bayreuth95444 Germany FIM Research Center University of Bayreuth Wittelsbacherring 10 Bayreuth95444 Germany University of Bayreuth Universitätsstraße 30 Bayreuth95447 Germany Frankfurt University of Applied Sciences Nibelungenpl. 1 Frankfurt am Main60318 Germany

ISBN: (纸本)9781713893608

Companies across industries aim to disseminate blockchain through respective projects that evaluate, design, or implement use cases. However, due to its novelty and complexity, blockchain poses novel challenges in carrying out such projects. Companies use success criteria to constantly evaluate projects. Even though literature provides frameworks for the general evaluation of projects, no research yet investigated if success criteria fundamentally differ for blockchain projects due to the characteristics of the technology. Therefore, we assess success dimensions and criteria, deduced and evaluated from an in-depth interview study with blockchain experts from 12 different projects. We contribute to the theory on blockchain project management by introducing a new success dimension and specific success criteria for blockchain projects. Our findings help to elaborate the value of blockchain in companies and novel possibilities to evaluate respective projects. We provide additional insights by assessing their relative importance and discussing implications for theory and practice. © 2021 42nd International Conference on Information systems, ICIS 2021 TREOs: "Building Sustainability and Resilience with IS: A Call for Action". All Rights Reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Designing a framework for digital KYC processes built on blockchain-based self-sovereign identity

arXiv

引用

arXiv 2021年

作者： Schlatt, Vincent Sedlmeir, Johannes Feulner, Simon Urbach, Nils Fim Research Center University of Bayreuth Bayreuth Germany Project Group Business & Information Systems Engineering of the Fraunhofer Fit Bayreuth Germany Frankfurt University of Applied Sciences Frankfurt Germany

Know your customer (KYC) processes place a great burden on banks, because they are costly, inefficient, and inconvenient for customers. While blockchain technology is often mentioned as a potential solution, it is not clear how to use the technology's advantages without violating data protection regulations and customer privacy. We demonstrate how blockchain-based self-sovereign identity (SSI) can solve the challenges of KYC. We follow a rigorous design science research approach to create a framework that utilizes SSI in the KYC process, deriving nascent design principles that theorize on blockchain's role for SSI. © 2021, CC BY-NC-ND.

关键词： Distributed ledger

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：