Informatik
Refine
Document Type
- Conference Proceeding (268)
- Article (69)
- Part of a Book (42)
- Book (13)
- Doctoral Thesis (8)
- Anthology (5)
- Working Paper (2)
- Patent (1)
With the capability of employing virtually unlimited compute resources, the cloud evolved into an attractive execution environment for applications from the High Performance Computing (HPC) domain. By means of elastic scaling, compute resources can be provisioned and decommissioned at runtime. This gives rise to a new concept in HPC: Elasticity of parallel computations. However, it is still an open research question to which extent HPC applications can benefit from elastic scaling and how to leverage elasticity of parallel computations. In this paper, we discuss how to address these challenges for HPC applications with dynamic task parallelism and present TASKWORK, a cloud-aware runtime system based on our findings. TASKWORK enables the implementation of elastic HPC applications by means of higher level development frameworks and solves corresponding coordination problems based on Apache ZooKeeper. For evaluation purposes, we discuss a development framework for parallel branch-and-bound based on TASKWORK, show how to implement an elastic HPC application, and report on measurements with respect to parallel efficiency and elastic scaling.
Due to frequently changing requirements, the internal structure of cloud services is highly dynamic. To ensure flexibility, adaptability, and maintainability for dynamically evolving services, modular software development has become the dominating paradigm. By following this approach, services can be rapidly constructed by composing existing, newly developed and publicly available third-party modules. However, newly added modules might be unstable, resource-intensive, or untrustworthy. Thus, satisfying non-functional requirements such as reliability, efficiency, and security while ensuring rapid release cycles is a challenging task. In this paper, we discuss how to tackle these issues by employing container virtualization to isolate modules from each other according to a specification of isolation constraints. We satisfy non-functional requirements for cloud services by automatically transforming the modules comprised into a container-based system. To deal with the increased overhead that is caused by isolating modules from each other, we calculate the minimum set of containers required to satisfy the isolation constraints specified. Moreover, we present and report on a prototypical transformation pipeline that automatically transforms cloud services developed based on the Java Platform Module System into container-based systems.
Mittlerweile ist der Einsatz von technischen Hilfsmitteln zu Analysezwecken im Sport fester Bestandteil im Trainingsalltag von Trainern und Athleten. In nahezu jeder Sportart werden Videoaufzeichnungen genutzt, um die Bewegungsausführung zu dokumentieren und zu analysieren. Allerdings reichen Aufnahmen von einem statischen Standort oftmals nicht mehr aus.
An dieser Stelle kann Virtual Reality (VR) eine Lösung dieses Problems bieten. Durch VR kann der aufgezeichneten Szene eine weitere Ebene hinzugefügt und die Bewegungsabläufe neu und detaillierter bewertet werden. Um Bewegungen in einer virtuellen Umgebung abzubilden, müssen diese mittels Motion Capturing (MoCap) aufgezeichnet werden.
Ziel dieser Arbeit ist es, herauszufinden, ob das MoCap System Perception Neuron in der Lage ist, Bewegungen in hoher Geschwindigkeit zu erfassen.
In den letzten Jahren beschäftigten sich Forscher und Automobilhersteller mit den Voraussetzungen für die Einführung von autonomem Fahren. Für Innovationen und Geschäftsmodelle im Bereich der intelligenten Mobilität, aber auch innerhalb der digitalen Wertschöpfungskette, spielen generell Zuverlässigkeit und Qualität der digitalen Datenübertragung eine entscheidende Rolle. Bevor das autonome Fahren vollständig eingeführt wird, muss man feststellen, welche Anforderungen an die digitale Infrastruktur beachtet werden müssen, gleichzeitig muss die Bedrohungslandschaft für autonomes Fahren analysiert werden.
Die folgende Arbeit beschäftigt sich damit, die Anforderungen und Gefahren zu analysieren und allgemeine Handlungsempfehlungen vorzuschlagen.
Ein stark erforschtes Gebiet der Computer Vision ist die Detektion von markanten Punkten des Gesichtszuges (englisch: facial feature detection), wie der Mundwinkel oder des Kinns. Daher lassen sich eine Vielzahl von veröffentlichten Verfahren finden, die sich jedoch teils deutlich hinsichtlich der Detektionsgenauigkeit, Robustheit und Geschwindigkeit unterscheiden. So sind viele Verfahren nur bedingt echtzeitfähig oder liefern nur mit hochaufgelösten Bildquellen ein zufriedenstellendes Ergebnis. In den letzten Jahren wurden daher Verfahren entwickelt, die versuchen, diese Problematiken zu lösen. In dieser Arbeit erfolgt eine Betrachtung dreier dieser State-of-the-Art Verfahren: Constrained Local Neural Fields (CLNF), Discriminative Response Map Fitting (DRMF) und Structured Output SVM (SO SVM), sowie deren Implementierungen. Dazu erfolgt ein empirischer Vergleich hinsichtlich der Detektionsgenauigkeit.
Mit der Informatics Inside 2018 findet diese Veranstaltungsform bereits zum 10. Mal statt und wir freuen uns besonders auf dieses Jubiläum. Die diesjährige Konferenz steht unter dem Motto „connect(IT);“ und zeigt damit einmal mehr die zentrale Bedeutung der Informatik im Zusammenhang mit Vernetzungen und dies auf allen Ebenen. Es geht nicht nur um die technische Vernetzung von Maschinen und Services, sondern auch um die Vernetzung von Menschen untereinander und die Zusammenarbeit zwischen Mensch und Maschine. Gerade die letzten beiden Punkte spiegeln einen der Schwerpunkte des Masterstudiengangs Human-Centered Computing sehr schön wieder. Sie finden in dem vorliegenden Tagungsband Fachbeiträge aus dem medizinischen Umfeld ebenso wie vielfältige Anwendungen aus dem Fahrzeugsektor. Selbstverständlich spielt das Thema Sicherheit in vernetzten Umgebungen eine wichtige Rolle und auch dazu finden Sie einen spannenden Beitrag. Der Kulturwandel im Bereich der Softwareentwicklung ist ebenso ein Thema wie Simulationen in verschiedenen Zusammenhängen.
Die Informatics Inside ist eine wissenschaftliche Konferenz des Masterstudiengangs Human-Centered Computing und wird von den Studierenden organisiert und durchgeführt. Sie erhalten während ihres Masterstudiums die Gelegenheit, sich in einem Fachgebiet ihrer Wahl zu vertiefen. Dies kann an der Hochschule, in einem Unternehmen, einem Forschungsinstitut oder im Ausland durchgeführt werden. Gerade diese flexible Ausgestaltung der Lehrveranstaltung „Wissenschaftliche Vertiefung“ führt zu vielfältigen Themenfeldern, die von den Studierenden bearbeitet werden. Neben der eigentlichen fachlichen Vertiefung spielt auch die Präsentation von wissenschaftlichen Ergebnissen eine wichtige Rolle und dies nicht nur während des Studiums. Ein gewähltes Fachgebiet so allgemeinverständlich aufzubereiten und zu vermitteln, dass es auch für Nicht-Spezialisten verständlich wird, stellt immer wieder eine besondere Herausforderung dar.
In the present tutorial we perform a cross-cut analysis of database storage management from the perspective of modern storage technologies. We argue that neither the design of modern DBMS, nor the architecture of modern storage technologies are aligned with each other. Moreover, the majority of the systems rely on a complex multi-layer and compatibility oriented storage stack. The result is needlessly suboptimal DBMS performance, inefficient utilization, or significant write amplification due to outdated abstractions and interfaces. In the present tutorial we focus on the concept of native storage, which is storage operated without intermediate abstraction layers over an open native storage interface and is directly controlled by the DBMS.
With on-demand access to compute resources, pay-per-use, and elasticity, the cloud evolved into an attractive execution environment for High Performance Computing (HPC). Whereas elasticity, which is often referred to as the most beneficial cloud-specific property, has been heavily used in the context of interactive (multi-tier) applications, elasticity-related research in the HPC domain is still in its infancy. Existing parallel computing theory as well as traditional metrics to analytically evaluate parallel systems do not comprehensively consider elasticity, i.e., the ability to control the number of processing units at runtime. To address these issues, we introduce a conceptual framework to understand elasticity in the context of parallel systems, define the term elastic parallel system, and discuss novel metrics for both elasticity control at runtime as well as the ex post performance evaluation of elastic parallel systems. Based on the conceptual framework, we provide an in depth analysis of existing research in the field to describe the state-of-the art and compile our findings into a research agenda for future research on elastic parallel systems.
Early reduction of risks in a startup or an innovation project is highly important. Appropriate means for risk reduction, such as testing business models with different kinds of experiments exist. However, deciding what to test and how to select the right test, is challenging for many startups and innovation projects. This article presents the so-called Business Experiments Navigator (BEN), a toolkit to assist startup and innovation processes. It compliments other tools such as the Business Model Canvas or the Lean Startup process. The main contribution of BEN is to bridge the gap between the riskiest assumptions of a business model and the multitude of available testing techniques by providing assumption templates. The Business Experiments Navigator has been validated in several workshops. Results show that it creates awareness among the workshop participants that a business model is based on assumptions which impose risks and need to be validated. Further, users of BEN were able to identify relevant assumptions and map different kinds of assumptions to appropriate testing techniques. The process applied in the workshops, as well as the assumption templates, helped the participants understand the main concepts and transfer their learnings, to their own business ideas.
A transaction is a demarcated sequence of application operations, for which the following properties are guaranteed by the underlying transaction processing system (TPS): atomicity, consistency, isolation, and durability (ACID). Transactions are therefore a general abstraction, provided by TPS that simplifies application development by relieving transactional applications from the burden of concurrency and failure handling. Apart from the ACID properties, a TPS must guarantee high and robust performance (high transactional throughput and low response times), high reliability (no data loss, ability to recover last consistent state, fault tolerance), and high availability (infrequent outages, short recovery times).
The architectures and workhorse algorithms of a high-performance TPS are built around the properties of the underlying hardware. The introduction of nonvolatile memories (NVM) as novel storage technology opens an entire new problem space, with the need to revise aspects such as the virtual memory hierarchy, storage management and data placement, access paths, and indexing. NVM are also referred to as storage-class memory (SCM).
Active storage
(2019)
In brief, Active Storage refers to an architectural hardware and software paradigm, based on collocation storage and compute units. Ideally, it will allow to execute application-defined data ... within the physical data storage. Thus Active Storage seeks to minimize expensive data movement, improving performance, scalability, and resource efficiency. The effective use of Active Storage mandates new architectures, algorithms, interfaces, and development toolchains.
Blockchains yield to new workloads in database management systems and K/V-stores. Distributed Ledger Technology (DLT) is a technique for managing transactions in ’trustless’ distributed systems. Yet, clients of nodes in blockchain networks are backed by ’trustworthy’ K/V-Stores, like LevelDB or RocksDB in Ethereum, which are based on Log-Structured Merge Trees (LSM Trees). However, LSM-Trees do not fully match the properties of blockchains and enterprise workloads.
In this paper, we claim that Partitioned B-Trees (PBT) fit the properties of this DLT: uniformly distributed hash keys, immutability, consensus, invalid blocks, unspent and off-chain transactions, reorganization and data state / version ordering in a distributed log-structure. PBT can locate records of newly inserted key-value pairs, as well as data of unspent transactions, in separate partitions in main memory. Once several blocks acquire consensus, PBTs evict a whole partition, which becomes immutable, to secondary storage. This behavior minimizes write amplification and enables a beneficial sequential write pattern on modern hardware. Furthermore, DLT implicate some type of log-based versioning. PBTs can serve as MV-store for data storage of logical blocks and indexing in multi-version concurrency control (MVCC) transaction processing.
Modern persistent Key/Value stores are designed to meet the demand for high transactional throughput and high data ingestion rates. Still, they rely on backwards-compatible storage stack and abstractions to ease space management, foster seamless proliferation and system integration. Their dependence on the traditional I/O stack has negative impact on performance, causes unacceptably high write-amplification, and limits the storage longevity.
In the present paper we present NoFTL KV, an approach that results in a lean I/O stack, integrating physical storage management natively in the Key/Value store. NoFTL-KV eliminates backwards compatibility, allowing the Key/Value store to directly consume the characteristics of modern storage technologies. NoFTLKV is implemented under RocksDB. The performance evaluation under LinkBench shows that NoFTL-KV improves transactional throughput by 33%, while response times improve up to 2.3x. Furthermore, NoFTL KV reduces write-amplification 19x and improves storage longevity by imately the same factor.
Background: Internationally, teledermatology has proven to be a viable alternative to conventional physical referrals. Travel cost and referral times are reduced while patient safety is preserved. Especially patients from rural areas benefit from this healthcare innovation. Despite these established facts and positive experiences from EU neighboring countries like the Netherlands or the United Kingdom, Germany has not yet implemented store-and-forward teledermatology in routine care.
Methods: The TeleDerm study will implement and evaluate store-and-forward teledermatology in 50 general practitioner (GP) practices as an alternative to conventional referrals. TeleDerm aims to confirm that the possibility of store-and-forward teledermatology in GP practices is going to lead to a 15% (n = 260) reduction in referrals in the intervention arm. The study uses a cluster-randomized controlled trial design. Randomization is planned for the cluster “county”. The main observational unit is the GP practice. Poisson distribution of referrals is assumed. The evaluation of secondary outcomes like acceptance, enablers and barriers uses a mixed methods design with questionnaires and interviews.
Discussion: Due to the heterogeneity of GP practice organization, patient management software, information technology service providers, GP personal technical affinity and training, we expect several challenges in implementing teledermatology in German GP routine care. Therefore, we plan to recruit 30% more GPs than required by the power calculation. The implementation design and accompanying evaluation is expected to deliver vital insights into the specifics of implementing telemedicine in German routine care.
We present an approach for segmenting individual cells and lamellipodia in epithelial cell clusters using fully convolutional neural networks. The method will set the basis for measuring cell cluster dynamics and expansion to improve the investigation of collective cell migration phenomena. The fully learning-based front-end avoids classical feature engineering, yet the network architecture needs to be designed carefully. Our network predicts how likely each pixel belongs to one of the classes and, thus, is able to segment the image. Besides characterizing segmentation performance, we discuss how the network will be further employed.
This work is a report on practical experiences with the issue of interoperability in German practice management systems (PMSs) from an ongoing clinical trial on teledermatology, the TeleDerm project. A proprietary and established web-platform for store-and-forward telemedicine is integrated with the IT in the GPs’ offices for automatic exchange of basic patient data. Most of the 19 different PMSs included in the study sample lack support of modern health data exchange standards, therefore the relatively old but widely available German health data exchange interface “Gerätedatentransfer” (GDT) is used. Due to the lack of enforcement and regulation of the GDT standard, several obstacles to interoperability are encountered. As a partial, but reusable working solution to cope with these issues, we present a custom middleware which is used in conjunction with GDT. We describe the design, technical implementation and observed hindrances with the existing infrastructure. A discussion on health care interfacing standards and the current state of interoperability in German PMS software is given.
Lots of movies are produced every year, too many to watch all of them and in particular, to get an overview about the evolution of typical movie genres and actors playing in them. Moreover, it is a challenging problem to detect correlations among the movies and the actors in those movies, in particular, if we are interested in time-varying data patterns like trends, countertrends, or anomalies and outliers. Those correlations are specifically interesting if they can be inspected on different levels of granularity, e.g., temporal, but also hierarchical in form of country- or continent-based correlations. In this paper we describe the IMDb Explorer, a webbased visualization tool that consists of two major views denoted by the movie cosmos and the career lines. Both views are linked and interactively manipulable while a list of user-defined metrics are explorable. We illustrate the usefulness of the visualization tool by applying it to the entire movie database provided by IMDb.
Workshops and tutorials
(2018)
The 19th International Conference on Product-Focused Software Process Improvement (PROFES 2018) hosted two workshops and three tutorials. The workshops and tutorials complemented and enhanced the main conference program, offering a wider knowledge perspective around the conference topics. The topics of the two workshops were Hybrid Development Approaches in Software Systems Development (HELENA) and Managing Quality in Agile & Rapid Software Development Processes (QUaSD). The topics of the tutorials were The human factor in agile transitions – using the personas concept in agile oaching, Process Management 4.0 – Best Practices, and Domain-specific languages for specification, development, and testing of autonomous systems.
Being able to monitor the heart activity of patients during their daily life in a reliable, comfortable and affordable way is one main goal of the personalized medicine. Current wearable solutions lack either on the wearing comfort, the quality and type of the data provided or the price of the device. This paper shows the development of a Textile Sensor Platform (TSP) in the form of an electrocardiogram (ECG)-measuring T-shirt that is able to transmit the ECG signal to a smartphone. The development process includes the selection of the materials, the design of the textile electrodes taking into consideration their electrical characteristics and ergonomy, the integration of the electrodes on the garment and their connection with the embedded electronic part. The TSP is able to transmit a real-time streaming of the ECG-signal to an Android smartphone through Bluetooth Low Energy (BLE). Initial results show a good electrical quality in the textile electrodes and promising results in the capture and transmission of the ECG signal. This is still a working- progress and it is the result of an interdisciplinary master project between the School of Informatics and the School of Textiles & Design of the Reutlingen University.
