Informatik
Refine
Year of publication
Document Type
- Conference proceeding (567) (remove)
Is part of the Bibliography
- yes (567)
Institute
- Informatik (567)
- Technik (2)
Publisher
- Springer (114)
- Hochschule Reutlingen (102)
- IEEE (83)
- Gesellschaft für Informatik (49)
- ACM (31)
- IARIA (19)
- Association for Information Systems (AIS) (11)
- RWTH Aachen (11)
- Deutsche Gesellschaft für Computer- und Roboterassistierte Chirurgie e.V. (9)
- SCITEPRESS (8)
- Università Politecnica delle Marche (8)
- University of Hawai'i at Manoa (6)
- IOS Press (5)
- SPIE (5)
- Fac. of Organization & Informatics, Univ. of Zagreb (4)
- RWTH (4)
- University of Hawaii at Manoa (4)
- Association for Computing Machinery (3)
- Deutsche Gesellschaft für Computer- und Roboterassistierte Chirurgie e. V. (3)
- Open Proceedings.org, Univ. of Konstanz (3)
- Science and Technology Publications (3)
- University of Konstanz, University Library (3)
- Academic Conferences International (2)
- American Marketing Association (2)
- Curran Associates (2)
- Curran Associates Inc. (2)
- EuroMed Press (2)
- GMDS e.V. (2)
- Gesellschaft für Informatik e.V (2)
- HTWG Konstanz (2)
- IADIS Press (2)
- IBM Research Division (2)
- International Society for Photogrammetry and Remote Sensing (2)
- Smart Home & Living Baden-Württemberg e.V. (2)
- Springer International Publishing (2)
- The Association for Computing Machinery, Inc. (2)
- University of Hawaii (2)
- AIP Publishing (1)
- Academic Conferences International Limited (1)
- Association for Computing Machinery ACM (1)
- CIDR (1)
- Cambridge University Press (1)
- Copenhagen Business School (1)
- Cuvillier Verlag (1)
- Deutsche Gesellschaft für Medizinische Physik (1)
- EMAC (1)
- Ed2.0Work (1)
- Elektronikpraxis, Vogel Business Media GmbH & Co. KG (1)
- EuroMedPress (1)
- Eurographics Association (1)
- Faculty of Economics (1)
- Faculty of Organization and Informatics, University of Zagreb (1)
- German Medical Science Publishing House (1)
- IADIS (1)
- International Association for Development of the Information Society (1)
- Johannes Kepler University Linz (1)
- Lund University (1)
- Morressier (1)
- NextMed (1)
- OpenProceedings (1)
- SISSA (1)
- SSRN (1)
- Science and Technology Publications, Lda (1)
- Shaker Verlag (1)
- Springer Gabler (1)
- The Association for Computing Machinery (1)
- University of Portsmouth (1)
- University of Zagreb Faculty of Organization and Informatics (1)
- Universität Trier (1)
- Universität des Saarlandes (1)
- libreriauniversitaria.it.edizioni (1)
- vwh (1)
Real Time Charging (RTC) applications that reside in the telecommunications domain have the need for extremely fast database transactions. Today´s providers rely mostly on in-memory databases for this kind of information processing. A flexible and modular benchmark suite specifically designed for this domain provides a valuable framework to test the performance of different DB candidates. Besides a data and a load generator, the suite also includes decoupled database connectors and use case components for convenient customization and extension. Such easily produced test results can be used as guidance for choosing a subset of candidates for further tuning/testing and finally evaluating the database most suited to the chosen use cases. This is why our benchmark suite can be of value for choosing databases for RTC use cases.
Context: The current situation and future scenarios of the automotive domain require a new strategy to develop high quality software in a fast pace. In the automotive domain, it is assumed that a combination of agile development practices and software product lines is beneficial, in order to be capable to handle high frequency of improvements. This assumption is based on the understanding that agile methods introduce more flexibility in short development intervals. Software product lines help to manage the high amount of variants and to improve quality by reuse of software for long term development.
Goal: This study derives a better understanding of the expected benefits for a combination. Furthermore, it identifies the automotive specific challenges that prevent the adoption of agile methods within the software product line.
Method: Survey based on 16 semi structured interviews from the automotive domain, an internal workshop with 40 participants and a discussion round on ESE congress 2016. The results are analyzed by means of thematic coding.
This document presents an algorithm for a nonobtrusive recognition of Sleep/Wake states using signals derived from ECG, respiration, and body movement captured while lying in a bed. As a core mathematical base of system data analytics, multinomial logistic regression techniques were chosen. Derived parameters of the three signals are used as the input for the proposed method. The overall achieved accuracy rate is 84% for Wake/Sleep stages, with Cohen’s kappa value 0.46. The presented algorithm should support experts in analyzing sleep quality in more detail. The results confirm the potential of this method and disclose several ways for its improvement.
The recovery of our body and brain from fatigue directly depends on the quality of sleep, which can be determined from the results of a sleep study. The classification of sleep stages is the first step of this study and includes the measurement of vital data and their further processing. The non-invasive sleep analysis system is based on a hardware sensor network of 24 pressure sensors providing sleep phase detection. The pressure sensors are connected to an energy-efficient microcontroller via a system-wide bus. A significant difference between this system and other approaches is the innovative way in which the sensors are placed under the mattress. This feature facilitates the continuous use of the system without any noticeable influence on the sleeping person. The system was tested by conducting experiments that recorded the sleep of various healthy young people. Results indicate the potential to capture respiratory rate and body movement.
At DBKDA 2019, we demonstrated that StrongDBMS with simple but rigorous optimistic algorithms, provides better performance in situations of high concurrency than major commercial database management systems (DBMS). The demonstration was convincing but the reasons for its success were not fully analysed. There is a brief account of the results below. In this short contribution, we wish to discuss the reasons for the results. The analysis leads to a strong criticism of all DBMS algorithms based on locking, and based on these results, it is not fanciful to suggest that it is time to re-engineer existing DBMS.
Medizinprodukte sind Gegenstände, Stoffe oder Software mit medizinischer Zweckbestimmung für die Anwendung am Menschen. Diese werden von Medizinprodukteherstellern entwickelt und auf den Markt eingeführt. Da die falsche Anwendung von Medizinprodukten bei Menschen zu Verletzbarkeit des menschlichen Körpers führen kann, ist eine angemessene Qualität der Medizinprodukte zu gewährtleisten. Um die Sicherstellung der Qualität einzuhalten, sind Medizinproduktehersteller verpflichtet, sich an die Medizinprodukteverordnung (MDR) zu halten. Für risikoreiche Produkte ist ergänzend die Nutzung eines Qualitätsmanagementsystems (QMS) verpflichtend. Dieses steuert die Struktur, Verantwortlichkeiten, Verfahren und Prozesse des Unternehmens, die für die Medizinprodukteentwicklung notwendig sind. In Zeiten der Digitalisierung werden Softwarelösungen eingesetzt, um die zeitaufwendigen Dokumentations- und Administrationstätigkeiten im QMS zu reduzieren und die Prozesse zu optimieren. Mit der Einführung einer Software wird ein QMS in der Praxis auch als elektronisches QMS (eQMS) bezeichnet. Weiterhin muss das gesamte QMS mit den Regularien konform sein. Deshalb ist das Ziel dieser Arbeit, mithilfe der regulatorischen Anforderungen herauszuarbeiten, welche Vorgaben bei der Einführung eines eQMS zu beachten sind und wie diese erfüllt werden können. Diese Arbeit bezieht sich auf die regulatorsichen Vorgaben aus der MDR und der ISO 13485. Die Norm beinhaltet Anforderungen an ein QMS von Medizinprodukten.
In this paper, an approach is introduced how reinforcement learning can be used to achieve interoperability between heterogeneous Internet of Things (IoT) components. More specifically, we model an HTTP REST service as a Markov Decision Process and adapt Q-Learning to the properties of REST so that an agent in the role of an HTTP REST client can learn the semantics of the service and, especially an optimal sequence of service calls to achieve an application specific goal. With our approach, we want to open up and facilitate a discussion in the community, as we see the key for achieving interoperability in IoT by the utilization of artificial intelligence techniques.
This study is about estimating the reproducibility of finding palpation points of three different anatomical landmarks in the human body (Xiphoid Process and the 2 Hip Crests) to support a navigated ultrasound application. On 6 test subjects with different body mass index the three palpation points were located five times by two examiners. The deviation from the target position was calculated and correlated to the fat thickness above each palpation point. The reproducibility of the measurements had a mean error of ≈13.5 mm +- 4 mm, which seems to be sufficient for the desired application field.
Medical applications are becoming increasingly important in the current development of health care and therefore a crucial part of the medical industry. The work focuses on the analysis of requirements and the challenges arisen from designing mobile medical applications in relation to the user interface. The paper describes the current status in the development of mobile medical apps and illustrates the development of e-health market. The author will explain the requirements and will illustrate the hurdles and problems. He refers to the German market which is similar to the European and compares that with the market in the USA.
Current data-intensive systems suffer from scalability as they transfer massive amounts of data to the host DBMS to process it there. Novel near-data processing (NDP) DBMS architectures and smart storage can provably reduce the impact of raw data movement. However, transferring the result-set of an NDP operation may increase the data movement, and thus, the performance overhead. In this paper, we introduce a set of in-situ NDP result-set management techniques, such as spilling, materialization, and reuse. Our evaluation indicates a performance improvement of 1.13 × to 400 ×.
Revenue management information systems are very important in the hospitality sector. Revenue decisions can be better prepared based on different information from different information systems and decision strategies. There is a lack of research about the usage of such systems in small and medium-sized hotels and architectural configurations. Our paper empirically shows the current development of revenue information systems. Furthermore, we define future developments and requirements to improve such systems and the architectural base.
In this paper we present our work in progress on revisiting traditional DBMS mechanisms to manage space on native Flash and how it is administered by the DBA. Our observations and initial results show that: the standard logical database structures can be used for physical organization of data on native Flash; at the same time higher DBMS performance is achieved without incurring extra DBA overhead. Initial experimental evaluation indicates a 20% increase in transactional throughput under TPC-C, by performing intelligent data placement on Flash, less erase operations and thus better Flash longevity.
The automation of work by means of disruptive technologies such as Artificial Intelligence (AI) and Robotic Process Automation (RPA) is currently intensely discussed in business practice and academia. Recent studies indicate that many tasks manually conducted by humans today will not in the future. In a similar vein, it is expected that new roles will emerge. The aim of this study is to analyze prospective employment opportunities in the context of RPA in order to foster our understanding of the pivotal qualifications, expertise and skills necessary to find an occupation in a completely changing world of work. This study is based on an explorative, content analysis of 119 job advertisements related to RPA in Germany. The data was collected from major German online job platforms, qualitatively coded, and subsequently analyzed quantitatively. The research indicates that there indeed are employment opportunities, especially in the consulting sector. The positions require different technological expertise such as specific programming languages and knowledge in statistics. The results of this study provide guidance for organizations and individuals on reskilling requirements for future employment. As many of the positions require profound IT expertise, the generally accepted perspective that existing employees affected by automation can be retrained to work in the emerging positions has to be seen extremely critical. This paper contributes to the body of knowledge by providing a novel perspective on the ongoing discussion of employment opportunities, and reskilling demands of the existing workforce in the context of recent technological developments and automation.
Significant advances have been achieved in mobile robot localization and mapping in dynamic environments, however these are mostly incapable of dealing with the physical properties of automotive radar sensors. In this paper we present an accurate and robust solution to this problem, by introducing a memory efficient cluster map representation. Our approach is validated by experiments that took place on a public parking space with pedestrians, moving cars, as well as different parking configurations to provide a challenging dynamic environment. The results prove its ability to reproducibly localize our vehicle within an error margin of below 1% with respect to ground truth using only point based radar targets. A decay process enables our map representation to support local updates.
In this paper, we present a new approach for achieving robust performance of data structures making it easier to reuse the same design for different hardware generations but also for different workloads. To achieve robust performance, the main idea is to strictly separate the data structure design from the actual strategies to execute access operations and adjust the actual execution strategies by means of so-called configurations instead of hard-wiring the execution strategy into the data structure. In our evaluation we demonstrate the benefits of this configuration approach for individual data structures as well as complex OLTP workloads.
RoPose-Real: real world dataset acquisition for data-driven industrial robot arm pose estimation
(2019)
It is necessary to employ smart sensory systems in dynamic and mobile workspaces where industrial robots are mounted on mobile platforms. Such systems should be aware of flexible and non-stationary workspaces and able to react autonomously to changing situations. Building upon our previously presented RoPose-system, which employs a convolutional neural network architecture that has been trained on pure synthetic data to estimate the kinematic chain of an industrial robot arm system, we now present RoPose-Real. RoPose-Real extends the prior system with a comfortable and targetless extrinsic calibration tool, to allow for the production of automatically annotated datasets for real robot systems. Furthermore, we use the novel datasets to train the estimation network with real world data. The extracted pose information is used to automatically estimate the observing sensor pose relative to the robot system. Finally we evaluate the performance of the presented subsystems in a real world robotic scenario.
As production workspaces become more mobile and dynamic it becomes increasingly important to reliably monitor the overall state of the environment. Therein manipulators or other robotic systems likely have to be able to act autonomously together with humans and other systems within a joint workspace. Such interactions require that all components in non-stationary environments are able to perceive the state relative to each other. As vision-sensors provide a rich source of information to accomplish this, we present RoPose, a convolutional neural network (CNN) based approach, to estimate the two dimensional joint configuration of a simulated industrial manipulator from a camera image. This pose information can further be used by a novel targetless calibration setup to estimate the pose of the camera relative to the manipulator’s space. We present a pipeline to automatically generate synthetic training data and conclude with a discussion of the potential usage of the same pipeline to acquire real image datasets of physically existent robots.
Rotating machinery occupies a predominant place in many industrial applications. However, rotating machines are often encountered with severe vibration problems. The measurement of these machines’ vibrations signal is of particular importance since it plays a crucial role in predictive maintenance. When the vibrations are too high, they often cause fatigue failure. They announce an unexpected stop or break and, consequently, a significant loss of productivity or an attack on the personnel’s safety. Therefore, fault identification at early stages will significantly enhance the machine’s health and significantly reduce maintenance costs. Although considerable efforts have been made to master the field of machine diagnostics, the usual signal processing methods still present several drawbacks. This paper examines the rotating machinery condition monitoring in the time and frequency domains. It also provides a framework for the diagnosis process based on machine learning by analyzing the vibratory signals.
Methods based exclusively on heart rate hardly allow to differentiate between physical activity, stress, relaxation, and rest, that is why an additional sensor like activity/movement sensor added for detection and classification. The response of the heart to physical activity, stress, relaxation, and no activity can be very similar. In this study, we can observe the influence of induced stress and analyze which metrics could be considered for its detection. The changes in the Root Mean Square of the Successive Differences provide us with information about physiological changes. A set of measurements collecting the RR intervals was taken. The intervals are used as a parameter to distinguish four different stages. Parameters like skin conductivity or skin temperature were not used because the main aim is to maintain a minimum number of sensors and devices and thereby to increase the wearability in the future.
In recent years, the rise of the digital transformation received significant importance in Business-to-Business (B2B) research. Social media applications provide executives with a raft of new options. Consequently, interfaces to social media platforms have also been integrated into B2B salesforce applications, although very little is as yet known about their usage and general impact on B2B sales performance. This paper evaluates 1) the conceptualization of social media usage in a dyadic B2B relationship; 2) the effects of a more differentiated usage construct on customer satisfaction; 3) antecedents of social media usage on multiple levels; and 4) the effectiveness of social media usage for different types of customers. The framework presented here is tested cross-industry against data collected from dyadic buyer seller relationships in the IT service industry. The results elucidate the preconditions and the impact of social media usage strategies in B2B sales relations.
When forecasting sales figures, not only the sales history but also the future price of a product will influence the sales quantity. At first sight, multivariate time series seem to be the appropriate model for this task. Nontheless, in real life history is not always repeatable, i.e. in the case of sales history there is only one price for a product at a given time. This complicates the design of a multivariate time series. However, for some seasonal or perishable products the price is rather a function of the expiration date than of the sales history. This additional information can help to design a more accurate and causal time series model. The proposed solution uses an univariate time series model but takes the price of a product as a parameter that influences systematically the prediction. The price influence is computed based on historical sales data using correlation analysis and adjustable price ranges to identify products with comparable history. Compared to other techniques this novel approach is easy to compute and allows to preset the price parameter for predictions and simulations. Tests with data from the Data Mining Cup 2012 demonstrate better results than established sophisticated time series methods.
Scenario-based analysis is a comprehensive technique to evaluate software quality and can provide more detailed insights than e.g. maintainability metrics. Since such methods typically require significant manual effort, we designed a lightweight scenario-based evolvability evaluation method. To increase efficiency and to limit assumptions, the method exclusively targets service- and microservice-based systems. Additionally, we implemented web-based tool support for each step. Method and tool were also evaluated with a survey (N=40) that focused on change effort estimation techniques and hands-on interviews (N=7) that focused on usability. Based on the evaluation results, we improved method and tool support further. To increase reuse and transparency, the web-based application as well as all survey and interview artifacts are publicly available on GitHub. In its current state, the tool-supported method is ready for first industry case studies.
Scheduled flexibility and individualization of knowledge transfer in foundations of computer science
(2017)
The opening of the German higher education system for new target groups involves a heterogeneous composition of students as never before and face up the universities to new challenges. Due to different educational biographies, the students don't show a homogeneous level of knowledge. Furthermore, their access to course content and their individual learning methods are very diverse. The existing lack of knowledge and the very unequal study speed have a significant influence on the learning behavior and learning motivation. During the first semesters, the dropout rate is appreciably higher. The reform project gives an overview of a didactic restructuring from a formerly conventional teaching and learning concept to a stronger combination of digital offers, combined with classical lectures in the basic modules of computer science. The teaching content is adjusted to the individual requirements and knowledge. Students with different previous knowledge get the possibility to increase their knowledge in different levels of abstraction. The aim of the reform project has to point out the possibilities, also the challenges of the digital process in higher education. At the same time the question has to be explored, how far does an accompanied and self-directed learning in own speed and in own individual depth of knowledge have a positive impact on the motivation and on the study success of a learner.
What might the attendee be able to do after being in your session?
Our work shows how to connect intra-operative devices via IEEE 11073 Service-oriented Device Connectivity (SDC).
Description of the Problem or Gap
Standardized device communication is essential for interoperability, availability of device data, and therefore for the intelligent operating room (OR) and arising solutions. The SDC standard was developed to make information from medical devices available in a uniform manner and enable interoperability. Existing devices are rarely SDC-capable and need interfaces to be interoperable via SDC.
Methods: What did you do to address the problem or gap?
We conceived an SDC-based architecture consisting of a service provider and service consumer. In our concept, the service provider is connected to the medical device and capable to translate the proprietary protocol of the device into SDC and vice versa. The service consumer is used to request or send information via the SDC protocol to the service provider and can function as a uniform bidirectional interface (e.g. for displaying or controlling). This concept was exemplarily demonstrated with the patient monitor MX800 of Philips to retrieve the device data (e.g. vital parameters) via SDC and partly for the operating light marLED X of KLS Martin Group.
Results: What was the outcome(s) of what you did to address the problem or gap?
The patient monitor MX800 was connected to a Raspberry Pi (RPi) via LAN, on which the service provider is running. The python script on the RPi establishes a connection to the monitor and translates incoming and outgoing messages from the proprietary protocol to SDC and vice versa to/from the service consumer. The service consumer is running on a laptop and acts as a simulation for different kinds of systems that want to get vital parameters or other information from the patient monitor. The operating light marLED X was connected to an RPi via USB-to-RS232. A python script on the RPi establishes a connection to the light and makes it possible via proprietary commands to get information of the light (e.g. status) and to control it (e.g. toggle the light, increment the intensity). A translation to SDC is not integrated yet.
Discussion of Results
Our practical implementation shows that medical devices can be accessed via external connections to get device data and control the device via commands. The example SDC implementation of the patient monitor MX800 makes it possible to request its data via the standardized communication protocol SDC. This is also possible for the operating light marLED X if its proprietary protocol is analyzed to be translatable to/from SDC. This would allow to control the device from an external system, or automatically depending on the status of the ongoing procedure. The advantage is, that existing intra-operative devices can be extended by a service provider which is capable of translating the proprietary protocol of the device in SDC and vice versa. This enables interoperability and an intelligent OR that, for example, is aware of all devices, their status, and data and can use this information to optimally support the surgeons and their team (e.g. provision of information, automated documentation). This interoperability allows that future innovations merely need to understand the SDC protocol instead of all vendor-dependent communication protocols.
Conclusion
Standardized device communication is essential to reach interoperability, and therefore intelligent ORs. Our contribution addresses the possibility of subsequently making medical devices SDC-capable. This may eliminate the need of understanding all the different proprietary protocols when developing new innovative solutions for the OR.
The digital transformation of the automotive industry has a significant impact on how development processes need to be organized in future. Dynamic market and technological environments require capabilities to react on changes and to learn fast. Agile methods are a promising approach to address these needs but they are not tailored to the specific characteristics of the automotive domain like product line development. Although, there have been efforts to apply agile methods in the automotive domain for many years, significant and widespread adoptions have not yet taken place. The goal of this literature review is to gain an overview and a better understanding of agile methods for embedded software development in the automotive domain, especially with respect to product line development. A mapping study was conducted to analyze the relation between agile software development, embedded software development in the automotive domain and software product line development. Three research questions were defined and 68 papers were evaluated. The study shows that agile and product line development approaches tailored for the automotive domain are not yet fully explored in the literature. Especially, literature on the combination of agile and product line development is rare. Most of the examined combinations are customizations of generic approaches or approaches stemming from other domains. Although, only few approaches for combining agile and software product line development in the automotive domain were found, these findings were valuable for identifying research gaps and provide insights into how existing approaches can be combined, extended and tailored to suit the characteristics of the automotive domain.
The need for creating digitally enhanced products, services, and experiences as well as the emergence of new or modified business models has a significant impact on the automotive domain. Innovative solutions and new topics such as Smart Mobility or Connectivity require current automotive development processes to undergo major changes. They need to be redesigned in a way that it is possible to learn and adapt continuously at a fast pace. Agile methods are promising approaches to address these new challenges. However, agile methods are not tailored to the specific characteristics of the automotive domain such as software product line (SPLs) development. Although, there have been efforts to apply agile methods in the automotive domain, widespread adoptions have not yet taken place.
Motivation: Aim of this project is the automatic classification of total hip endoprosthesis (THEP) components in 2D Xray images. Revision surgeries of total hip arthroplasty (THA) are common procedures in orthopedics and trauma surgery. Currently, around 400.000 procedures per year are performed in the United States (US) alone. To achieve the best possible result, preoperative planning is crucial. Especially if parts of the current THEP system are to be retained.
Methods: First, a ground truth based on 76 X-ray images was created: We used an image processing pipeline consisting of a segmentation step performed by a convolutional neural network and a classification step performed by a support vector machine (SVM). In total, 11 classes (5 pans and 6 shafts) shall be classified.
Results: The ground truth generated was of good quality even though the initial segmentation was performed by technicians. The best segmentation results were achieved using a U-net architecture. For classification, SVM architectures performed much better than additional neural networks.
Conclusions: The overall image processing pipeline performed well, but the ground truth needs to be extended to include a broader variability of implant types and more examples per training class.
Die Segmentierung und das Tracking von minimal-invasiven robotergeführten Instrumenten ist ein wesentlicher Bestandteil für verschiedene computer assistierte Eingriffe. Allerdings treten in der minimal-invasiven Chirurgie, die das Anwendungsfeld für den hier beschriebenen Ansatz darstellt, häufig Schwierigkeiten durch Reflexionen, Schatten oder visuelle Verdeckungen durch Rauch und Organe auf und erschweren die Segmentierung und das Tracking der Instrumente.
Dieser Beitrag stellt einen Deep Learning Ansatz für ein markerloses Tracking von minimal-invasiven Instrumenten vor und wird sowohl auf simulierten als auch realen Daten getestet. Es wird ein simulierter als auch realer Datensatz mit Ground Truth Kennzeichnung für die binäre Segmentierung von Instrument und Hintergrund erstellt. Für den simulierten Datensatz werden Bilder aus einem simulierten Instrument und realem Hintergrund zusammengesetzt. Im Falle des realen Datensatzes spricht man von der Zusammensetzung der Bilder aus einem realen Instrument und Hintergrund. Insgesamt wird auf den simulierten Daten eine Pixelgenauigkeit von 94.70 Prozent und auf den realen Daten eine Pixelgenauigkeit von 87.30 Prozent erreicht.
Segmentierung von Polypen in Koloskopie-Bilddaten : eine Potentialanalyse von Deep-Learning-Methoden
(2018)
Kolorektale Karzinome haben eine hohe Sterblichkeitsrate, wenn sie spät entdeckt werden. Eine frühzeitige Entfernung von bösartigen Polypen im Magen-Darm-Trakt, die deren Vorstufen bilden, bietet jedoch hohe Überlebenschancen. Bei Darmspiegelungen werden gerade kleine Polypen aber recht häufig übersehen. Zuverlässige bildverarbeitende Systeme, die Polypen in einem Koloskopie-Frame nicht nur detektieren, sondern pixelgenau segmentieren, könnten Ärzten bei Darmkrebs-Screenings helfen. Diese Arbeit analysiert den aktuellen Stand der Segmentierung von Polypen im Gastrointestinaltrakt. Weiterführend wird untersucht, inwiefern die in letzter Zeit sehr erfolgreichen Methoden des Deep Learning hier Vorteile bieten.
In the present paper we demonstrate the novel technique to apply the recently proposed approach of In-Place Appends – overwrites on Flash without a prior erase operation. IPA can be applied selectively: only to DB-objects that have frequent and relatively small updates. To do so we couple IPA to the concept of NoFTL regions, allowing the DBA to place update-intensive DB-objects into special IPA-enabled regions. The decision about region configuration can be (semi-)automated by an advisor analyzing DB-log files in the background.
We showcase a Shore-MT based prototype of the above approach, operating on real Flash hardware. During the demonstration we allow the users to interact with the system and gain hands-on experience under different demonstration scenarios.
Im präventiven Krisenmanagement geht es um die frühzeitige Erkennung von möglichen, unvorhersehbaren Ereignissen. Hierzu zählen beispielhaft Busunfälle, einstürzende Gebäude und ähnliche Großschadensereignisse. Krisen treten meist unerwartet auf und neigen oftmals aufgrund der knapp bemessenen Handlungszeit zu Fehlentscheidungen. Um dies zu verhindern, dient das präventive Krisenmanagement dazu, sämtliche auftretende Ereignisse mittels einer Simulation zuvor durchzuspielen, um im Falle einer reellen Krise die notwendigen Schritte bestmöglich einzuleiten. Um Simulationen für das Krisenmanagement zu präzisieren und die Ergebnisse effektiv und vereinfacht zu veranschaulichen, ist es notwendig, eine Vorauswahl an vorhandenen Szenarien für Vergleiche heraussuchen zu können. Diese Arbeit entstand im Rahmen des FP-7 EU Projekts CRISMA (Crisis Management) [1] und dient zur Evaluation eines Konzepts zur Vorauswahl geeigneter Szenarien, welche in früheren Simulationen entstanden.
OpenAPI, WADL, RAML, and API Blueprint are popular formats for documenting Web APIs. Although these formats are in general both human and machine-readable, only the part of the format describing the syntax of a Web API is machine-understandable. Descriptions, which explain the meaning and purpose of Web API elements, are embedded as natural language text snippets into documents and target human readers but not machines. To enable machines to read and process these state-of-practice Web API documentation, we propose a Transformer model that solves the generic task of identifying a Web API element within a syntax structure that matches a natural language query. For our first prototype, we focus on the Web API integration task of matching output with input parameters and fined-tuned a pre-trained CodeBERT model to the downstream task of question answering with samples from 2,321 OpenAPI documentation. We formulate the original question answering problem as a multiple choice task: given a semantic natural language description of an output parameter (question) and the syntax of the input schema (paragraph), the model chooses the input parameter (answer) in the schema that best matches the description. The paper describes the data preparation, tokenization, and fine-tuning process as well as discusses possible applications of our model as part of a recommender system. Furthermore, we evaluate the generalizability and the robustness of our fine-tuned model, with the result that it achieves an accuracy of 81.46% correctly chosen parameters.
Semi-automated image data labelling using AprilTags as a pre-processing step for machine learning
(2019)
Data labelling is a pre-processing step to prepare data for machine learning. There are many ways to collect and prepare this data, but these are usually associated with a greater effort. This paper presents an approach to semi-automated image data labelling using AprilTags. The AprilTags attached to the object, which contain a unique ID, make it possible to link the object surfaces to a particular class. This approach will be implemented and used to label data of a stackable box.
The data is evaluated by training a You Only Look Once (YOLO) net, with a subsequent evaluation of the detection results. These results show that the semi-automatically collected and labelled data can certainly be used for machine learning. However, if concise features of an object surface are covered by the AprilTag, there is a risk that the concerned class will not be recognized. It can be assumed that the labelled data can not only be used for YOLO, but also for other machine learning approaches.
Serverless computing is an emerging cloud computing paradigm with the goal of freeing developers from resource management issues. As of today, serverless computing platforms are mainly used to process computations triggered by events or user requests that can be executed independently of each other. These workloads benefit from on-demand and elastic compute resources as well as per-function billing. However, it is still an open research question to which extent parallel applications, which comprise most often complex coordination and communication patterns, can benefit from serverless computing.
In this paper, we introduce serverless skeletons for parallel cloud programming to free developers from both parallelism and resource management issues. In particular, we investigate on the well known and widely used farm skeleton, which supports the implementation of a wide range of applications. To evaluate our concepts, we present a prototypical development and runtime framework and implement two applications based on our framework: Numerical integration and hyperparameter optimization - a commonly applied technique in machine learning. We report on performance measurements for both applications and discuss
the usefulness of our approach.
Diese Arbeit liefert einen Konzeptentwurf, der die Integration verschiedener Systeme mit prozessrelevanten klinischen Diensten gewährleistet. Chirurgische Abläufe werden in Form von Prozessen modelliert. Die Wahl der Notation und die Art der Modellierung dieser Prozesse spielt in der heutigen Forschung in diesem Gebiet eine zentrale Rolle. Sind diese Prozesse modelliert, besteht die Möglichkeit, diese in einer Workflow-Engine automatisiert auszuführen. Im Rahmen der Entwicklung eines Workflow-Managment-Systems stellt sich die Frage, wie die Anbindung dieser Workflow-Engine mit anderen Systemen erfolgen soll. In der Arbeit werden Schnittstellen abstrakt in der Web Services Description Language (WSDL) definiert. Darum werden automatisiert Artefakte erzeugt. Auf der Grundlage dieser Artefakte erfolgt die Integration der Systeme. Die Workflow-Engine kommunizieren über SOAP-Nachrichten (Simple Object Access Protocol) mit den entsprechenden Systemen. Dieser Ansatz wurde mithilfe eines Prototyps validiert und umgesetzt.
Asymmetric read/write storage technologies such as Flash are becoming
a dominant trend in modern database systems. They introduce
hardware characteristics and properties which are fundamentally
different from those of traditional storage technologies such
as HDDs.
Multi-Versioning Database Management Systems (MV-DBMSs)
and Log-based Storage Managers (LbSMs) are concepts that can
effectively address the properties of these storage technologies but
are designed for the characteristics of legacy hardware. A critical
component of MV-DBMSs is the invalidation model: commonly,
transactional timestamps are assigned to the old and the new version,
resulting in two independent (physical) update operations.
Those entail multiple random writes as well as in-place updates,
sub-optimal for new storage technologies both in terms of performance
and endurance. Traditional page-append LbSM approaches
alleviate random writes and immediate in-place updates, hence reducing
the negative impact of Flash read/write asymmetry. Nevertheless,
they entail significant mapping overhead, leading to write
amplification.
In this work we present an approach called Snapshot Isolation
Append Storage Chains (SIAS-Chains) that employs a combination
of multi-versioning, append storage management in tuple granularity
and novel singly-linked (chain-like) version organization.
SIAS-Chains features: simplified buffer management, multi-version
indexing and introduces read/write optimizations to data placement
on modern storage media. SIAS-Chains algorithmically avoids
small in-place updates, caused by in-place invalidation and converts
them into appends. Every modification operation is executed
as an append and recently inserted tuple versions are co-located.
Die Arbeit stellt die Vision des Internet of Things (IoT) vor und betrachtet sowohl Möglichkeiten der Nutzung als auch Gefahrenpotentiale für die Sicherheit der Nutzer. Insbesondere wird hierbei der Anwendungsfall Smart Home näher betrachtet und am Beispiel ZigBee gravierende Schwächen dieser Geräte aufgezeigt.
Das Ziel dieser Arbeit ist, die Infrastruktur einer modernen Fahrzeug-zu Fahrzeug-Kommunikation auf ihre Sicherheit zu prüfen. Dazu werden die Sicherheitsstandards für die Funkkommunikation genauer beschrieben und anschließend mit möglichen Angriffsmodellen geprüft. Mit dem erläuterten Wissen der VANET Architektur werden verschiedene Angriffe verständlicher. Dadurch werden die Schwachstellen offengelegt und Gegenmaßnahmen an passenden Punkten in der Architektur verdeutlicht.
Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans. Systems must be able to recognize and assess human actions in real-time. To train the corresponding data-driven algorithms, a significant amount of annotated training data is required. We demonstrate a pipeline to detect humans, estimate their pose, track them over time and recognize their actions in real-time with standard monocular camera sensors. For action recognition, we transform noisy human pose estimates in an image like format we call Encoded Human Pose Image (EHPI). This encoded information can further be classified using standard methods from the computer vision community. With this simple procedure, we achieve competitive state-of-the-art performance in pose based action detection and can ensure real-time performance. In addition, we show a use case in the context of autonomous driving to demonstrate how such a system can be trained to recognize human actions using simulation data.
A sleep study is a test used to diagnose sleep disorders and is usually done in sleep laboratories. The golden standard for evaluation of sleep is overnight polysomnography (PSG). Unfortunately, in-lab sleep studies are expensive and complex procedures. Furthermore, with a minimum of 22 wire attachments to the patient for sleep recording, this medical procedure is invasive and unfamiliar for the subjects. To solve this problem, low-cost home diagnostic systems, based on noninvasive recording methods requires further researches.
For this intention it is important to find suitable bio vital parameters for classifying sleep phases WAKE, REM, light sleep and deep sleep without any physical impairment at the same time. We decided to analyse body movement (BM), respiration rate (RR) and heart rate variability (HRV) from existing sleep recordings to develop an algorithm which is able to classify the sleep phases automatically. The preliminary results of this project show that BM, RR and HRV are suitable to identify WAKE, REM and NREM stage.
The respiratory rate is a vital sign indicating breathing illness. It is necessary to analyze the mechanical oscillations of the patient's body arising from chest movements. An inappropriate holder on which the sensor is mounted, or an inappropriate sensor position is some of the external factors which should be minimized during signal registration. This paper considers using a non-invasive device placed under the bed mattress and evaluates the respiratory rate. The aim of the work is the development of an accelerometer sensor holder for this system. The normal and deep breathing signals were analyzed, corresponding to the relaxed state and when taking deep breaths. The evaluation criterion for the holder's model is its influence on the patient's respiratory signal amplitude for each state. As a result, we offer a non-invasive system of respiratory rate detection, including the mechanical component providing the most accurate values of mentioned respiratory rate.
To evaluate the quality of a person´s sleep it is essential to identify the sleep stages and their durations. Currently, the gold standard in terms of sleep analysis is overnight polysomnography (PSG), during which several techniques like EEG (eletroencephalogram), EOG (electrooculogram), EMG (electromyogram), ECG (electrocardiogram), SpO2 (blood oxygen saturation) and for example respiratory airflow and respiratory effort are recorded. These expensive and complex procedures, applied in sleep laboratories, are invasive and unfamiliar for the subjects and it is a reason why it might have an impact on the recorded data. These are the main reasons why low-cost home diagnostic systems are likely to be advantageous. Their aim is to reach a larger population by reducing the number of parameters recorded. Nowadays, many wearable devices promise to measure sleep quality using only the ECG and body-movement signals. This work presents an android application developed in order to proof the accuracy of an algorithm published in the sleep literature. The algorithm uses ECG and body movement recordings to estimate sleep stages. The pre-recorded signals fed into the algorithm have been taken from physionet1 online database. The obtained results have been compared with those of the standard method used in PSG. The mean agreement ratios between the sleep stages REM, Wake, NREM-1, NREM-2 and NREM-3 were 38.1%, 14%, 16%, 75% and 54.3%.
Smart meter based business models for the electricity sector : a systematical literature research
(2017)
The Act on the Digitization of the Energy Transition forces German industries and households to introduce smart meters in order to save engery, to gain individual based electricity tariffs and to digitize the energy data flow. Smart meter can be regarded as the advancement of the traditional meter. Utilizing this new technology enables a wide range of innovative business models that provide additional value for the electricity suppliers as well as for their customers. In this study, we followed a two-step approach. At first, we provide a state-of-the-art comparison of these business models found in the literature and identify structural differences in the way they add value to the offered products and services. Secondly, the business models are grouped into categories with respect to customer segmetns and the added value to the smart grid. Findings indicate that most business models focus on the end-costumer as their main customer.
Although still in the early stages of diffusion, smartwatches represent the most popular type of wearable devices. Yet, little is known why some people are more likely to adopt smartwatches than others. To deepen the understanding of underlying factors prompting adoption behavior, the authors develop a theoretical model grounded in technology acceptance and social psychology literature. Empirical results reveal perceived usefulness and visibility as important factors that drive intention. The magnitude of these antecedents is influenced by an individual’s perception of viewing smartwatches as a technology and/or as a fashion accessory. Theoretical and managerial implications are discussed.
Der vorliegende Artikel beleuchtet die grundsätzlichen Möglichkeiten der Integration von Funktionalitäten der sozialen Medien in Unternehmen. Darauf aufbauend wird Social Commerce als zentraler Gegenstand der Unternehmensführung hergeleitet. Dabei stehen der kundenseitige Kaufprozess und dessen Schnittstellen zu Kommunikationsinstrumenten des Social Webs im Vordergrund. Gezeigt wird die Beeinflussung des individuellen Kaufprozesses durch Social Media. Diese Wirkungsdynamiken sind nachfolgend die Grundlage für die Deskription von möglichen strategischen Einsatzfeldern und Bereichen des Social Commerce in der Unternehmensführung.
Die Simulation menschlichen Gruppenverhaltens kann bei der Kapazitäten-, Risiko- und Evakuierungs Planung von Gebäuden hilfreich sein, bei der Produktion von Filmen für eindrucksvolle Massen-Szenen eingesetzt werden oder virtuelle Schauplätze in Echtzeit-Anwendungen beleben. Die Herausforderungen liegen vor allem in einem realistischen Erscheinungsbild der virtuellen Crowd, glaubwürdigem Verhalten innerhalb eines sozialen Verbundes, realitätsnahen Animationen und der Wahrung der Echtzeitfähigkeit interaktiver Anwendungen. Im Rahmen dieser Arbeit wird der aktuelle Stand der Technik vorgestellt, Technologien evaluiert und ein Crowd Simulation Prototyp mit der Unity Engine implementiert.
In recent years, the rise of social media received significant importance in marketing research and practice. Consequently, interfaces to social media platforms have also been integrated into Business-to-Business (B2B) salesforce applications, although very little is as yet known about their usage and general impact on B2B sales performance. This paper evaluates 1) the conceptualization of social media usage in dyadic B2B relationships; 2) the effects of a more differentiated usage construct on customer satisfaction; 3) antecedents of social media usage on multiple levels; and 4) the effectiveness of social media usage for different types of cus-tomers. The framework presented here is tested cross-industry against data collected from dyadic buyer-seller relationships in the IT service industry. The results elucidate the precondi-tions and the impact of social media usage strategies in B2B sales relations.
Social media usage in business-to-business sales : conceptualization, antecedents, and outcomes
(2015)
In recent years, the rise of social media received significant importance in marketing research. Social media applications now provide executives with a raft of new options. Consequently, interfaces to social media platforms have also been integrated into Business to-Business (B2B) salesforce applications, although very little is as yet known about their usage and general impact on B2B sales performance. This paper evaluates 1) the conceptualization of social media usage in a dyadic B2B relationship; 2) the effects of a more differentiated usage construct on customer satisfaction; 3) antecedents of social media usage on multiple levels; and 4) the effectiveness of social media usage for different types of customers. The framework presented here is tested cross-industry against data collected from dyadic buyer seller relationships in the IT service industry. The results elucidate the preconditions and the impact of social media usage strategies in B2B sales relations.
Business process models provide a considerable number of benefits for enterprises and organizations, but the creation of such models is costly and time-consuming, which slows down the organizational adoption of business process modeling. Social paradigms pave new ways for business process modeling by integrating stakeholders and leveraging knowledge sources. However, empirical research about the impact of social paradigms on costs of business process modeling is sparse. A better understanding of their impact could help to reduce the cost of business process modeling and improve decision-making on BPM activities. The paper constributes to this field by reporting about an empirical investigation via survey research on the perceived influence of different cost factors among experts. Our results indicate that different cost components, as well as the use of social paradigms, influence cost.
Modern enterprises reshape and transform continuously by a multitude of management processes with different perspectives. They range from business process management to IT service management and the management of the information systems. Enterprise Architecture (EA) management seeks to provide such a perspective and to align the diverse management perspectives. Therefore, EA management cannot rely on hierarchic - in a tayloristic manner designed - management processes to achieve and promote this alignment. It, conversely, has to apply bottom-up, information-centered coordination mechanisms to ensure that different management processes are aligned with each other and enterprise strategy. Social software provides such a bottom-up mechanism for providing support within EAM-processes. Consequently, challenges of EA management processes are investigated, and contributions of social software presented. A cockpit provides interactive functions and visualization methods to cope with this complexity and enable the practical use of social software in enterprise architecture management processes.