Ja
Refine
Year of publication
- 2019 (160) (remove)
Document Type
- Journal article (63)
- Conference proceeding (52)
- Book chapter (22)
- Book (13)
- Doctoral Thesis (3)
- Report (3)
- Issue of a journal (2)
- Anthology (1)
- Working Paper (1)
Is part of the Bibliography
- yes (160)
Institute
- ESB Business School (73)
- Informatik (45)
- Life Sciences (18)
- Technik (13)
- Texoversum (9)
Publisher
- Hochschule Reutlingen (47)
- Elsevier (13)
- Universitätsbibliothek Tübingen (9)
- Deutsche Gesellschaft für Computer- und Roboterassistierte Chirurgie e.V. (7)
- Stellenbosch University (7)
- MDPI (6)
- MIM, Marken-Institut München (6)
- De Gruyter (5)
- Fac. of Organization & Informatics, Univ. of Zagreb (4)
- ACS (2)
The aim of this paper is to show to what extent Artificial Intelligence can be used to optimize forecasting capability in procurement as well as to compare AI with traditional statistic methods. At the same time this article presents the status quo of the research project ANIMATE. The project applies Artificial Intelligence to forecast customer orders in medium-sized companies.
Precise forecasts are essential for companies. For planning, decision making and controlling. Forecasts are applied, e.g. in the areas of supply chain, production or purchasing. Medium-sized companies have major challenges in using suitable methods to improve their forecasting ability.
Companies often use proven methods such as classical statistics as the ARIMA algorithm. However, simple statistics often fail while applied for complex non-linear predictions.
Initial results show that even a simple MLP ANN produces better results than traditional statistic methods. Furthermore, a baseline (Implicit Sales Expectation) of the company was used to compare the performance. This comparison also shows that the proposed AI method is superior.
Until the developed method becomes part of corporate practice, it must be further optimized. The model has difficulties with strong declines, for example due to holidays. The authors are certain that the model can be further improved. For example, through more advanced methods, such as a FilterNet, but also through more data, such as external data on holiday periods.
Ever since the 1980s, researchers in computer science and robotics have been working on making autonomous cars. Due to recent breakthroughs in research and devel- opment, such as the Bertha Benz Project [ZBS+14], the goal of fully autonomous vehicles seems closer than ever before. Yet a lot of questions remain unanswered. Especially now that the automotive industry moves towards autonomous systems in series production vehicles, the task of precise localization has to be solved with automotive grade sensors and keep memory and processing consumption at a mini- mum. This thesis investigates the Simultaneous Localization and Mapping (SLAM) prob- lem for autonomous driving scenarios on a parking lot using low cost automotive sensors. The main focus is herby devoted to the RAdio Detection And Ranging (RADAR) sensor, which has not been widely analyzed in an autonomous driving scenario so far, even though they are abundant in the automotive industry for ap- plications such as Adaptive Cruise Control (ACC). Due to the high noise floor, the radar sensor has widely been disregarded in the Intelligent Transportation Systems and Robotics communities with regards to SLAM applications. However in this thesis, it is shown that the RADAR sensor proves to be an affordable, robust and precise sensor, when modeling its physical properties correctly. In this regard, a GraphSLAM based framework is introduced, which extracts features from the RADAR sensor and generates an optimized map of the surroundings using the RADAR sensor alone. This framework is used to enable crowd based localization, which is not limited to the RADAR sensor alone. By integrating an automotive Light Detection and Ranging (LiDAR) and stereo camera sensor, a robust and precise localization system can be built that that is suitable for autonomous driving even in complex parking lot scenarios. It it is thereby shown that the RADAR sensor is strongly contributing to obtaining good results in a sensor fusion setup. These results were obtained on an extensive dataset on a parking lot, which has been recorded over the course of several months. It contains different weather conditions, different configurations of parked cars and a multitude of different trajectories to validate the approaches described in this thesis and to come to the conclusion that the RADAR sensor is a reliable sensor in series autonomous driving systems, both in a multi sensor framework and as a single component for localization.
The digital age makes it possible to be globally networked at any time. Digital communication is therefore an important aspect of today’s world. Hence, the further development and expansion of this is becoming increasingly important. Even within a wireless system, copper channels are important as part of the overall network. Given the need to keep pushing at the current limitations, careful design of the cables in connection with an adapted coding of the bits is essential to transmit more and more data.
One of the most popular and widespread cabling technologies is symmetrical copper cabling [1, pp. 8-15]. It is also known as Twisted Pair and it is of immense importance for the cabling of communication networks.
At the time of writing this thesis, data rates of up to 10 GBit/s over a transmission distance of 100 m and 40 GBit/s over a transmission distance of 30 m are standardized for symmetrical copper cabling [2]. Other lengths are not standardized. Short lengths in particular are of great interest for copper cables, because copper cables are usually used for short distances, such as between computers and the campus network or within data centres.
This work has focused on the transmission of higher order Pulse Amplitude Modulation and the associated transmission performance. The central research question is:“how well can we optimize the transmission technique in order to be able to maximise the data bandwidth over Ethernet cable and, given that remote powering is also a significant application of these cables, how much will the resulting heating affect this transmission and what can be done to mitigate that?”
To answer this question, the cable parameters are first examined. A series of spectral measurements, such as Insertion Loss, Return Loss, Near End Crosstalk and Far End Crosstalk, provide information about the electromagnetic interference and the influence of the ohmic resistance on the signal. Based on these findings, the first theoretical statements and calculations can be made. In the next step, data transmissions over different transmission lengths are realized. The examination of the eye diagrams of the different transmission approaches ultimately provides information about the signal quality of the transmissions. An overview of the maximum transmission rate depending on the transmission distance shows the potential for different applications.
Furthermore, the simultaneous transmission of energy and data is a significant advantage of copper. However, the resulting heat development has an influence on the data transmission. Therefore, the influence of the ambient temperature of cables is investigated in the last part and changes in the signal quality are clarified.
Frost reduction in mechanical balanced ventilation by efficient means of preheating cold supply air
(2019)
This study has focused on evaluating the financial potential of wastewater and geothermal heat recovery systems in a multi-family building. The recovered heat was used to improve the performance of mechanical ventilation with heat recovery (MVHR) system during the coldest days in central Sweden. The main issue, which was targeted with these solutions, was to reduce frost formation in the system and hence increase its thermal efficiency. By looking at the life cycle cost over a lifespan of 20 years, the observed systems were being evaluated economically. Furthermore, statistical analyses were carried-out to counter the uncertainty that comes with the calculation. It was found that the studied wastewater systems have a high possibility of generating savings in this period, while the one fed by geothermal energy is less likely to compensate for its high initial cost. All designed systems however, managed to reduce operational cost by 35-45% due to lower energy usage.
Digitalization changes the manufacturing dramatically. In regard of employees’ demands, global trends and the technological vision of future factories, automotive manufacturing faces a huge number of diverse challenges. Currently, research focuses on technological aspects of future factories in terms of digitalization. New ways of work and new organizational models for future factories have not been described yet. There are assumptions on how to develop the organization of work in a future factory but up to now, literature shows deficits in scientifically substantiated answers in this research area. Consequently, the objective of this paper is to present an approach on a work organization design for automotive Industry 4.0 manufacturing. Future requirements were analyzed and deducted to criteria that determine future agile organization design. These criteria were then transformed into functional mechanisms, which define the approach for shopfloor organization design
Der Halo-Effekt im Fußball
(2019)
Der Halo-Effekt ist eine aus der Sozialpsychologie bekannte kognitive Verzerrung. Ein Halo-Effekt tritt dann auf, wenn ein globaler Eindruck oder eine Information über ein hervorstechendes Merkmal die Beurteilung anderer Eigenschaften prägt. Im vorliegenden Beitrag wird der Frage nachgegangen: Gibt es einen Halo-Effekt im Fußball? Überstrahlt der sportliche Erfolg bzw. Misserfolg die Wahrnehmung der Fans womöglich sogar hinsichtlich nicht-sportlicher Aspekte? Der Beitrag gibt den aktuellen Stand zur Halo-Forschung wider und präsentiert die Ergebnisse einer empirischen Untersuchung, in deren Rahmen Fans von Vereinen aus der deutschen Fußball-Bundesliga befragt werden.
Dieser Bericht fasst die wesentlichen Arbeiten und Ergebnisse zusammen, die in dem Verbundvorhaben „GalvanoFlex_BW“ im Kalenderjahr 2018 durchgeführt und erzielt wurden. Dazu lässt sich zunächst sagen, dass die Messwertaufnahme und –auswertung abgeschlossen ist. Es wurden verschiedene Messkampagnen bei der Fa. NovoPlan durchgeführt. Bei C&C Bark konnte man teilweise auf bestehende Daten zurückgreifen, die punktuell durch weitere Messungen ergänzt wurden. Bei der Fa. Hartchrom konnten aufgrund von Personalmangel keine Messungen durchgeführt werden. Die aufgenommenen Daten wurden in eine Effizienzbewertung überführt, aus der im Folgenden allgemeine Aussagen abgeleitet werden sollen. Dazu ist ein Simulationsprogramm aufgesetzt worden, das in der Lage ist, Prozessketten energetisch abzubilden und zu optimieren. Zudem sollen aus den Messdaten verbesserte Profile für den Wärmebedarf in den Unternehmen entwickelt werden, die daraufhin der KWK-Optimierung zur Verfügung gestellt werden. Im Zuge der Entwicklung und Bewertung stromoptimierter KWK- Strategien ist ein bestehendes Simulationsmodell entsprechend weiterentwickelt worden. Konkret wurde das Modell um eine verbesserte Lastprognose für Strom und Wärme für Industriebetriebe ergänzt, und das Optimierungsverfahren wurde um eine zweite Dimension erweitert. Während bislang allein die Optimierung der Eigenstromdeckung mit einer Begrenzung der BHKW-Starts als Nebenbedingung möglich war, ist jetzt die Kappung der elektrischen Lastspitze zusätzlich in der Zielfunktion integriert. Gerade bei Industrieunternehmen lässt sich auf diese Weise eine weitere, zum Teil nicht unerhebliche Energiekosteneinsparung erreichen, was durch die ersten Berechnungen anhand der drei im Reallabor vertretenden Betriebe bestätigt wird. Die Ergebnisse werden unter AP 8 (Umsetzung) diskutiert. Der Dialog mit weiteren Unternehmen und Institutionen außerhalb des Vorhabens konnte über die Branchenplattfom weitergeführt werden. In 2018 wurden zwei Veranstaltungen dieser Art durchgeführt, und im Frühjahr 2019 wird ein weiterer Workshop zu diesem Thema durchgeführt. Die sozialwissenschaftliche Begleitforschung wurde mit der zweiten Phase der Firmenbefragungen ebenfalls planmäßig weitergeführt. Mit Blick auf die Umsetzung eines BHKW-Konzeptes haben sich dabei zwei wichtige Punkte wie folgt gezeigt: Zum einen muss die umsetzende Firma eine gewisse „Energieeffizienz-Reife“ besitzen, die sich u.a. in der Erfahrung bei der Durchführung von Energieeffizienzmaßnahmen zeigt, da die Installation eines BHKWs eine äußerst komplexe Maßnahme darstellt. Zum anderen müssen andere unternehmensspezifische Kontextfaktoren hinzukommen, wie z.B. aus anderen Gründen durchzuführende bauliche Maßnahmen, so dass gewisse zeitliche Entscheidungsfenster entstehen, in denen die Umsetzung von KWK-Maßnahmen sinnvoll sind.
In Folge der gegenwärtigen Digitalisierung in der produzierenden Industrie werden Anwendungen oder Services mit potentiell positiven Auswirkungen auf Faktoren wie Effektivität und Arbeitsqualität entwickelt. Ein geeigneter Ansatz zur Stärkung motivierender Aspekte im Arbeitskontext kann Gamification darstellen. In dieser Arbeit ist die initiale Konzeption und Evaluation eines Gamification-Ansatzes für Anwender eines KI-Service zur Maschinenoptimierung dargestellt und möglichen Anforderungen an ein Konzept zur Motivationssteigerung extrahiert.
In dieser Ausarbeitung wird eine zeitliche Vorhersage von Erdbeben getroffen. Hierfür werden mit einem Datensatz aus Labor-Erdbeben Convolutional Neural Networks (CNN) trainiert. Die trainierten Netzwerke geben Vorhersagen, indem sie einen Input an seismischen Daten klassifizieren. Durch das Klassifizieren kann das CNN die zeitliche Entfernung zum nächsten Erdbeben vorhersagen. Es werden hierfür zwei Ansätze miteinander verglichen. Beim ersten Ansatz werden die Originaldaten in ein CNN gegeben. Beim zweiten Ansatz wird vor dem CNN eine Vorverarbeitung der Daten mit den Mel Frequency Cepstral Coefficients (MFCC) durchgeführt. Es zeigt sich, dass mit beiden Ansätzen eine gute Klassifikation möglich ist. Die Kombination aus MFCC und CNN liefert die besseren quantitativen Ergebnisse. Hierbei konnte eine Genauigkeit von 65 % erreicht werden.
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.
Bereits zum elften Mal findet nun die Studierendenkonferenz Informatics Inside statt. Als Teil des Masterstudiengangs Human-Centered Computing organisieren Masterstudierende selbständig eine vollumfängliche wissenschaftliche Konferenz. Die Informatik ist nach wie vor ständigem Wandel unterworfen. Unsere Studierenden tragen diesem Wandel bei, indem sie in ihrer wissenschaftllichen Vertiefung aktuelle Problemstellungen durch innovative Konzepte lösen. Inzwischen ist die Informatik aber auch nicht immer sofort sichtbar. Das merken wir immer dann, wenn etwas nicht wie vorgesehen funktioniert. Das diesjährige Motto der Informatics Inside ist experience (IT);, verdeckt als Funktionsaufruf:).
Anders als Digital-ICs, die hochautomatisiert entworfen werden können, ist der Entwurf analoger ICs bis heute Handarbeit. Übliche auf Optimierung basierende Automatisierungsverfahren scheitern. Die Ursachen wurden jetzt in einem Forschungsprojekt untersucht, um neue Ansätze zur Entwurfsautomatisierung analoger ICs abzuleiten.
Additive manufacturing is a key technology which applies the ideas of Industry 4.0 in order to enable the production of personalized and highly customized products economically. Especially small and medium sized companies often lack the competence and experience to evaluate objectively and profoundly the potential of additive manufacturing technologies in small and medium sized companies. Furthermore, the method has been validated in a small medical technology company evaluating the additive manufacturing potential of an existing surgery tool.
The Eleventh International Conference on Advances in Databases, Knowledge, and Data Applications (DBKDA 2019), held between June 02, 2019 to June 06, 2019 - Athens, Greece, continued a series of international events covering a large spectrum of topics related to advances in fundamentals on databases, evolution of relation between databases and other domains, data base technologies and content processing, as well as specifics in applications domains databases.
Advances in different technologies and domains related to databases triggered substantial improvements for content processing, information indexing, and data, process and knowledge mining. The push came from Web services, artificial intelligence, and agent technologies, as well as from the generalization of the XML adoption.
High-speed communications and computations, large storage capacities, and loadbalancing for distributed databases access allow new approaches for content processing with incomplete patterns, advanced ranking algorithms and advanced indexing methods.
Evolution on e-business, ehealth and telemedicine, bioinformatics, finance and marketing, geographical positioning systems put pressure on database communities to push the ‘de facto’ methods to support new requirements in terms of scalability, privacy, performance, indexing, and heterogeneity of both content and technology.
We welcomed academic, research and industry contributions. The conference had the followingtracks:
Knowledgeanddecisionbase
Databasestechnologies
Datamanagement
GraphSM: Large-scale Graph Analysis, Management and Applications
The desire to combine advanced user friendly interfaces with a product personality communicating environmental friendliness to customers poses new challenges for car interior designers, as little research has been carried out in this field to date. In this paper, the creation of three personas aimed at defining key German car users with pro environmental behaviour is presented. After collecting ethnographic data of potential drivers through literature review, information about generation and Euro car segment led to the definition of three key user groups. The resulting personas were applied to determine the most important interaction points in car interior. Finally, present design cues of eco-friendly product personality developed in the field of automotive design were explored. Our work presents three strategic directions for the design development of future in-car user interfaces named as a) foster multimodal mobility; b) emphasize the interlinkage economy - sustainable driving; and c) highlight new technological developments. The presented results are meant as an impulse for developers to fit the needs of green customers and drivers when designing user-friendly HMI components.
Creativity, problem-solving skills and the ability for collaborative work are considered key competences for facing the challenges of the 21st century. Children are born with an inherent creativity that decreases throughout their school careers. A research team of designers and educators investigates whether the implementation of Design Thinking (DT) in textile education in German elementary schools is a suitable method to preserve children’s creativity. Initial surveys with teachers and pilot studies in elementary schools showed high motivation and openmindedness towards DT in classroom. The challenge will be to develop suitable teaching modules for elementary schools of the federal state Baden Württemberg.
Kreativität, Problemlösekompetenz und kollaboratives Arbeiten werden in zahlreichen internationalen Studien sowie von der OECD (2017) als Schlüsselkompetenzen des 21. Jahrhunderts definiert. Ungeachtet dessen orientieren sich viele Lehr-Lern Methoden noch immer an der Vermittlung vordefinierter Lösungswege. Studien im Sekundarbereich in den USA, Deutschland und Asien zeigen, dass Design Thinking durch seine kreativen und kollaborativen Elemente zu einem nachhaltigeren Lernerfolg bei Lernenden und seitens der Lehrenden zu höherer Zufriedenheit bei der Vermittlung der Inhalte führen kann.
Kernelemente des Design Thinking sind: der iterative Prozess mit seinen Phasen Verstehen, Beobachten, Sichtweisen definieren, Ideen finden, Prototypen bauen, Testen; die Arbeit in multidisziplinären Teams sowie die Nutzerorientierung bei der Definition der Aufgabe (Brown, 2009). Die Phasen des iterativen Prozesses weisen eine hohe Kongruenz mit den prozessorientierten Kompetenzen des Faches Kunst/Werken und des Sachunterrichts gemäß dem Bildungsplan für Grundschulen (Ministerium für Kultus, Jugend und Sport Baden Württemberg, 2016) auf. Im Rahmen eines interdisziplinären Promotionsvorhabens an der PH Freiburg soll, basierend auf einem qualitativen Forschungsdesign, untersucht werden, inwieweit sich Design Thinking eignet, Kreativität, Problemlösekompetenz und kollaboratives Arbeiten von Grundschulkindern in Kunst/Werken und im Sachunterricht aus Sicht von Lehrpersonen zu fördern. Vorstudien mit Lehrpersonen und Ausbildungslehrkräften, bei welchen Erhebungen per Fragebogen nach Teilnahme an einem Design Thinking Workshop eingesetzt wurden, sowie zwei Pilotunterrichtseinheiten an Grundschulen mit Teilnehmender Beobachtung, Experteninterviews und Kinderinterviews in Kleingruppen, zeigen erste Ergebnisse.
Small and Medium Enterprises (SMEs) which play substantial role in the development of any economy have been on the rise in the recent periods. Consequently, these enterprises are faced with a myriad of challenges which could potentially be solved through adoption of technology. Nonetheless, it has been observed that the new technological uptake among SMEs remains limited with the majority of them opting to maintain the status quo with regards to technology awareness and innovation strategies.
In a literature review, this paper explores three major dynamics curtailing adoption of new technologies by SMEs in the manufacturing: Knowledge absorptive capacity and management factors, organisational structures as well as technological awareness. Firstly, with regards to knowledge absorptive capacity and management factors, this study shows how these factors drive innovation potentials in SMEs.
Secondly, with regards to technological awareness factors, this study documents how perceived usefulness, costs, network and infrastructure, education and skills, training and attitude as well as knowledge influence adoption of new technologies among SMEs in the world. Lastly, the study concludes by analysing how organisational structures drive innovation potentials of SMEs in the wake of swift and profound technological changes in the market.