Refine
Year of publication
Document Type
- Conference Proceeding (120) (remove)
Language
- English (120) (remove)
Has Fulltext
- yes (120)
Is part of the Bibliography
- no (120)
Keywords
- Mikroservice (8)
- Serviceorientierte Architektur (7)
- Agilität <Management> (6)
- Energiemanagement (6)
- Agile Softwareentwicklung (5)
- Insurance Industry (5)
- Versicherungswirtschaft (5)
- COVID-19 (4)
- Computersicherheit (4)
- Concreteness (4)
- Digitalisierung (4)
- Energieeffizienz (4)
- Rechnernetz (4)
- SOA (4)
- Semantik (4)
- Text Mining (4)
- energy management (4)
- Agile methods (3)
- Angewandte Botanik (3)
- Cloud Computing (3)
- Complex Event Processing (3)
- Computersimulation (3)
- Erkennungssoftware (3)
- Gepresste Pflanzen (3)
- German (3)
- Gießerei (3)
- Herbar Digital (3)
- Herbarium (3)
- Information Retrieval (3)
- Informationsmanagement (3)
- Klassifikation (3)
- Microservices (3)
- Nachhaltigkeit (3)
- OCR (3)
- PROFInet (3)
- Recognition software (3)
- Telearbeit (3)
- Virtualisierung (3)
- Visualisierung (3)
- foundry (3)
- microservices (3)
- Agile software development (2)
- Benutzererlebnis (2)
- Benutzeroberfläche (2)
- Big Data (2)
- Consistency (2)
- Contract Analysis (2)
- Deutsch (2)
- Disambiguation (2)
- Distributional Semantics (2)
- Elektrospinnen (2)
- Energieeinsparung (2)
- Ethernet (2)
- Ganzzahlige lineare Optimierung (2)
- Industrie 4.0 (2)
- Information Visualization (2)
- Konkretum <Linguistik> (2)
- Kulturerbe (2)
- Künstliche Intelligenz (2)
- Machine Learning (2)
- Microservice (2)
- Microservices Architecture (2)
- Molecular switches (2)
- Network Security (2)
- Neuronales Netz (2)
- Open Access (2)
- PROFINET Security (2)
- Rechtswissenschaften (2)
- Resiliency (2)
- Sachtext (2)
- Semantic Web (2)
- Simulation (2)
- Sprachnorm (2)
- Triazole (2)
- Urban Logistics (2)
- User Interfaces (2)
- Vergleich (2)
- Wikibase (2)
- Wikidata (2)
- XML (2)
- agile methods (2)
- agile software development (2)
- batch-wise parallel process (2)
- dwell-time (2)
- eduscrum (2)
- energy efficiency (2)
- linear integer programming (2)
- optimal scheduling (2)
- remote work (2)
- soft constraint (2)
- technical energy management (2)
- Ähnlichkeit (2)
- 2D data processing (1)
- 3D data (1)
- 3d mapping (1)
- 4-day work week (1)
- API (1)
- Abbreviations (1)
- Abkürzung (1)
- Ablaufplanung (1)
- Absolvent (1)
- Acronyms (1)
- Adaptive IT Infrastructure (1)
- Agent <Informatik> (1)
- Agile Manifesto (1)
- Agile Practices (1)
- Agile Software Development (1)
- Agile education (1)
- Agile method (1)
- Agile practices (1)
- Air quality (1)
- Akronym (1)
- Algorithmus (1)
- Alternative work schedule (1)
- Ambiguität (1)
- Anergy (1)
- Annotation (1)
- Anomalieerkennung (1)
- Anomaly detection (1)
- Anonymization (1)
- Application Programming Interface (1)
- Arbeitsablauf (1)
- Arbeitswelt (1)
- Arbeitszufriedenheit (1)
- Articial intelligence (1)
- Asymmetric encryption (1)
- Attack detection (1)
- Ausbildung (1)
- Auswahl (1)
- Authentication (1)
- Authentifikation (1)
- Authorization (1)
- Automation (1)
- AutomationML (1)
- Automatische Klassifikation (1)
- Automatische Sprachanalyse (1)
- Automatisierungssystem (1)
- Autorisierung (1)
- Azyklischer gerichteter Graph (1)
- BaaS (Backend-as-a-service) (1)
- Bahnplanung (1)
- Batteriefahrzeug (1)
- Battery Electric Vehicles (1)
- Beruf (1)
- Bibliothek (1)
- Big Data Analytics (1)
- Bilderkennung (1)
- Bildersprache (1)
- Bildersuchmaschine (1)
- Bildmaterial (1)
- Bildverarbeitung (1)
- Biokunststoff (1)
- Blackboard Pattern (1)
- Book of Abstract (1)
- Bring Your Own Device (1)
- C-SPARQL (1)
- CI/CD (1)
- CQL (1)
- Case Management (1)
- Chargenbetrieb (1)
- Chatbot (1)
- Choreography (1)
- Citizens (1)
- City-Logistik (1)
- Classification (1)
- Codegenerierung (1)
- Codierung (1)
- Composite materials (1)
- Computer simulation (1)
- Computerlinguistik (1)
- Constructive Alignment (1)
- Consumerization (1)
- Context Awareness (1)
- Corporate Credit Risk (1)
- Corpus construction (1)
- Crowdshipping (1)
- Cyberattacke (1)
- Data Cubes (1)
- Data Management (1)
- Data Science (1)
- Data Sharing (1)
- Data handling (1)
- Data-Warehouse-Konzept (1)
- Datenaufbereitung (1)
- Datenerfassung (1)
- Datenstrom (1)
- Datenwürfel (1)
- Decision Support (1)
- Decision Support Systems, Clinical (1)
- Decision Support Tool (1)
- Deep Convolutional Networks (1)
- Design Science (1)
- Designwissenschaft <Informatik> (1)
- DevOps (1)
- Dewey-Dezimalklassifikation (1)
- Didactic (1)
- Dienstgüte (1)
- Digital Wellbeing (1)
- Digital storage (1)
- Digitalization (1)
- Digitization (1)
- Dimension 2 (1)
- Disambiguierung (1)
- District Heating (1)
- Docker (1)
- Dokumentanalyse (1)
- Domain Driven Design (DDD) (1)
- Drehkolbenverdichter (1)
- Dynamic identification (1)
- Dynamic modelling (1)
- Dynamische Modellierung (1)
- E-Grocery (1)
- E-Learning (1)
- EPN (1)
- Education (1)
- Eilzustellung (1)
- Eindringerkennung (1)
- Electrospinning (1)
- Elektromobilität (1)
- Empfehlungssystem (1)
- Enduser Device (1)
- Energieerzeugung (1)
- Energieverbrauch (1)
- Entscheidungsunterstützungssystem (1)
- Evaluation (1)
- Event Processing Network (1)
- Event Processing Network Model (1)
- Exergie (1)
- Exergy (1)
- Explainable anomaly detection (1)
- FHIR (1)
- FaaS (Function-as-a-service) (1)
- Fachsprache (1)
- Fassung (1)
- Feature and Text Extraction (1)
- Fernunterricht (1)
- Fernwärmeversorgung (1)
- Figurative Language (1)
- Finite-Elemente-Methode (1)
- Flachheitsbasierte Vorsteuerung (1)
- Flexible Struktur (1)
- Focus Group (1)
- Forschungsdaten (1)
- Framework (1)
- Framework <Informatik> (1)
- Function as a Service (1)
- GECCO: German Corona Consensus Data Set (1)
- Gemischt-ganzzahlige Optimierung (1)
- Genetic algorithms (1)
- Genetischer Algorithmus (1)
- Geschlechtsunterschied (1)
- Gesundheitsfürsorge (1)
- Gesundheitsinformationssystem (1)
- Graph-based Text Representations (1)
- Graphische Benutzeroberfläche (1)
- Gruppeninterview (1)
- Hadoop (1)
- Health IT (1)
- Health Information Interoperability (1)
- Heat Pump (1)
- Home Care (1)
- Hybrid Conference (1)
- ICS Security (1)
- ISO 9001 (1)
- IT security (1)
- Image Recognition (1)
- Image Retrieval (1)
- Imagery (1)
- Images (1)
- Indicator Measurement (1)
- Industrial Security (1)
- Industrial robots (1)
- Industrieroboter (1)
- Industry 4.0 (1)
- Information Dissemination (1)
- Information Extraction (1)
- Information Management (1)
- Information Science (1)
- Informationsmodellierung (1)
- Informationstechnik (1)
- Intelligent control (1)
- Intelligentes Stromnetz (1)
- Internet der Dinge (1)
- Interoperabilität (1)
- Istio (1)
- Keyword Extraction (1)
- Kinematic calibration (1)
- Kinematik (1)
- Knowledge Life Cycle (1)
- Knowledge Maps (1)
- Kommunikation (1)
- Kompakkt (1)
- Kontextbezogenes System (1)
- Korpus <Linguistik> (1)
- Krankenhaus (1)
- Krankenunterlagen (1)
- Kreditrisiko (1)
- Kryptologie (1)
- Kubernetes (1)
- LIG (1)
- LOINC (1)
- LSTM (1)
- Latent Semantic Analysis (1)
- Layout Detection (1)
- Lean Management (1)
- Lebensmittel (1)
- Legal Documents (1)
- Legal Writings (1)
- Legende <Bild> (1)
- Leistungskennzahl (1)
- Leistungssteigerung (1)
- Lemmatization (1)
- Lernmotivation (1)
- Lexical Semantics (1)
- Lieferservice (1)
- Linear Indexed Grammars (1)
- Linked Data (1)
- Linked Open Data (1)
- Literaturbericht (1)
- Liver Transplantation (1)
- Low Exergy Heat Net (1)
- Luftqualität (1)
- MIMOS II (1)
- MapReduce (1)
- Markov Models (1)
- Maschinelles Lernen (1)
- Masterstudium (1)
- Mathematisches Modell (1)
- Media Didactic Concept (1)
- Medical Coding (1)
- Mediendidaktik (1)
- Medizin (1)
- Medizinische Bibliothek (1)
- Messwerterfassung (1)
- Mikro-Kraft-Wärme-Kopplung (1)
- Mischanlage (1)
- Mobile (1)
- Mobile Device Management (1)
- Modellprädiktive Regelung (1)
- Motivation (1)
- Multidimensional Analysis (1)
- Multidimensional analysis (1)
- Mössbauer (1)
- Mößbauer-Spektrometer (1)
- Mößbauer-Spektroskopie (1)
- NFDI (1)
- NFDI4Culture – Konsortium für Forschungsdaten materieller und immaterieller Kulturgüter (1)
- NLP (1)
- NMPC (1)
- Neural controls (1)
- Neural networks (1)
- Neural-network models (1)
- Nichtlineare modellprädiktive Regelung (1)
- Nierentransplantation (1)
- Normality model (1)
- Notation <Klassifikation> (1)
- OPC UA (1)
- OT Security (1)
- Online-Trajektoriengenerierung (1)
- Open Repositories (1)
- Open Science (1)
- Open Source (1)
- OpenRefine (1)
- OpenStack (1)
- Optimale Kontrolle (1)
- Orchestration (1)
- PDF <Dateiformat> (1)
- PDF Document Analysis (1)
- POS Tagging (1)
- PageRank (1)
- Paket (1)
- Paraphrase (1)
- Paraphrase Similarity (1)
- Path accuracy (1)
- Patient empowerment (1)
- Personennahverkehr (1)
- Phraseologie (1)
- Physics (1)
- Physik (1)
- Polymere (1)
- Polymers (1)
- Portable Micro-CHP Unit (1)
- Pregel (1)
- Privacy by Design (1)
- Problemorientiertes Lernen (1)
- Processes (1)
- Produktionsprozess (1)
- Projektmanagement (1)
- Prozessmanagement (1)
- Prozessoptimierung (1)
- Prüfstand (1)
- Pseudonymization (1)
- QM (1)
- Quality Control (1)
- Quality Management (1)
- Quality assessment (1)
- Quality of Service (1)
- Qualität (1)
- Qualitätskontrolle (1)
- Qualitätsmanagement (1)
- REST <Informatik> (1)
- RESTful (1)
- RFID (1)
- Recommender System (1)
- Reduction of Complexity (1)
- Reference Architecture (1)
- Referenzmodell (1)
- Regalbediengerät (1)
- Regalförderzeug (1)
- Regional Development (1)
- Regional Innovation Systems (1)
- Regional Policy (1)
- Remote work (1)
- Repository <Informatik> (1)
- Representational State Transfer (1)
- Requirements engineering (1)
- Resilienz (1)
- Richardson Maturity Model (1)
- Rissausbreitung (1)
- Robotics (1)
- Robotik (1)
- RuleCore (1)
- SCO (1)
- SOA co-existence (1)
- Sakura Science Program (1)
- Schlagwortkatalog (1)
- Schlagwortnormdatei (1)
- Schwarmintelligenz (1)
- Scientific image search (1)
- Scrum <Vorgehensmodell> (1)
- Secure communication (1)
- Security (1)
- Security Knowledge (1)
- Security Ontology (1)
- Selbstgesteuertes Lernen (1)
- Self-directed Learning (1)
- Semantic Web Technologies (1)
- Semantics (1)
- Semantisches Datenmodell (1)
- Serverless Computing (1)
- Service Mesh (1)
- Service Orientation (1)
- Service-orientation (1)
- Shortest Path (1)
- Signal processing (1)
- Signalverarbeitung (1)
- Similarity Measures (1)
- Simulation Modeling (1)
- Situation Awareness (1)
- Smart Buildings (1)
- Smart Grid (1)
- Smart Society (1)
- Society 5.0 (1)
- Software Architecture (1)
- Softwarearchitektur (1)
- Softwareentwicklung (1)
- Softwarewerkzeug (1)
- Spannungsintensitätsfaktor (1)
- Spin crossover (1)
- Standardised formulation (1)
- Statistical Methods (1)
- Statistische Methoden (1)
- Straßenverkehr (1)
- Structural Analysis (1)
- Supply Chain Management (1)
- Supply Chains (1)
- Sustainable development (1)
- Swarm Intelligence (1)
- Systems Librarian, Data Librarian, Job advertisement analysis, Job profiles, New competencies (1)
- Taxonomie (1)
- Techno-Economic Analysis (1)
- Terminologie (1)
- Terminology (1)
- Territorial Intelligence (1)
- Tertiary study (1)
- Tertiärbereich (1)
- Test Bench (1)
- Text Similarity (1)
- Text annotation (1)
- Textbooks (1)
- Thermal Storage (1)
- Thesaurus (1)
- Thin film (1)
- Title Matching (1)
- Transmission measurement setup (1)
- Transplantatabstoßung (1)
- Triazole complexes (1)
- Twitter <Softwareplattform> (1)
- Twitter analysis (1)
- Umweltbilanz (1)
- Unternehmen (1)
- User Generated Content (1)
- Verbal Idioms (1)
- Verbundwerkstoff (1)
- Versicherungsbetrieb (1)
- Versicherungsvertrag (1)
- Verteiltes System (1)
- Vertrag (1)
- Vertragsklausel (1)
- Verweilzeit (1)
- Videospiel (1)
- Viertagewoche (1)
- Virtuelle Realität (1)
- Virtuelles Laboratorium (1)
- Visualization (1)
- Waveguides (1)
- Wellenleiter (1)
- Wikimedia Commons (1)
- Wikipedia categories (1)
- Wind power plant (1)
- Windkraftwerk (1)
- Wissenschaftliche Bibliothek (1)
- Word Counting (1)
- Word Norms (1)
- Workflow (1)
- Wort (1)
- Wärmepumpe (1)
- Wärmespeicher (1)
- Wärmeübertragung (1)
- XML-Model (1)
- XML-Schema (1)
- Zeitreihe (1)
- Zweiwortsatz (1)
- abstractness (1)
- aerospace engineering (1)
- agent-based simulation (1)
- aggregation server (1)
- agile education (1)
- application (1)
- attributional LCA (1)
- bio-based plastics (1)
- biocomposites (1)
- build automation (1)
- build server (1)
- class room (1)
- code generation (1)
- combined heat and power (1)
- concreteness (1)
- consequential LCA (1)
- constraint pushing (1)
- context vectors (1)
- covid 19 (1)
- crack propagation rate (1)
- credit risk (1)
- cultural heritage (1)
- cyber security (1)
- data mapping (1)
- data stream processing (1)
- data warehouse (1)
- digital twins (1)
- distance learning (1)
- distributed systems (1)
- distributional semantics (1)
- dynamic programming (1)
- dynamic trajectories (1)
- e-mobility (1)
- eLearning (1)
- eco-design (1)
- eduDScloud (1)
- education (1)
- energy data (1)
- energy data information model (1)
- energy information model (1)
- energy monitoring (1)
- energy profiles (1)
- fall prediction (1)
- fall prevention (1)
- fall risk (1)
- finite element method (1)
- flatness-based control (1)
- flexible structure (1)
- game analysis (1)
- gender (1)
- generic interface (1)
- graduate (1)
- graft rejection (1)
- graphical user interface (1)
- hemp (1)
- high-quality Learning Formats (1)
- image processing (1)
- increasing continuous differentiability (1)
- industrial production process (1)
- information extraction (1)
- information modeling (1)
- information system (1)
- integrated passenger and freight transport (1)
- interoperability (1)
- key performance indicators (1)
- kidney transplant (1)
- library and information science (1)
- lidar (1)
- life-cycle-assessment (1)
- linked data (1)
- literature review (1)
- matrix calulations (1)
- measurement data acquisition (1)
- mixed-integer programming (1)
- model predictive control (1)
- moving average filter (1)
- natural fiber (1)
- neural network model (1)
- online trajectory generation (1)
- openEHR (1)
- pmCHP (1)
- point clouds (1)
- prediction methods (1)
- private cloud (1)
- problem based learning (1)
- professional life (1)
- real-time application (1)
- recommender systems (1)
- research data management (1)
- research information (1)
- rural transport simulation (1)
- scaling (1)
- scheduling (1)
- security (1)
- security protocol extensions (1)
- semantic knowledge (1)
- semistructured interview (1)
- sensor-based assessment (1)
- sentiment dictionaries (1)
- serverless architecture (1)
- serverless functions (1)
- service models (1)
- service-orientation (1)
- situation-awareness (1)
- smart buildings (1)
- standardized semantics (1)
- stereo vision (1)
- stress intensity factor (1)
- supervised machine learning (1)
- survey (1)
- sustainability (1)
- system integration (1)
- systematic literature review (1)
- taxonomy (1)
- text mining (1)
- thesauri (1)
- time-series forecast (1)
- tool evaluation (1)
- user experience (1)
- user generated content (1)
- virtual distance teaching (1)
- virtual lab (1)
- virtual reality (1)
- visual delegates (1)
- visual perception (1)
- wearable sensors (1)
- web crawling (1)
- word embedding space (1)
- work satisfaction (1)
- work-life balance (1)
- working life (1)
- workload decomposition (1)
- Öffentliche Bibliothek (1)
- Überwachtes Lernen (1)
This paper presents a possibility to extend the formalism of linear indexed grammars. The extension is based on the use of tuples of pushdowns instead of one pushdown to store indices during a derivation. If a restriction on the accessibility of the pushdowns is used, it can be shown that the resulting formalisms give rise to a hierarchy of languages that is equivalent with a hierarchy defined by Weir. For this equivalence, that was already known for a slightly different formalism, this paper gives a new proof. Since all languages of Weir's hierarchy are known to be mildly context sensitive, the proposed extensions of LIGs become comparable with extensions of tree adjoining grammars and head grammars.
Autonomous mobile six-legged robots are able to demonstrate the potential of intelligent control systems based on recurrent neural networks. The robots evaluate only two forward and two backward looking infrared sensor signals. Fast converging genetic training algorithms are applied to train the robots to move straight in six directions. The robots performed successfully within an obstacle environment and there could be observed a never trained useful interaction between each of the single robots. The paper describes the robot systems and presents the test results. Video clips are downloadable under www.inform.fh-hannover.de/download/lechner.php. Held on IFAC International Conference on Intelligent Control Systems and Signal Processing (ICONS 2003, April 2003, Portugal).
All of us are aware of the changes in the information field during the last years. We all see the paradigm shift coming up and have some idea how it will challenge our profession in the future. But how the road to excellence - in education of information specialists in the future - will look like? There are different models (new and old ones) for reorganising the structure of education: * Integration * Specialisation * Step-by step-model * Modul System * Network System / Combination model The paper will present the actual level of discussion on building up a new curriculum at the Department of Information and Communication (IK) at the FH Hannover. Based on the mission statement of the department »Education of information professionals is a part of the dynamic evolution of knowledge society« the direction of change and the main goals will be presented. The different reorganisation models will be explained with its objectives, opportunities and forms of implementation. Some examples will show the ideas and tools for a first draft of a reconstruction plan to become fit for the future. This talk has been held at the German-Dutch University Conference »Information Specialists for the 21st Century« at the Fachhochschule Hannover - University of Applied Sciences, Department of Information and Communication, October 14 -15, 1999 in Hannover, Germany.
Our research project, "Rationalizing the virtualization of botanical document material and their usage by process optimization and automation (Herbar-Digital)" started on July 1, 2007 and will last until 2012. Its long-term aim is the digitization of the more than 3,5 million specimens in the Berlin Herbarium. The University of Applied Sciences and Arts in Hannover collaborates with the department of Biodiversity Informatics at the BGBM (Botanic Garden and Botanical Museum Berlin-Dahlem) headed by Walter Berendsohn. The part of Herbar-Digital here presented deals with the analysis of the generated high resolution images (10,400 lines x 7,500 pixel).
The methods developed in the research project "Herbar Digital" are to help plant taxonomists to master the great amount of material of about 3.5 million dried plants on paper sheets belonging to the Botanic Museum Berlin in Germany. Frequently the collector of the plant is unknown. So a procedure had to be developed in order to determine the writer of the handwriting on the sheet. In the present work the static character is transformed into a dynamic form. This is done with the model of an inert ball which is rolled through the written character. During this off-line writer recognition, different mathematical procedures are used such as the reproduction of the write line of individual characters by Legendre polynomials. When only one character is used, a recognition rate of about 40% is obtained. By combining multiple characters, the recognition rate rises considerably and reaches 98.7% with 13 characters and 93 writers (chosen randomly from the international IAM-database [3]). Another approach tries to identify the writer by handwritten words. The word is cut out and transformed into a 6-dimensional time series and compared e.g. by means of DTW-methods. A global statistical approach using the whole handwritten sentences results in a similar recognition rate of more than 98%. By combining the methods, a recognition rate of 99.5% is achieved.
The research project "Herbar Digital" was started in 2007 with the aim to digitize 3.5 million dried plants on paper sheets belonging to the Botanic Museum Berlin in Germany. Frequently the collector of the plant is unknown, so a procedure had to be developed in order to determine the writer of the handwriting on the sheet. In the present work the static character was transformed into a dynamic form. This was done with the model of an inert ball which was rolled along the written character. During this off-line writer recognition, different mathematical procedures were used such as the reproduction of the write line of individual characters by Legendre polynomials. When only one character was used, a recognition rate of about 40% was obtained. By combining multiple characters, the recognition rate rose considerably and reached 98.7% with 13 characters and 93 writers (chosen randomly from the international IAM-database [3]). A global statistical approach using the whole handwritten text resulted in a similar recognition rate. By combining local and global methods, a recognition rate of 99.5% was achieved.
The automated transfer of flight logbook information from aircrafts into aircraft maintenance systems leads to reduced ground and maintenance time and is thus desirable from an economical point of view. Until recently, flight logbooks have not been managed electronically in aircrafts or at least the data transfer from aircraft to ground maintenance system has been executed manually. Latest aircraft types such as the Airbus A380 or the Boeing 787 do support an electronic logbook and thus make an automated transfer possible. A generic flight logbook transfer system must deal with different data formats on the input side – due to different aircraft makes and models – as well as different, distributed aircraft maintenance systems for different airlines as aircraft operators. This article contributes the concept and top level distributed system architecture of such a generic system for automated flight log data transfer. It has been developed within a joint industry and applied research project. The architecture has already been successfully evaluated in a prototypical implementation.
Automatic classification of scientific records using the German Subject Heading Authority File (SWD)
(2012)
The following paper deals with an automatic text classification method which does not require training documents. For this method the German Subject Heading Authority File (SWD), provided by the linked data service of the German National Library is used. Recently the SWD was enriched with notations of the Dewey Decimal Classification (DDC). In consequence it became possible to utilize the subject headings as textual representations for the notations of the DDC. Basically, we we derive the classification of a text from the classification of the words in the text given by the thesaurus. The method was tested by classifying 3826 OAI-Records from 7 different repositories. Mean reciprocal rank and recall were chosen as evaluation measure. Direct comparison to a machine learning method has shown that this method is definitely competitive. Thus we can conclude that the enriched version of the SWD provides high quality information with a broad coverage for classification of German scientific articles.
In recent years, multiple efforts for reducing energy usage have been proposed. Especially buildings offer high potentials for energy savings. In this paper, we present a novel approach for intelligent energy control that combines a simple infrastructure using low cost sensors with the reasoning capabilities of Complex Event Processing. The key issues of the approach are a sophisticated semantic domain model and a multi-staged event processing architecture leading to an intelligent, situation-aware energy management system.
In huge warehouses or stockrooms, it is often very difficult to find a certain item, because it has been misplaced and is therefore not at its assumed position. This position paper presents an approach on how to coordinate mobile RFID agents using a blackboard architecture based on Complex Event Processing.
Regional Innovation Systems describe the relations between actors, structures and infrastructures in a region in order to stimulate innovation and regional development. For these systems the collection and organization of information is crucial. In the present paper we investigate the possibilities to extract information from websites of companies. First we describe regional innovation systems and the information types that are necessary to create them. Then we discuss the possibilities of text mining and keyword extraction techniques to extract this information from company websites. Finally, we describe a small scale experiment in which keywords related to economic sectors and commodities are extracted from the websites of over 200 companies. This experiment shows what the main challenges are for information extraction from websites for regional innovation systems.
Complications may occur after a liver transplantation, therefore proper monitoring and care in the post-operation phase plays a very important role. Sometimes, monitoring and care for patients from abroad is difficult due to a variety of reasons, e.g., different care facilities. The objective of our research for this paper is to design, implement and evaluate a home monitoring and decision support infrastructure for international children who underwent liver transplant operation. A point-of-care device and the PedsQL questionnaire were used in patients’ home environment for measuring the blood parameters and assessing quality of life. By using a tablet PC and a specially developed software, the measured results were able to be transmitted to the health care providers via internet. So far, the developed infrastructure has been evaluated with four international patients/families transferring 38 records of blood test. The evaluation showed that the home monitoring and decision support infrastructure is technically feasible and is able to give timely alarm in case of abnormal situation as well as may increase parent’s feeling of safety for their children.
Fall events and their severe consequences represent not only a threatening problem for the affected individual, but also cause a significant burden for health care systems. Our research work aims to elucidate some of the prospects and problems of current sensor-based fall risk assessment approaches. Selected results of a questionnaire-based survey given to experts during topical workshops at international conferences are presented. The majority of domain experts confirmed that fall risk assessment could potentially be valuable for the community and that prediction is deemed possible, though limited. We conclude with a discussion of practical issues concerning adequate outcome parameters for clinical studies and data sharing within the research community. All participants agreed that sensor-based fall risk assessment is a promising and valuable approach, but that more prospective clinical studies with clearly defined outcome measures are necessary.
Complex Event Processing (CEP) has been established as a well-suited software technology for processing high-frequent data streams. However, intelligent stream based systems must integrate stream data with semantical background knowledge. In this work, we investigate different approaches on integrating stream data and semantic domain knowledge. In particular, we discuss from a software engineering per- spective two different architectures: an approach adding an ontology access mechanism to a common Continuous Query Language (CQL) is compared with C-SPARQL, a streaming extension of the RDF query language SPARQL.
Regional knowledge map is a tool recently demanded by some actors in an institutional level to help regional policy and innovation in a territory. Besides, knowledge maps facilitate the interaction between the actors of a territory and the collective learning. This paper reports the work in progress of a research project which objective is to define a methodology to efficiently design territorial knowledge maps, by extracting information of big volumes of data contained in diverse sources of information related to a region. Knowledge maps facilitate management of the intellectual capital in organisations. This paper investigates the value to apply this tool to a territorial region to manage the structures, infrastructures and the resources to enable regional innovation and regional development. Their design involves the identification of information sources that are required to find which knowledge is located in a territory, which actors are involved in innovation, and which is the context to develop this innovation (structures, infrastructures, resources and social capital). This paper summarizes the theoretical background and framework for the design of a methodology for the construction of knowledge maps, and gives an overview of the main challenges for the design of regional knowledge maps.
BYOD Bring Your Own Device
(2013)
Using modern devices like smartphones and tablets offers a wide variety of advantages; this has made them very popular as consumer devices in private life. Using them in the workplace is also popular. However, who wants to carry around and handle two devices; one for personal use, and one for work-related tasks? That is why “dual use”, using one single device for private and business applications, may represent a proper solution. The result is “Bring Your Own Device,” or BYOD, which describes the circumstance in which users make their own personal devices available for company use. For companies, this brings some opportunities and risks. We describe and discuss organizational issues, technical approaches, and solutions.
This paper describes the approach of the Hochschule Hannover to the SemEval 2013 Task Evaluating Phrasal Semantics. In order to compare a single word with a two word phrase we compute various distributional similarities, among which a new similarity measure, based on Jensen-Shannon Divergence with a correction for frequency effects. The classification is done by a support vector machine that uses all similarities as features. The approach turned out to be the most successful one in the task.
Research information, i.e., data about research projects, organisations, researchers or research outputs such as publications or patents, is spread across the web, usually residing in institutional and personal web pages or in semi-open databases and information systems. While there exists a wealth of unstructured information, structured data is limited and often exposed following proprietary or less-established schemas and interfaces. Therefore, a holistic and consistent view on research information across organisational and national boundaries is not feasible. On the other hand, web crawling and information extraction techniques have matured throughout the last decade, allowing for automated approaches of harvesting, extracting and consolidating research information into a more coherent knowledge graph. In this work, we give an overview of the current state of the art in research information sharing on the web and present initial ideas towards a more holistic approach for boot-strapping research information from available web sources.
The technical, environmental and economic potential of hemp fines as a natural filler in bioplastics to produce biocomposites is the subject of this study – giving a holistic overview. Hemp fines are an agricultural by-product of the hemp fibres and shives production. Shives and fibres are for example used in the paper, animal bedding or composite area. About 15 to 20 wt.-% per kg hemp straw results in hemp fines after processing. In 2010 about 11,439 metric tons of hemp fines were produced in Europe. Hemp fines are an inhomogeneous material which includes hemp dust, shives and fibre. For these examinations the hemp fines are sieved in a further step with a tumbler sieving machine to obtain more specified fractions. The untreated hemp fines (ex work) as well as the sieved fractions are combined with a polylactide polymer (PLA) using a co-rotating twin screw extruder to produce biocomposites with different hemp fine content. By using an injection moulding machine standard test bars are produced to conduct several material tests. The Young’s modulus is increased and the impact strength reduced by hemp fines. With a content of above 15 wt.-% hemp fines are also improving the environmental (global warming potential) and economic performance in comparison to pure PLA.
The dependency of word similarity in vector space models on the frequency of words has been noted in a few studies, but has received very little attention. We study the influence of word frequency in a set of 10 000 randomly selected word pairs for a number of different combinations of feature weighting schemes and similarity measures. We find that the similarity of word pairs for all methods, except for the one using singular value decomposition to reduce the dimensionality of the feature space, is determined to a large extent by the frequency of the words. In a binary classification task of pairs of synonyms and unrelated words we find that for all similarity measures the results can be improved when we correct for the frequency bias.
In distributional semantics words are represented by aggregated context features. The similarity of words can be computed by comparing their feature vectors. Thus, we can predict whether two words are synonymous or similar with respect to some other semantic relation. We will show on six different datasets of pairs of similar and non-similar words that a supervised learning algorithm on feature vectors representing pairs of words outperforms cosine similarity between vectors representing single words. We compared different methods to construct a feature vector representing a pair of words. We show that simple methods like pairwise addition or multiplication give better results than a recently proposed method that combines different types of features. The semantic relation we consider is relatedness of terms in thesauri for intellectual document classification. Thus our findings can directly be applied for the maintenance and extension of such thesauri. To the best of our knowledge this relation was not considered before in the field of distributional semantics.
Smart Cities require reliable means for managing installations that offer essential services to the citizens. In this paper we focus on the problem of evacuation of smart buildings in case of emergencies. In particular, we present an abstract architecture for situation-aware evacuation guidance systems in smart buildings, describe its key modules in detail, and provide some concrete examples of its structure and dynamics.
Editorial for the 15th European Networked Knowledge Organization Systems Workshop (NKOS 2016)
(2016)
Knowledge Organization Systems (KOS), in the form of classification systems, thesauri, lexical databases, ontologies, and taxonomies, play a crucial role in digital information management and applications generally. Carrying semantics in a well-controlled and documented way, Knowledge Organisation Systems serve a variety of important functions: tools for representation and indexing of information and documents, knowledge-based support to information searchers, semantic road maps to domains and disciplines, communication tool by providing conceptual framework, and conceptual basis for knowledge based systems, e.g. automated classification systems. New networked KOS (NKOS) services and applications are emerging, and we have reached a stage where many KOS standards exist and the integration of linked services is no longer just a future scenario. This editorial describes the workshop outline and overview of presented papers at the 15th European Networked Knowledge Organization Systems Workshop (NKOS 2016) in Hannover, Germany.
Integrating distributional and lexical information for semantic classification of words using MRMF
(2016)
Semantic classification of words using distributional features is usually based on the semantic similarity of words. We show on two different datasets that a trained classifier using the distributional features directly gives better results. We use Support Vector Machines (SVM) and Multirelational Matrix Factorization (MRMF) to train classifiers. Both give similar results. However, MRMF, that was not used for semantic classification with distributional features before, can easily be extended with more matrices containing more information from different sources on the same problem. We demonstrate the effectiveness of the novel approach by including information from WordNet. Thus we show, that MRMF provides an interesting approach for building semantic classifiers that (1) gives better results than unsupervised approaches based on vector similarity, (2) gives similar results as other supervised methods and (3) can naturally be extended with other sources of information in order to improve the results.
The CogALex-V Shared Task provides two datasets that consists of pairs of words along with a classification of their semantic relation. The dataset for the first task distinguishes only between related and unrelated, while the second data set distinguishes several types of semantic relations. A number of recent papers propose to construct a feature vector that represents a pair of words by applying a pairwise simple operation to all elements of the feature vector. Subsequently, the pairs can be classified by training any classification algorithm on these vectors. In the present paper we apply this method to the provided datasets. We see that the results are not better than from the given simple baseline. We conclude that the results of the investigated method are strongly depended on the type of data to which it is applied.
Discovery and efficient reuse of technology pictures using Wikimedia infrastructures. A proposal
(2016)
Multimedia objects, especially images and figures, are essential for the visualization and interpretation of research findings. The distribution and reuse of these scientific objects is significantly improved under open access conditions, for instance in Wikipedia articles, in research literature, as well as in education and knowledge dissemination, where licensing of images often represents a serious barrier.
Whereas scientific publications are retrievable through library portals or other online search services due to standardized indices there is no targeted retrieval and access to the accompanying images and figures yet. Consequently there is a great demand to develop standardized indexing methods for these multimedia open access objects in order to improve the accessibility to this material.
With our proposal, we hope to serve a broad audience which looks up a scientific or technical term in a web search portal first. Until now, this audience has little chance to find an openly accessible and reusable image narrowly matching their search term on first try - frustratingly so, even if there is in fact such an image included in some open access article.
Industrial Control Systems (ICS) succumb to an ever evolving variety of threats. Additionally, threats are increasing in number and get more complex. This requires a holistic and up-to-date security concept for ICS as a whole. Usually security concepts are applied and updated based on regularly performed ICS security assessments. Such ICS security assessments require high effort and extensive knowledge about ICS and its security. This is often a problem for small and mediumsized enterprises (SME), which do not have sufficient respective sufficiently skilled human resources. This paper defines in a first step requirements on the knowledge needed to perform an ICS security assessment and the life cycle of this knowledge. Afterwards the ICS security knowledge and its life cycle are developed and discussed considering the requirements and related work.
Nowadays, smartphones and sensor devices can provide a variety of information about a user’s current situation. So far, many recommender systems neglect this kind of information and thus cannot provide situationspecific recommendations. Situation-aware recommender systems adapt to changes in the user’s environment and therefore are able to offer recommendations that are more appropriate for the current situation. In this paper, we present a software architecture that enables situation awareness for arbitrary recommendation techniques. The proposed system considers both (semi-)static user profiles and volatile situational knowledge to obtain meaningful recommendations. Furthermore, the implementation of the architecture in a museum of natural history is presented, which uses Complex Event Processing to achieve situation awareness.
The amount of papers published yearly increases since decades. Libraries need to make these resources accessible and available with classification being an important aspect and part of this process. This paper analyzes prerequisites and possibilities of automatic classification of medical literature. We explain the selection, preprocessing and analysis of data consisting of catalogue datasets from the library of the Hanover Medical School, Lower Saxony, Germany. In the present study, 19,348 documents, represented by notations of library classification systems such as e.g. the Dewey Decimal Classification (DDC), were classified into 514 different classes from the National Library of Medicine (NLM) classification system. The algorithm used was k-nearest-neighbours (kNN). A correct classification rate of 55.7% could be achieved. To the best of our knowledge, this is not only the first research conducted towards the use of the NLM classification in automatic classification but also the first approach that exclusively considers already assigned notations from other
classification systems for this purpose.
Editorial for the 17th European Networked Knowledge Organization Systems Workshop (NKOS 2017)
(2017)
Knowledge Organization Systems (KOS), in the form of classification systems, thesauri, lexical databases, ontologies, and taxonomies, play a crucial role in digital information management and applications generally. Carrying semantics in a well-controlled and documented way, Knowledge Organization Systems serve a variety of important functions: tools for representation and indexing of information and documents, knowledge-based support to information searchers, semantic road maps to domains and disciplines, communication tool by providing conceptual framework, and conceptual basis for knowledge based systems, e.g. automated classification systems. New networked KOS (NKOS) services and applications are emerging, and we have reached a stage where many KOS standards exist and the integration of linked services is no longer just a future scenario. This editorial describes the workshop outline and overview of presented papers at the 17th European Networked Knowledge Organization Systems Workshop (NKOS 2017) which was held during the TPDL 2017 Conference in Thessaloniki, Greece.
During the transition from conventional towards purely electrical, sustainable mobility, transitional technologies play a major part in the task of increasing adaption rates and decreasing range anxiety. Developing new concepts to meet this challenge requires adaptive test benches, which can easily be modified e.g. when progressing from one stage of development to the next, but also meet certain sustainability demands themselves.
The system architecture presented in this paper is built around a service-oriented software layer, connecting a modular hardware layer for direct access to sensors and actuators to an extensible set of client tools. Providing flexibility, serviceability and ease of use, while maintaining a high level of reusability for its constituent components and providing features to reduce the required overall run time of the test benches, it can effectively decrease the CO2 emissions of the test bench while increasing its sustainability and efficiency.
This paper presents a cascaded methodology for enhancing the path accuracy of industrial robots by using advanced control schemes. It includes kinematic calibration as well as dynamic modeling and identification. This is followed by a centralized model-based compensation of robot dynamics. The implemented feed-forward torque control shows the expected improvements of control accuracy. However, external measurements show the influence of joint elasticities as systematic path errors. To further increase the accuracy an iterative learning controller (ILC) based on external camera measurements is designed. The implementation yields to significant improvements of path accuracy. By means of a kind of automated ”Teach-In”, an overall effective concept for the automated calibration and optimization of the accuracy of industrial robots in high-dynamic path-applications is realized.
NOA is a search engine for scientific images from open access publications based on full text indexing of all text referring to the images and filtering for disciplines and image type. Images will be annotated with Wikipedia categories for better discoverability and for uploading to WikiCommons. Currently we have indexed approximately 2,7 Million images from over 710 000 scientific papers from all fields of science.
Scientific papers from all disciplines contain many abbreviations and acronyms. In many cases these acronyms are ambiguous. We present a method to choose the contextual correct definition of an acronym that does not require training for each acronym and thus can be applied to a large number of different acronyms with only few instances. We constructed a set of 19,954 examples of 4,365 ambiguous acronyms from image captions in scientific papers along with their contextually correct definition from different domains. We learn word embeddings for all words in the corpus and compare the averaged context vector of the words in the expansion of an acronym with the weighted average vector of the words in the context of the acronym. We show that this method clearly outperforms (classical) cosine similarity. Furthermore, we show that word embeddings learned from a 1 billion word corpus of scientific exts outperform word embeddings learned from much larger general corpora.
The reuse of scientific raw data is a key demand of Open Science. In the project NOA we foster reuse of scientific images by collecting and uploading them to Wikimedia Commons. In this paper we present a text-based annotation method that proposes Wikipedia categories for open access images. The assigned categories can be used for image retrieval or to upload images to Wikimedia Commons. The annotation basically consists of two phases: extracting salient keywords and mapping these keywords to categories. The results are evaluated on a small record of open access images that were manually annotated.
Against the background of climate change and finite fossil resources, bio-based plastics have been in the focus of research for the last decade and were identified as a promising alternative to fossil-based plastics. Now, with an evolving bio-based plastic market and application range, the environmental advantages of bio-based plastic have come to the fore and identified as crucial by different stakeholders. While the majority of assessments for bio-based plastics are carried out based on attributional life cycle assessment, there have been only few consequential studies done in this area. Also, the application of eco-design strategies has not been in the focus for the bio-based products due to the prevailing misconceptions of renewable materials (as feedstock for bio-based plastics) considered in itself as an ‘eco-design strategy’. In this paper, we discuss the life cycle assessment as well as eco-design strategies of a bio-based product taking attributional as well as consequential approaches into account.
This paper deals with new job profiles in libraries, mainly systems librarians (German: Systembibliothekare), IT librarians (German: IT-Bibliothekare) and data librarians (German: Datenbibliothekare). It investigates the vacancies and requirements of these positions in the German-speaking countries by analyzing one hundred and fifty published job advertisements of OpenBiblioJobs between 2012-2016. In addition, the distribution of positions, institutional bearers, different job titles as well as time limits, scope of work and remuneration of the positions are evaluated. The analysis of the remuneration in the public sector in Germany also provides information on demands for a bachelor's or master's degree.
The average annual increase in job vacancies between 2012 and 2016 is 14.19%, confirming the need and necessity of these professional library profiles.
The higher remuneration of the positions in data management, in comparison to the systems librarian, proves the prerequisite of the master's degree and thus indicates a desideratum due to missing or few master's degree courses. Accordingly, the range of bachelor's degree courses (or IT-oriented major areas of study with optional compulsory modules in existing bachelor's degree courses) for systems and IT librarians must be further expanded. An alternative could also be modular education programs for librarians and information scientists with professional experience, as it is already the case for music librarians.
In the context of modern mobility, topics such as smart-cities, Car2Car-Communication, extensive vehicle sensor-data, e-mobility and charging point management systems have to be considered. These topics of modern mobility often have in common that they are characterized by complex and extensive data situations. Vehicle position data, sensor data or vehicle communication data must be preprocessed, aggregated and analyzed. In many cases, the data is interdependent. For example, the vehicle position data of electric vehicles and surrounding charging points have a dependence on one another and characterize a competition situation between the vehicles. In the case of Car2Car-Communication, the positions of the vehicles must also be viewed in relation to each other. The data are dependent on each other and will influence the ability to establish a communication. This dependency can provoke very complex and large data situations, which can no longer be treated efficiently. With this work, a model is presented in order to be able to map such typical data situations with a strong dependency of the data among each other. Microservices can help reduce complexity.
The transfer of historically grown monolithic software architectures into modern service-oriented architectures creates a lot of loose coupling points. This can lead to an unforeseen system behavior and can significantly impede those continuous modernization processes, since it is not clear where bottlenecks in a system arise. It is therefore necessary to monitor such modernization processes with an adaptive monitoring concept in order to be able to correctly record and interpret unpredictable system dynamics. For this purpose, a general measurement methodology and a specific implementation concept are presented in this work.
Portable-micro-Combined-Heat-and-Power-units are a gateway technology bridging conventional vehicles and Battery Electric Vehicles (BEV). Being a new technology, new software has to be created that can be easily adapted to changing requirements. We propose and evaluate three different architectures based on three architectural paradigms. Using a scenario-based evaluation, we conclude that a Service-Oriented Architecture (SOA) using microservices provides a higher quality solution than a layered or Event-Driven Complex-Event-Processing (ED-CEP) approach. Future work will include implementation and simulation-driven evaluation.
Cloud computing has become well established in private and public sector projects over the past few years, opening ever new opportunities for research and development, but also for education. One of these opportunities presents itself in the form of dynamically deployable, virtual lab environments, granting educational institutions increased flexibility with the allocation of their computing resources. These fully sandboxed labs provide students with their own, internal network and full access to all machines within, granting them the flexibility necessary to gather hands-on experience with building heterogeneous microservice architectures. The eduDScloud provides a private cloud infrastructure to which labs like the microservice lab outlined in this paper can be flexibly deployed at a moment’s notice.
In industrial production facilities, technical Energy Management Systems are used to measure, monitor and display energy consumption related information. The measurements take place at the field device level of the automation pyramid. The measured values are recorded and processed at the control level. The functionalities to monitor and display energy data are located at the MES level of the automation pyramid. So the energy data from all PLCs has to be aggregated, structured and provided for higher level systems. This contribution introduces a concept for an Energy Data Aggregation Layer, which provides the functionality described above. For the implementation of this Energy Data Aggregation Layer, a combination of AutomationML and OPC UA is used.
Concreteness of words has been studied extensively in psycholinguistic literature. A number of datasets have been created with average values for perceived concreteness of words. We show that we can train a regression model on these data, using word embeddings and morphological features, that can predict these concreteness values with high accuracy. We evaluate the model on 7 publicly available datasets. Only for a few small subsets of these datasets prediction of concreteness values are found in the literature. Our results clearly outperform the reported results for these datasets.
Lemmatization is a central task in many NLP applications. Despite this importance, the number of (freely) available and easy to use tools for German is very limited. To fill this gap, we developed a simple lemmatizer that can be trained on any lemmatized corpus. For a full form word the tagger tries to find the sequence of morphemes that is most likely to generate that word. From this sequence of tags we can easily derive the stem, the lemma and the part of speech (PoS) of the word. We show (i) that the quality of this approach is comparable to state of the art methods and (ii) that we can improve the results of Part-of-Speech (PoS) tagging when we include the morphological analysis of each word.
Hadoop is a Java-based open source programming framework, which supports the processing and storage of large volumes of data sets in a distributed computing environment. On the other hand, an overwhelming majority of organizations are moving their big data processing and storing to the cloud to take advantage of cost reduction – the cloud eliminates the need for investing heavily in infrastructures, which may or may not be used by organizations. This paper shows how organizations can alleviate some of the obstacles faced when trying to make Hadoop run in the cloud.
Nowadays, REST is the most dominant architectural style of choice at least for newly created web services. So called RESTfulness is thus really a catchword for web application, which aim to expose parts of their functionality as RESTful web services. But are those web services RESTful indeed? This paper examines the RESTfulness of ten popular RESTful APIs (including Twitter and PayPal). For this examination, the paper defines REST, its characteristics as well as its pros and cons. Furthermore, Richardson's Maturity Model is shown and utilized to analyse those selected APIs regarding their RESTfulness. As an example, a simple, RESTful web service is provided as well.
Our work is motivated primarily by the lack of standardization in the area of Event Processing Network (EPN) models. We identify general requirements for such models. These requirements encompass the possibility to describe events in the real world, to establish temporal and causal relationships among the events, to aggregate the events, to organize the events into a hierarchy, to categorize the events into simple or complex, to create an EPN model in an easy and simple way and to use that model ad hoc. As the major contribution, this paper applies the identified requirements to the RuleCore model.
Aim/Purpose: We explore impressions and experiences of Information Systems graduates during their first years of employment in the IT field. The results help to understand work satisfaction, career ambition, and motivation of junior employees. This way, the attractiveness of working in the field of IS can be increased and the shortage of junior employees reduced.
Background: Currently IT professions are characterized by terms such as “shortage of professionals” and “shortage of junior employees”. To attract more people to work in IT detailed knowledge about experiences of junior employees is necessary.
Methodology: Data from a large survey of 193 graduates of the degree program “Information Systems” at University of Applied Sciences and Arts Hannover (Germany) show characteristics of their professional life like work satisfaction, motivation, career ambition, satisfaction with opportunities, development and career advancement, satisfaction with work-life balance. It is also asked whether men and women gain the same experiences when entering the job market and have the same perceptions.
Findings: The participants were highly satisfied with their work, but limitations or restrictions due to gender are noteworthy.
Recommendations for Practitioners: The results provide information on how human resource policies can make IT professions more attractive and thus convince graduates to seek jobs in the field. For instance, improving the balance between work and various areas of private life seems promising. Also, restrictions with respect to the work climate and improving communication along several dimensions need to be considered.
Future Research: More detailed research on ambition and achievement is necessary to understand gender differences.
The Gravitational Search Algorithm is a swarm-based optimization metaheuristic that has been successfully applied to many problems. However, to date little analytical work has been done on this topic.
This paper performs a mathematical analysis of the formulae underlying the Gravitational Search Algorithm. From this analysis, it derives key properties of the algorithm's expected behavior and recommendations for parameter selection. It then confirms through empirical examination that these recommendations are sound.
In the present paper we sketch an automated procedure to compare different versions of a contract. The contract texts used for this purpose are structurally differently composed PDF files that are converted into structured XML files by identifying and classifying text boxes. A classifier trained on manually annotated contracts achieves an accuracy of 87% on this task. We align contract versions and classify aligned text fragments into different similarity classes that enhance the manual comparison of changes in document versions. The main challenges are to deal with OCR errors and different layout of identical or similar texts. We demonstrate the procedure using some freely available contracts from the City of Hamburg written in German. The methods, however, are language agnostic and can be applied to other contracts as well.