Felix Engel

Felix Engel
University of Hagen · Faculty for Mathematics and Computer Science; Chair for Multimedia and Internet Applications

Dr.-Ing.

About

54
Publications
4,114
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
155
Citations
Citations since 2016
46 Research Items
144 Citations
201620172018201920202021202201020304050
201620172018201920202021202201020304050
201620172018201920202021202201020304050
201620172018201920202021202201020304050
Introduction
I currently work on a semantic search engine. The engine implements an ontology based information retrieval approach. I have tested the current development with several TREC benchmarks. Overall, I get a good recall, but no good precision. I now try to use a graph representation of the underlying ontology and to apply graph embeddings on those to get better precision values
Additional affiliations
November 2015 - present
FernUniversität in Hagen
Position
  • PostDoc Position
Education
March 2009 - October 2015
FernUniversität in Hagen
Field of study
  • Infromation Retrieval, Machine Learning
October 2003 - March 2009
University of Duisburg-Essen
Field of study
  • Information Systems

Publications

Publications (54)
Chapter
Full-text available
Digitalisierung umgreift mittlerweile sämtliche gesellschaftlichen Funktionsbereiche und ist aus den lebensweltlichen Vollzügen kaum mehr wegzudenken. Technische Artefakte vernetzen sich immer stärker und bilden unter anderem einen (unsichtbaren) Hintergrund, mit dem menschliche Handlungen auf vielfältige Weise implizit und explizit verwoben sind....
Article
Full-text available
Multimedia Indexing and Retrieval is generally designed and implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results but also leads to more complex graph structures. However,...
Presentation
Full-text available
Presentation of the "Graph Codes - 2D Projections of Multimedia Feature Graphs for Fast and Effective Retrieval" on the ICIVR2021 conference.
Conference Paper
Full-text available
Multimedia Indexing and Retrieval is generally designed and implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results but also leads to more complex graph structures. However,...
Article
This article summarizes selected aspects of a dissertation project and prior publications related to the DFG-funded RecomRatio research project. As such, it provides an end-to-end overview of a research project that aims at extracting and utilizing Emerging Knowledge represented by two concepts that we define as Emerging Named Entities and Emerging...
Article
Indexing and Retrieval of multimedia is generally implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results, but also leads to more complex graph structures. However, graph-tr...
Chapter
To make the SenseCare KM-EP system more useful and smart, we integrated emotion recognition from facial expression. People with dementia have capricious feelings; the target of this paper is measuring and predicting these facial expressions. Analysis of data from emotional monitoring of dementia patients at home or during medical treatment will hel...
Article
Full-text available
To cope with the growing number of multimedia assets on smartphones and social media, an integrated approach for semantic indexing and retrieval is required. Here, we introduce a generic framework to fuse existing image and video analysis tools and algorithms into a unified semantic annotation, indexing and retrieval model resulting in a multimedia...
Chapter
Automated argument stance (pro/contra) detection is a challenging text categorization problem, especially if said arguments are to be detected for new topics. In previous research, we designed and evaluated an explainable machine learning based classifier. It was capable to achieve 96% F1 for argument stance recognition within the same topic and 60...
Conference Paper
Full-text available
Affective Computing is a rather new and multidisciplinary research field that seeks for sophisticated automation in emotion detection for later analysis. However, the automated emotion detection and analysis require as well comprehensive data management support e.g. to keep control about produced data, to enable its efficient reuse through classifi...
Conference Paper
Full-text available
The reduced cost of DNA sequencing allows metagenomics to be applied on a larger scale. With metagenomic analysis, we have better insight into supplement usage, methane production, and feed conversion efficiency in livestock systems. Nevertheless, sequencing machines generate an enormous amount of complex data. Conventional method used in the analy...
Conference Paper
Affective Computing is a relative new, dynamic and interdisciplinary research field. Numerous contributions from fields like computer science, psychology, cognitive science, sociology, physiology and medical science have been made. Consequently, it is getting hard to track all recently published trends for early insights utilisation in practise or...
Conference Paper
Obesity is a global challenge that affects health and wellbeing worldwide. In this position paper, we review the digital technology used in prevention of obesity and present the proposed STOP project that integrates state-of-the-art wearable technology, chatbot, gamification data fusion and machine learning with the aim to provide personalised supp...
Article
Traditionelle Gedächtnisinstitutionen – Archive, Bibliotheken und Museen – stehen vor der Herausforderung der digitalen Transformation. Insbesondere, da Inhalte aus unterschiedlichen Gründen nur zum Teil online verfügbar sind, während die externe Nachfrage nach der Nutzung der vorhandenen Archivinhalte ständig steigt. Dr beitrag befasst sich daher...
Conference Paper
Full-text available
Collaborative interdisciplinary research has the added difficulty, that researchers from different fields have different backgrounds and employ heterogeneous technical vocabularies. Certain problems could have already been solved in one field, but the solution is described in such a fashion, that it is difficult for researchers from another field t...
Conference Paper
People’s worries about robot and AI software and how it can go wrong have led them to think of it and its associated algorithms and programs as being like Mary Shelley’s Frankenstein monster. The term Franken-algorithms has been used. Furthermore, there are concerns about driverless cars, automated General Practitioner Doctors (GPs) and robotic sur...
Conference Paper
Full-text available
The aim of this paper is to describe and explain the most significant updates which have been made to the version 2 OAIS [1], which was published in 2012, from the point of view of the authors, who have all been deeply involved with the revision. These updates resulted in a draft which, at the time of writing, is the text to be submitted for Consul...
Preprint
Full-text available
Heterogeneity of data sources is a challenge for Big Data applications. This contribution presents an approachbased on the conceptual foundation of the mediator/wrapperarchitecture where source data is transformed into a globalschema and transferred to one or more data sinks with ApacheKafka. Given appropriate wrappers, arbitrary data sources and...
Conference Paper
Heterogeneity of data sources is a challenge for Big Data applications. This contribution presents an approach based on the conceptual foundation of the mediator/wrapper architecture where source data is transformed into a global schema and transferred to one or more data sinks with Apache Kafka. Given appropriate wrappers, arbitrary data sources a...
Chapter
In the domain of cultural heritage, a lot of archives and data collections already exist. Thus, one of the main challenges for curators and archivists in this domain consists of exchanging data with other archives and integrating similar collections. Typical usage scenarios in this area can only be realized by semantically integrating all available...
Conference Paper
The use of Affective Computing in the medical domain is gaining momentum, but is challenged through requirements arising through the inherent processing of personal sensitive data, that will effect comprehensive analysis reproducibility. Reproducibility is a key element in good research practice and a key ingredient to comprehensively validate AC a...
Chapter
This paper discusses an opportunity for using affective computing modalities to support the monitoring of emotional wellbeing of older people. The ageing population is escalating and is associated with an increase in the number of persons with dementia. It is also reported that older people can suffer from social isolation and that people with deme...
Conference Paper
In recent years, most breakthroughs in fields such as image and video processing were based on machine learning technologies that allow computers to recognize objects in images with nearly human precision. In some application domains, computers even surpassed human level performance. These breakthroughs result from an exponential increase of comput...
Chapter
Full-text available
Challenges in Big Data. Challenges in Big Data Analytics. Bigdata Reference Model. A Survey of Big Data Analytics Tools. Understanding Data Science Behind Business Analytics. Big Data Predictive Modelling and Analytics. Deep Learning for Engineering Big Data analytics. A Framework for Minimising Data Leakage from Non-Production Systems. Big Data ac...
Chapter
Full-text available
Due to the increasing volume of data and the necessity to analyse those data in real-time, it is inalienable to use big data technologies and new innovative methodologies to generate added value and a sustainable knowledge-base. One of such big data technologies is Apache Hadoop and its modules and components like HDFS, Storm, Zeppelin, HBase, and...
Book
This book constitutes the thoroughly refereed post-workshop proceedings of the AVI 2016 Workshop on Road Mapping Infrastructures for Advanced Visual Interfaces Supporting Big Data Applications in Virtual Research Environments, AVI-BDA 2016, held in Bari, Italy, in June 2016. The 10 revised full papers in this volume present the elaborated outcome...
Conference Paper
Many different recommender system (RS) frameworks have been developed by the research community. Most of these RS frameworks are designed only for research purposes and offline evaluation of different algorithms. A reuse of such frameworks in a productive environment is only possible with high effort. In this paper, we present a concept of a generi...
Conference Paper
Full-text available
This paper introduces an approach to develop an up-todate information technology infrastructure that can support Advanced Visual User interfaces for Distributed Big Data Analysis in Virtual Labs to be used in eScience, Industrial Research, and Data Science Education. The paper introduces and motivates the current situation in this application area...
Conference Paper
Analytics and visualisation of Big Data appearance is still a challenging task. In this paper, the management and visualisation of big data streams will be discussed at hand of data that comes into existence during the care of people with dementia in their own homes. Therein, basic requirements are explored towards the development of a data managem...
Chapter
Recent studies by Amgen and Bayer showed that only 11% and 25% respectively of reviewed cancer research projects produced scientifically valid results. The awareness of this fact is accompanied by increasingly stringent regulations, which enforce compliance to ensure the ability to validate research results through its proper reproducibility. Furth...
Article
Full-text available
This article outlines how the Knowledge-based Production Process Planning can be applied to develop data management policy rules (DMPRs). The process supports the creation and evolution of data management plans and their automated execution. The planning is guided by a policy refinement process where a methodological approach derives rules from nat...
Poster
There exist an urgent demand to keep the full traceability and reproducibility of research findings based on observational and other research data to ensure the ability to validate research results for proper later re-use. The awareness of this fact is accompanied by increasingly stringent regulations from reimbursement agencies, which enforces the...
Conference Paper
Full-text available
There is an increasingly urgent need to ensure the fullest possible preservation of research findings, both for proper validation of the research in question and to enable its comprehensive reuse. Furthermore, research undertakings are expensive and the return on investment needs to be secured by research funding agencies and public funding bodies...
Conference Paper
Sensor Enabled Affective Computing for Enhancing Medical Care (SenseCare) is a project to reduce clinical treatment costs and to enhance life quality of patients with Dementia related disease like Alzheimer. This paper defines usage scenarios of SenseCare related to clinical record data management, outlines current challenges and goals in this fiel...
Article
This paper outlines challenges and requirements for developing tools and services supporting automated generation, management, evolution, and execution of Data Management Plans (DMPs) by reviewing Research Data Management (RDM)processes in the light of using the method of Knowledge-based and Process-oriented Innovation Management (German: Wissenbas...
Conference Paper
Full-text available
A framework for expert searching developed at the Univer-sity of Hagen supports the use of contextual factors motivated in the field of expertise seeking. A user can query the system with skills which the person to be found should be an expert in. The result is a list of users from the searched knowledge base, ranked by relevance for the given quer...
Conference Paper
The SCIDIP-ES project provides an e-infrastructure to support long-term preservation and use of the knowledge encoded in scientific data. The infrastructure offers a set of generic, sustainable services and toolkits based on the CASPAR prototypes to support efficient preservation planning and management along with usability and access needs. The SC...
Conference Paper
The documentation of processes or employee- and product-related-data in the enterprise does comprehen- sively contribute to the preservation and future access to acquired in-house knowledge. Sophisticated access to this data is an essential part of successful knowledge man- agement. With the increasing use of semantic web rec- ommendations and tech...
Article
Full-text available
In the area of information retrieval the concept of relevance feedback is used to provide high relevant documents to the user. The process of gaining relevance data is usually based on ex-plicit Relevance Feedback. But it turned out, that users are usually not willing to provide such data. This paper describes a Relevance Feedback ap-proach that su...
Article
Full-text available
Supporting access to archived scientific publications, supplementary data, and multimedia objects as a basis for various types of reuse in scientific work processes and in publication processes is still an open issue in many ways. Reuse comprises, for instance, the subsequent verification of the content or its exploitation with a novel purpose. Ret...

Network

Cited By

Projects

Projects (8)
Project
Integration, Scalability and Semantic for Multimedia Information Retrieval