wir bieten...
Dekobild im Seitenkopf ISMLL
Projects & Cooperations:

Research Projects


(Start: October 2018)
The University of Hildesheim would like to combine its expertise in the field of Data Science, which has found expression in the international Master's course Data Analytics, currently the largest Data Science course in Germany, and in the establishment of a Research and Innovation Center Data Science, with the expertise in the programs located at the university in order to offer all students an educational opportunity in the field of Data Science that takes into account the different requirements and focal points of the subjects without sacrificing the teaching of the underlying methods. Its core consists of a set of two introductory courses in data science, which are structured micromodularly, i.e. in units of a maximum of 10 minutes: methodological modules, which are the same for all subjects, and example modules, which illustrate a method using an example from the respective field. [more]
Contact: Lars Schmidt-Thieme Lukas Brinkmeyer


(Start: October 2018)
The project team consisting of the Information Systems and Machine Learning Lab (ISMLL) of the University of Hildesheim and the MediFox GmbH, the leading software provider for software solutions for mobile nursing services plans to improve the route scheduling capabilities of existing software applications. Therefore we will develop a software prototype which adopts state-of-the art heuristic optimization methods to find a ideal route and operation schedule considering all side conditions. In a second step a smart optimization model is developed, which learns how to automatically optimize respective arbitrary routing problems by employing meta learning approaches, facilitated by the huge data base of MediFox. [more]
Contact: Lars Schmidt-Thieme Jonas Falkner


(Start: June 2018)
The goal of the "Automated Development of Data Analysis" project between PSIORI GmbH and the Information Systems and Machine Learning Lab (ISMLL) is to find novel techniques to automate client specific data analysis via a meta learning approach. This enables the data scientist to offer "rapid data analysis" als a new service. These will enable clients to take a fast and cost effienct look into the world of big data and machine learing. This especially enables small and mid tier businesses to benefit from the new generation of data analysis and AI technology tools. [more]
Contact: Lars Schmidt-Thieme, Randolf Scholz Rafael Drumond

Data-driven Mobility Services

(Start: February 2018)
Data-driven Mobility Services is a three years cooperative research project between Volkswagen Financial Services (concretely the Data Analytcs Unit 'DnA') and Information Systems and Machine Learning Lab (ISMLL) at Uni Hildesheim. As part of the contracted research cooperaton, several data analytics studies are being conducted, which includes parking availability prediction, automatic damage assessment for cars, and residual value prediction for cars. The outcome of the research done at ISMLL can be directly integrated into the backend system developed by the DnA unit, especially after the prototyping phase, during which a proof of concept is presented that highlights the effective of the solutions presented. [more]
Contact: Lars Schmidt-Thieme, Mohsan Jameel Hadi S. Jomaa Ahmed Rashed


(Start: November 2017)
The progressive digitalization of economy and society is making more and more processes observable and thus open to partial automation or at least decision support through machine learning models: in Industry 4.0 machine data can be used used to detect problems early and avoid failures or to reduce manufacturing variances and make planning more robust, in autonomous driving cars sensor and video data is already in use for simple maneuvers such as parking and will soon also be used for driving on highways, in the area of ​​e-health they help in segmenting organs and tumors or predicting how a tumor will most likely develop. [more]
Contact: Lars Schmidt-Thieme,Ahmed Rashed


(Start: September 2014)
One of the major challenges of learning predictive models for complex tasks is the right hyperparameter and model selection strategy, as state-of-the-art approaches such as grid-search and random sampling require many runs of the learning algorithm, and therefore are usually conducted on large compute clusters rather than resource-restricted platforms such as robots, cars or mobile phones for instance. Therefore, autonomous hyperparameter learning strategies that are able to take into account observations of past hyperparameter performances on related problems have to be developed, enabling learning systems to learn in a fraction of the time it takes today. [more]
Contact: Nicolas Schilling, Martin Wistuba, Lars Schmidt-Thieme


(Start: November 2012)
iTalk2Learn wants to develop a platform for intelligent support that combines structured learning with exploratory learning activities. To do so cognitive models are applied, that represent the learning behavior of students in elementary education. The platform will enable learners to communicate and interact more naturally via state of the art touch and speech interfaces. [more]
Contact: Neelava Sengupta, Carlotta Schatten, Lars Schmidt-Thieme

REDUCTION - Reducing Environmental Footprint based on Multi-Modal Fleet management Systems for Eco-Routing and Driver Behaviour Adaptation

(Start: September 2011)
REDUCTION focuses on advanced solutions that combine mechanical / measurement technologies with information and communication technologies (ICT) for the management of multi-modal fleets, in order to reduce their environmental footprint. [more]
Contact: Josif Grabocka, Lars Schmidt-Thieme

EFRE project: AcoGPR - Adaptive Contactless Ground Penetrating Radar

(Start: Juni 2011)
The ISMLL researches on advanced supervised machine learning models in the context of urban planning and development. The analysis of data gathered from ground penetrating radars allows for exact positioning of supply lines. Jointly with the University of Braunschweig and Detectino GmbH, a local company from Hildesheim, a mobile radar vehicle will be constructed and tested in real application scenarios. [more]
Contact: Andre Busche, Lars Schmidt-Thieme

DFG project on Multirelational Factorization Models

(Since April 2011)
Factorization models are machine learning models that predict quantities based on historical data, i.e., customer preferences, health risks, etc. Factorization models specifically address problems where interactions between objects should be predicted about which not many data are known. The ISMLL works on factorization models for several years now. [more]
Contact: Lars Schmidt-Thieme

RFID-Enhanced Museum for Interactive Experience (REMIX)

(since Sep. 2010)
Visitors to physical museums are often overwhelmed by the vast amount of information available in the space they are exploring, making it difficult to select personally interesting content. Personalization solutions can provide the required user-centered interactivity between the visitors and the museums. The aim of the REMIX project is to address this problem using recommender systems. [more]
Contact: Alexandros Nanopoulos, Rasoul Karimi

Master Online Intelligent Embedded Microsystems (IEMS)

(since October 2007)
Within the "Master Online Intelligent Embedded Microsystems" (IEMS) offered by the University of Freiburg, we provide the module "Analytic Methods". The module deals with probability theory, statistics and differential equations.
Contact: Christoph Freudenthaler, Lars Schmidt-Thieme

Recently Completed Projects

Learning Recommender Systems for Online Shops(LEFOS)

(ended on Feb. 2011)
The LEFOS project aims at integrating recommender system components like the ones known from Amazon ("Customers Who Bought This Item Also Bought") in line of business E-commerce shops... [more]
Contact: Artus Krohn-Grimberghe, Lars Schmidt-Thieme

Dynamic Personalization of Multimedia (MyMedia)

(ended on Feb. 2011)
We are drowning in a sea of information overload. Television channels, books and music assault our senses with far too much content. The volume of content on the internet is literally exploding. Not only traditional media but millions of individual users are putting their own content on the web. The massive popularity of YouTube is just one example of this phenomenon. So, in this flood, how do you find content that matters to you? How do you discover multimedia information and entertainment in a way that suits you personally? Isn’t there an easier way? ... [more]
Contact: Zeno Gantner, Lars Schmidt-Thieme

See also Completed Research Projects and Past Industry Cooperation