Our research agenda covers the following areas and is conducted within the confines of projects executed with industry partners:
- Database and Big Data technology
- Data Mining, Statistics and Predictive Modeling
- Machine Learning and Graph Analytics
- Information Retrieval and Natural Language Processing
- Business Intelligence and Visual Analytics
- Data Warehousing and Decision Support
- Communication and Visualization of Results
- Privacy, Security and Ethics
- Entrepreneurship and Data Product Design
This list gets directly filled from ZHAW's project database. Not all projects may show up due to interlinkage aspects.
Based on long-standing work and a unique market position, Eaternity successfully distributes a solution for managing CO2 transparency covering the entire value added chain, from food product to full menu. This CTI project enables Eaternity to use the results of its groundwork and turn it into an attractive, scalable and cost-efficient product, ...
The new product of ARGUS DATA INSIGHTS Schweiz AG "Real Time Print Media Monitoring" is an automated pipeline. It identifies relevant articles in print media, extracts them and sends them to the customers in real-time. Core of this project is the automated segmentation of full newspaper pages into articles, this is developed within the project ...
Roche Business Analytics
In this project we design and implement a prototype for solving a highly challenging business analytics use case at Roche. The prototype is based on state-of-the-art technology in the areas of advanced data management, information retrieval and machine learning.
Urban Water Research Data Warehouse
In this project we develop a data warehouse for management of environmental sensor data. The idea is to integrate different data sets from various sensor data by leveraging modern data warehousing technology. The data management approach will open up new avenues for novel urban water research.
The goal of this project is to develop an innovative market monitoring application for an e-commerce platform. The project is done in collaboration with an industry partner. Unlike traditional e-commerce applications where users need to log into the system and thus leave traces when they search for specific products or even buy them afterwards, our ...
A model based three-stage classifier for airborne particles
Computer controlled scanning electron microscopy (CCSEM) is a widely-used method for single airborne particle analysis. It produces large amounts of chemical and morphological data, whose processing and interpretation can be very time consuming. We have developed for Particle Vision GmbH an automated three-stage particle classifier based on ...
Big Data Query Processing
The goal of this project is to perform a proof-of-concept for Big Data query processing with an international industry partner. In particular, we investigate if a Big Data solution based on Apache Hadoop and Cloudera’s Impala can handle the complex query workload of our industry partner subject to minimal response times (near real-time). The main ...
NoSQL Data Warehouse
In this project we evaluated query processing features of various NoSQL databases such as Cassandra, Redis, MongoDB, etc. We performed a detailed performance analysis on multi-dimensional point and range queries.
SODES: Swiss Open Data Exploration System
In recent years, national and international institutions, governments and NGOs have made large amounts of data publicly available: there exist literally thousands of open data sources, with temperature measurements, stock market prices, population and income statistics etc. However, most open data sets are provided only in proprietary data formats. ...
SNF/NRP project: Bio-SODA
One of the major promises of Big Data lies in the simultaneous mining of multiple sources of data. This is particularly important in life sciences, where different and complementary data are scattered across multiple resources. To overcome this issue, the use of RDF/semantic web technology is emerging, but querying these systems often proves to be too complex for most users—thereby hampering wide development and adoption of these technologies.