New app Mobile Social Worker developed by our student Karel Zavadil as part of his Bachelor thesis will help people in crisis seek professional help.

A unique tool to promote urban cycling Cykloplánovač has been developed by experts from the Agent Technology Centre of Faculty of Electrical Engineering together with students from Open Informatics program. This application combines intelligent navigation and data analysis and can accordingly plan the route in 25 Czech cities and Bratislava. 

Wine database analysis for Navrátilova Ltd. company.

The cooperation of the Department with industry on the basis of the innovation voucher in Prague, 2014.

miXGENE.ORG - a public tool for integrated analysis of microarray, microRNA and methylation data

Systems biology focuses on complex interaction within biological systems. These complex interactions, hidden both in high-throughput measurements and a vast amount of existing biological knowledge, are difficult to be mined without an aid of automated tools. MiXGENE is a workflow management tool that develops and analyzes accurate, mainly disease predictive, models from the raw omics data.

Predicting protein properties with spatial statistical machine learning: Proteins are what we are made of and what controls what happens inside of us. Yet, we know too little about the functions of the thousands of specific proteins that have been discovered. We design algorithms that learn to predict “what the protein does” from “what the protein looks like”.

Will it break down once warranty’s over? We ask a similar question in a more complex setting: in the European project SUPREME, we explore how machine learning and data mining techniques can be used to predict failures in an industrial plant

Project Self-Organizing Maps for Multi-Goal Path Planning Task aims to develop a planning framework to increase reliability of autonomous navigation of mobile robots in surveillance missions. The approach is based on self-organizing principles applied in multi-goal path planning that are combined with models of localization uncertainty evolution.

MYWAY is a 7th Framework ICT Project implemented by 14 partner organisations from across Europe that range from public authorities, research centers to SME’s. Placing the traveller at the heart of mobility, MYWAY develops an integrated platform, the European Smart Mobility Resource Manager, that enables combining all sorts of transport services and automatically handling transactions related to their usage into a seamless point-to-point mobility service. 

The SUstainable and PERsuasive Human Users moBility in future cities (SUPERHUB) project is an international 7th Framework ICT project involving 20 partners from all around Europe. SUPERHUB develops next generation journey planning and travel assistenace tools for seamless sustainable urban mobility. Combining new techniques of large scale data capture and processing, next-generation algorithms for dynamic personalized multimodal journey planning and adaptive perusasive user interfaces, it helps travellers to make the best use of transport services available in modern cities. 

The Deterministic Domain-independent Multi-agent Planning project studies both formally and empirically deterministic domain-independent multi-agent planning. We generalize the domain-independent formalisms and techniques developed for single-agent planning towards the key concepts of multi-agent planning. The goal of the project is to provide theoretical complexity analysis of communication and computation costs, and perform empirical evaluation on a comprehensive multi-agent planning testbed.

Our project Towards Robust Multiagent Plans focuses on theoretical and applied research in field of multiagent planning in dynamic environments. The objective of the project is to connect, both formally and empirically, between the developments in domain-specific multiagent planning and the concepts of generic, domain-independent, problem solving and propose solutions and techniques robust to uncertainty, dynamism and non-determinism of environments modelled closely to real world.