Data Science Seminar by Joao Paulo Carvalho – University of Lisbon

You are cordially invited to the Data Science Seminar that will take place on Friday, 28th October 2016 (TU/e AUD2).

Participation is free of charge, but please register by sending an email to is@tue.nl before 26th October 2016.

Speaker: Joao Paulo Carvalho, INESC ID’s Spoken Language Systems Laboratory
Title: Fuzzy Fingerprints: Identification and classification in Big data using top-k values

Information about the event is as follows:

Abstract: Fuzzy Fingerprints are a recently introduced technique inspired by the fact that many types of data studied in the physical and social sciences can be approximated with a Zipfian distribution. I.e., the frequency of an item is inversely proportional to its rank in the frequency table. Fuzzy Fingerprints efficiently use the implicit information contained in top-k most frequent data values to perform identification in large datasets. The term “fingerprint” is used in the sense that fingerprints are unique, and are usually left unintentionally, allowing us to identify their “owners”. The fingerprint concept can be extended from single users to categories, topics or classes, allowing us to perform tasks such as classification and recommendation.

In this talk I will approach the ideas behind Fuzzy Fingerprints and show case studies and applications involving: identification of anonymous users based on their phone and web usage habits; text author identification based on their writing habits; classification and identification in social data (e.g. detecting tweets related to a given trending topic); classification based on medical text data; movie recommendation; etc.

This event is technically co-sponsored by the Benelux Chapter of IEEE
Computational Intelligence Society.

Back to Event Calender

BPM Cluster meeting – Presentation by Rob Kusters: Risks and problems on the intersection of Agile and traditional development methods in hybrid organizations

Speaker: Rob Kusters

Title: Risks and problems on the intersection of Agile and traditional development methods in hybrid organizations

Abstract: This research aims to identify the risks and problems experienced in the alignment and collaboration between Agile and traditional development methods within hybrid organizations. A literature search was executed looking at evidence from combinations of Agile, traditional development methods and hybrid organizations. The analysis focuses on risks, problems and challenges to scope the research area. Classification workshops were used to group the results from literature into a coherent whole. The result was tested in a single embedded case study.

Back to EventCalender

Colloquium IS Irene Vanderfeesten: End-to-end process management in high tech manufacturing – an introduction to the HORSE project

Speaker:
Irene Vanderfeesten

Title:
End-to-end process management in high tech manufacturing – an introduction to the HORSE project

Abstract:
The HORSE project is a EU Horizon 2020 research and development project in the area of “factories of the future”. It aims to develop a framework for smart factories that increases efficiency and effectiveness of manufacturing processes by applying and extending process management technology and by integrating human and robotic activities on the workfloor while ensuring a safe and healthy work environment.  In this presentation I will introduce the HORSE project, its goals, its applications, and the contribution  of the TU/e HORSE team to the framework as a whole. I will report on the progress we have made so far in the requirements analysis, complete system design and development of manufacturing process management.

Back to event

Inaugural lecture Prof.dr.ir. Jos J.M. Trienekens Friday October 28, 2016

Prof.dr.ir. Jos J.M. Trienekens was appointed October 1st 2015 as endowed professor of Information Management in Educational Value Networks ” at the Open University. The chair at the Faculty of Management, Science and Technology funded by DEKRA Certification BV in Arnhem.

He will deliver his inaugural lecture:

Date: 28 October 2016
Location: Aula from the Vergadercentrum Pretoria from the Open University. Address: Valkenburgerweg, 177, 6419 AT Heerlen
Time: Reception from 15.30h, Inaugural Lecture: 16:00h (precisely)

Registration: Mandatory until 21 October 2016, via www.ou.nl/uitnodiging.

DocumentDocumentDocument

 

Bewaren

Bewaren

Bewaren

Bewaren

Colloquium IS Xudong Lu: september (Exceptional date this time: WEDNESDAY this time)

Speaker:
Xudong Lu

Title: Utilizing Electronic Heath Records to Support Risk Prediction of Cardiovascular Diseases

Abstract: The presentation will introduce the recent research in Zhejiang University of China on Risk Assessment of Cardiovascular Diseases based on data mining techniques. The research are based on 15000 patient records collected from the hospital. The features are retrieved through Medical NLP techniques, the different risk prediction models have been used on the data, and the results have been evaluated and compared to the GRACE model which has been used in clinical practice now.

About the speaker:

Xudong Lu is a professor of medical informatics at BMI lab of Zhejiang University in China, and a visiting research professor at Technical University of Eindhoven in the Netherlands this week. Before his employment in ZJU, he has the industrial experience of working at Nihon Kohden Corporation in Japan (a well-known corporation on its physiology examination devices and information systems) from 2002-2003. His research focuses are on electronic medical record and clinical decision support. He is the project leader of the National “863” project of “Research on High-end EMR-S and its pilot implementations” initiated since 2011. Besides, he has also involved in several national projects on clinical decision support system.

Back to event

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Bewaren

Colloquium IS Rodrigo Gonçalves: Obtaining, analyzing and manipulating traffic data for a vehicle routing application

Speaker:
Rodrigo Gonçalves

Title:
Obtaining, analyzing and manipulating traffic data for a vehicle routing application.

Abstract:
Vehicle routing problem concerns the service of a logistics company. How things are delivered from one or more depots in a given set of vehicles which move on a given road network to a set of customers. The solution is a set of routes which minimizes global transportation costs. Solutions are obtained based on known characteristics of routes such as travel times or distances between customers. Even though distances are fixed, travel times fluctuate. They are heavily dependent on punctual occurrences, like weather related events or traffic accidents, but also on the period of the year, month and day. In this talk, I will discuss how travel time data was obtained from a TomTom API, how we overcame API limitations by manipulating data and I’ll provide an analysis of how travel time changes with the period of the year, month and day.

Back to event

Colloquium IS Arthur ter Hofstede: Patterns: A Personal Reflection

Speaker:
Arthur ter Hofstede

Title:
Patterns: A Personal Reflection

Abstract:
In the (very) late nineties, I became involved in the Workflow Patterns Initiative. My first foray into patterns-related research. Over time, a number of different patterns collections would be defined and pattern-based evaluations conducted. In this talk I would like to reflect on my experiences with this type of research and discuss the use of patterns, the challenges in defining them, methodological considerations, and typical criticisms.

Back to event

Colloquium Jos Trienekens, april: “Information Quality, framing an evolving information management concept”

Speaker:
Jos Trienekens

Title:
Information Quality, framing an evolving information management concept

Abstract:
Over the years information quality has been subject to many Ph.D research and MSc. projects in the information/software management research group of our capacity group Information Systems.

This presentation will position the information quality concept in a three-level framework, and will clarify characteristics of various research projects (in our group). On each level the focus areas of specification, metrication, standardisation and continuous improvement will be discussed.

In recent years the concept of information quality has evolved towards an IT Governance subject in inter-organisational networks.  Some examples of this evolution will be presented with reference to current Ph.D projects in our research group.

Back to event

Colloquium IS Rik Eshuis: maart

Speaker:
Rik Eshuis

Title:
Supporting knowledge-intensive processes with case management

Abstract:
In recent years, case management has emerged as an approach to support knowledge workers in performing and coordinating business processes. These knowledge-intensive processes are semi-structured and can easily change. Case data and business rules determine the actual flow of work in a knowledge-intensive process. In this talk, I will discuss when to apply case management, how to design knowledge-intensive processes for case management, and how to manage changes in these knowledge-intensive processes.

Back to event

 

Colloquium IS Claudia Chituc:

Speaker:
Claudia Chituc

Title:
The business value of big data: opportunities and challenges

Abstract:
Information and communication technologies are used to store and analyze increasing amounts of digital data.  Although numerous advantages are associated with big data, research on the business value of big data is scarce. This presentation will report on some projects undertook towards identifying opportunities for obtaining business value out of big data.  Two models will be discussed, which provide support (e.g., to decision makers/ stakeholders) in understanding how to derive value from big data.

Back to event