PhD defense of Rui de Almeida: Conditional Density Models Integrating Fuzzy and Probabilistic Representations of Uncertainty @June 26 Erasmus University Rotterdam

Erasmus School of Economics (ESE), Erasmus University Rotterdam – See More
On Thursday June 26 Rui de Almeida will defend his Ph.D. thesis entitled “Conditional Density Models Integrating Fuzzy and Probabilistic Representations of Uncertainty” @ Senate Hall, A-Building, Woudestein Campus 11.30-13.00 hrs.

Prom./coprom.: Prof.dr.ir. Uzay Kaymak / Prof.  João M. Sousa

Abstract

Conditional density estimation is an important problem in a variety of areas such as system identification, machine learning, artificial intelligence, empirical economics, macroeconomic analysis, quantitative finance and risk management.

This work considers the general problem of conditional density estimation, i.e., estimating and predicting the density of a response variable as a function of covariates. The semi-parametric models proposed and developed in this work combine fuzzy and probabilistic representations of uncertainty, while making very few assumptions regarding the functional form of the response variable’s density or changes of the functional form across the space of covariates. These models possess sufficient generalization power to approximate a non-standard density and the ability to describe the underlying process using simple linguistic descriptors despite the complexity and possible non-linearity of this process.

These novel models are applied to real world quantitative finance and risk management problems by analyzing financial time-series data containing non-trivial statistical properties, such as fat tails, asymmetric distributions and changing variation over time.

New Employee Helen Ma

I did my PhD in the department of Computer Science in The Chinese University of Hong Kong from 2003 to 2006. My research project was bidding strategies in agent based continuous double auctions (CDAs). I had been researching on the new bidding strategy and powerful factors which can improve the performance of existing bidding strategies in CDAs. After that, I had worked as PostDoc from 2007 to 2012 in the national research institute of mathematics and computer science (CWI), and later at the department of the Built Environment, TU/e, The Netherlands. In the meanwhile, I had extended my research area from bidding strategies adopted by agents to the auctions mechanisms in centralized systems and distributed systems. Moreover, giving my experience on multi-agent simulation and adaptive agent behaviour, I had been involved in the activity travel scheduling for multiple individuals where joint activity and travel scheduling, credit mechanism, social network, and negotiation have been interwoven into such a dynamic system. Since 2012, I had been working at R&D, Vanderlande Industries. My work focused on a new generation of software product which plans realtime multiple shuttles’ travelling and meets the throughput requirement in the distribution center.

New Employee Harold Lijten

My name is Harold Lijten.
My colleagues describe me as a weathered professional with a broad and deep knowledge of the finance domain and its intersection with  IT.  My  professional specialization is enterprise- software architecture and software development.
During my daily practices some really interesting questions cross my path and they are the reason for me to maintain a solid link with the academic world.

One of these questions which has my attention for a long time is; can we create capabilities within the architecture of an information system which facilitate a substantial increase of the flexibility and life-time of an information system? My strong desire to answer this question has led to some years of research already.
The purpose of my current research is to determine the contribution of the concept scenario planning applied during the process of designing and developing an information system. The main subject of study is researching the possible implications for the life-time of an information system and its architecture when scenario planning is used during the process of design and development.

New Employee Bilge Celik Aydin

I am graduated from Industrial Engineering Department from Middle East Technical University in 2009. I completed my MSc degree in 2011 there while working as a teaching assistant. I have assisted courses such as simulation, systems thinking, network flow, work systems analysis and design, data mining and so on.
I focused on data mining and multi criteria optimization during my masters studies. For my thesis, I developed a distance-based multi-criteria optimization algorithm for the sorting problem.
I was involved in an applied project in KU Leuven last year about process improvement in the emergency department of Turnhout Hospital. We developed an advanced simulation model of the department based on the real data provided by the hospital. What-if analysis is conducted for evaluating the performance of different schedules. The project continues with integration of a genetic algorithm for staff schedules with the simulation model.

Presentation Dr Peter Szlosarek

A bioinformatic approach to mesothelioma therapeutics: from ADAM to TRAP

Arginine deprivation is a novel antimetabolite strategy for the treatment of arginine-dependent cancers that exploits differential expression and regulation of key urea cycle enzymes. Several studies have focused on inactivation of argininosuccinate synthetase 1 (ASS1) in a range of malignancies, including melanoma, hepatocellular carcinoma, and mesothelioma. Promoter methylation, in particular, has been identified as a mechanism for loss of the tumor suppressor role of ASS1 leading to tumoral dependence on exogenous arginine. Clinical trials of several arginine depletors are ongoing, including pegylated arginine deiminase (ADI-PEG20, Polaris Group, US) and bioengineered forms of human arginase. The challenge will be to identify tumors sensitive to arginine depletors, and integrate these agents into multimodality drug regimens using predictive biomarkers. Here, we have applied a bioinformatic approach to identify tractable pathways with ADI-PEG20 in the treatment of patients with mesothelioma. Recently, our phase 2 study of ADI-PEG20 in mesothelioma (ADAM) completed accrual and we are now launching a phase I combinatorial trial (TRAP) in the UK based on our bioinformatics studies.

Bio:

Dr Peter Szlosarek (MBBS BSc MRCP PhD) is a Clinical Senior Lecturer at the Barts Cancer Institute, and Cancer Physician at St. Bartholomew’s Hospital, London. He studied Medicine and Pharmacology at King’s College, London and then specialised in Medical Oncology completing a PhD on the links between TNF-a, inflammation and cancer at the University of London. His clinical and lab research interests are in metabolic approaches to cancer therapy, particularly the role of arginine deprivation therapy in arginine-dependent cancers. This has led to clinical trials of the arginine-depleting agent ADI-PEG20 (Polaris Group, US) in mesothelioma (CTAAC grant) and small cell lung cancer, the latter a collaboration with the Ludwig Institute for Cancer Research in New York, US. He is funded by several grant bodies including Cancer Research UK, Barts and The London Charity, Medical Research Council and the British Lung Foundation. He maintains a research-orientated clinical practice at Barts in thoracic and cutaneous malignancy and is a member of the Royal College of Physicians, the Association of Cancer Physicians, the EORTC, AACR and ASCO.

Event details

Presentation on ZJU Research Xudong Lu

Abstract: The BMI lab at Zhejiang University is a pioneer of biomedical informatics research in China. The lab has close links with strategic clinical and industrial partners, and leads several national key projects in healthcare IT domain in the coming few years. Clinical Decision Support is one of the main research focuses in the Lab. In this presentation the speaker will give an introduction of three CDSS researches conducted by the lab recently.

Clinical Decision Support System for chronic diseases. Since 2006, the lab has cooperated with PLA General Hospital in China to conduct research on clinical decision support system. The purpose was to find a methodology and application to improve the quality of primary care in the broad rural area in China through CDSS. The diseases with metabolic symptoms were targeted at first based on computational guideline methodology. Recently the diseases of headache disorders and AD have been chosen in order to verify and improve the methodology in a much broader area. Based on the experience learned from these studies, a common framework based on openEHR has been proposed with the purpose of facilitating creating CDS applications for different types of chronic diseases.

Medical Knowledge Translational Platform. Since 2011, the lab has been in charge of the national “863” project of China “High-end EMR system and its pilot implementation”. One of the main features of the High-end EMR system is integrating with medical knowledge and providing CDS services for clinical staffs. The research of medical knowledge translational platform is one part of such works. In the presentation, the speaker will introduce the concepts, methodology framework and initial results of this work.

Clinical Pathway Analysis. CPA project has been funded by Philips through Brain Bridge Program. The researches include two parts, one from the exchanging Ph.D student in TU/e and the other from the researchers in China. In the presentation, the speaker will introduce the progress of the related researches of CPA in China, including discovery of CP patterns, similarity measurement between patient traces and CPA toolkit development.

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. 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.

 

New Employee Rui Jorge de Almeida

I received my 5 year degree in Mechanical Engineering in 2005 from Technical University of Lisbon, Instituto Superior Técnico, Portugal. During my studies I was a research assistant in characterization of liquid films by interferometry and atomic force microscopy. In 2006 I obtained my Master of Science degree also in Mechanical Engineering from the same university. During my masters, I was a research assistant for a one year period in a project of image based classification. Directly after my masters, I started my PhD in Econometrics at the Erasmus Research Institute of Management, Erasmus University of Rotterdam. In this thesis, I worked on developing new models that combine probabilistic and fuzzy uncertainty applied to risk forecasting. During my PhD I received a grant from COST Action IC072 in 2011 to perform a short term research visit at Université de Technologie de Compiègne, France, where I worked on rule-based models using the belief functions framework, and an IEEE-CIS Walter Karplus Student Research Grant in 2012 for a short term research visit at Laboratoire d’Informatique de Paris 6, Université Pierre et Marie Curie, France, where I worked on linguistic summaries of patient data to detect medical events. In 2013 I did a research visit at LISTIC, Université de Savoie, France, to work in information fusion based on expert knowledge using the belief functions framework.

Seminar prof. Adnan Yazici from Middle East Technical University, Ankara, Turkey

Event Details

Speaker:  Prof.Dr. Adnan Yazıcı, Computer Engineering Department, Middle East Technical University, Ankara-Turkey

Title:   Modeling and Management of Multimedia Data

Abstract: Due to the developments in information and communication technologies, the volume and usage of multimedia data increases rapidly and extracting semantic information and querying them has become an important requirement in our daily lives. Conceptually modeling multimedia information, extracting semantic information from multimedia data, storing and querying multimedia content in and from a multimedia database system and accessing them efficiently from a database are some of the important research topics in multimedia information retrieval area. In this talk I will talk about the research on multimedia information/data management that has been going on in Multimedia Database Laboratory, established in Computer Engineering Department at Middle East Technical University.

Biography: Prof. Dr. Adnan Yazıcı is chairman of Dept. of Computer Engineering, METU. He received his Ph.D. in Computer Science from the Department of EECS at Tulane University, USA, in 1991, where he also has been a visiting professor between 1998 and 2000. His current research interests include intelligent database systems, fuzzy database modeling, spatio-temporal databases, multimedia and video databases, and wireless multimedia sensor networks. Prof.Dr. Adnan Yazıcı has published more than 180 international technical papers and co-authored two books, which are titled Fuzzy Database Modeling (by Springer) and Uncertainty Approaches for Spatial Data Modeling and Processing: a Decision Support Perspective (by Springer). He is a senior member of IEEE and has received IBM Faculty Award for 2011 and Young Investigator Award bestowed by the Parlar Foundation, for the year 2001. Dr. Yazıcı was a Conference Co-Chair of the 23rd IEEE International Conference on Data Engineering (ICDE) in 2007 and a Conference Co-Chair of the 38th Very Large Data Bases (VLDB 2012) conference. He was also the Program Committee Chair of the 18th International Symposium of Computer and Information Sciences (ISCIS 2003), one of the Program Committee co-chairs of  ISCIS 2010 and Flexible Query Answering Systems (FQAS 2011). He is the director of Multimedia Database Lab. in the Computer Engineering Department at METU.

New IS Employee: Anna Wilbik

In 2004 I received my M.Sc. degree in Computer Science from Warsaw University of Technology, Faculty of Mathematics and Information Science for thesis about genetic algorithms in learning methods of associative memory.
Directly after my studies I worked as Research Assistant at Systems Research Institute, Polish Academy of Science. In November 2010 I defended there my Ph. D. in Computer Science with thesis on linguistic summaries of time series using fuzzy sets and their application for performance analysis of mutual funds and got promoted to Assistant Professor.
In spring 2011 I went to Columbia, MO, USA, where I spent a year as a post-doc at Electrical and Computer Engineering Department, University of Missouri. I started working there on application of linguistic summaries to eldercare problem.
Last fall I had chance to participate in Top 500 Innovators Science – Management – Commercialization Program – a professional development program in the field of Science Management and Commercialization held at Stanford University, CA, USA.