Samulski.nl - Maurice Samulski » university

Thesis defense

Maurice Samulski — Tue, 15 Nov 2011 13:09:00 +0000

Finally! After five years of research and article writing, I am glad to announce that I am defending my Ph.D. thesis “Computer Aided Detection as a Decision Aid in Medical Screening” on wednesday, 14th december 2011 at 10.30 in the aula of the Radboud University Nijmegen. You are all welcome to attend this public defense. Afterwards, a reception will take place in the aula.

The thesis has been printed by Ipskamp Drukkers and is currently being shipped out. If you didn’t receive a copy, please send me an email with your address and I’ll make sure you will get a copy. Meanwhile, my thesis and invitation is also available online:

Download thesis and invitation

EIBIR Winter School 2010 – Viladrau

Maurice Samulski — Tue, 26 Jan 2010 15:05:47 +0000

I’ve been to the EIBIR Winter School that took place from January 17 – 22, 2010 in Viladrau, Spain to learn a lot about biomedical imaging research focused on the two leading causes of death worldwide: cardiovascular and oncologic diseases. During the five days, there were a lot of intense lectures hosted in the Hostal de la Gloria, Viladrau. To break the week, we also had a very nice excursion: a walk through the forest with a guide that took us to the house of one of the most famous bandits: Serrallonga. After the heavy week of studying, we finished our stay in Viladrau and went up into the Turo de l’Home ( ‘mountain man’ in Castilian), which is the highest mountain in the Montseny massif with a height of 1712 meters.

Master Thesis

Maurice Samulski — Mon, 19 Jun 2006 12:39:00 +0000

Breast cancer is the most common life-threatening type of cancer affecting women in The Netherlands. The success of the treatment of breast cancer largely depends on the stage of a tumor at the time of detection. Therefore, early detection of breast cancer is essential. Although mammography screening is currently the most effective tool for early detection of breast cancer, up to one-fifth of women with invasive breast cancer have a mammogram that is interpreted as normal, i.e., a false-negative mammogram result. To overcome such limitations, Computer-Aided Diagnosis (CAD) systems for automatic classification of breast lesions as either benign or malignant are being developed. CAD systems help radiologists with the interpretation of lesions, such that they refer less women for further examination when they actually have benign lesions. In this thesis we constructed several types of classifiers, i.e., Bayesian networks and support vector machines, for the task of computer-aided diagnosis of breast lesions.

Classification of Breast Lesions in Digital Mammograms, Master Thesis (1.3 MB PDF)

Image compression: Fourier vs Wavelets

Maurice Samulski — Wed, 19 Apr 2006 14:46:15 +0000

Digital images have become an important source of information in the modern world of communication systems. Thinks about FBI fingerprints, MRI scans, ECG data, digital camera photos, building plans etc. In their raw form, these images require an enormous amount of memory. With the introduction of multimedia computing, the demand for processing, storing and transmitting images has increased exponentially. In the last two decades a considerable amount of research has been devoted to tackle the problem of image compression.

During the Research Lab 4 course, I wrote a paper about the similarities and differences, advantages and disadvantages of the two well known compression techniques: Fourier and Wavelets. JPEG, JPEG2000, DiVX and MPEG, all of them are based on one of these two techniques.

Research Paper (3.8 MB PDF) (5.5 MB PS)

Presentation (1.9MB PPT) (2.2MB PDF) (HTML)

Hypercomputation

Maurice Samulski — Sun, 01 May 2005 18:15:05 +0000

Currently, hypercomputation is still very theoretical and there is still enough to discuss. Hypercomputation concerns the study of computation beyond that defined by the Turing machine. It is a multi-disciplinary research area across a wide variety of fields, including computer science, philosophy, physics, electronics, biology and artifical intelligence.

For a seminar to be given at the university, I’ve written with two fellow students a paper about the pre-hypercomputation history, explanation of hypercomputation and the philosphy of hypercomputation and artificial intelligence.

Paper (DUTCH) (518 KB PDF) (1.1 MB PS)

Presentation (ENGLISH) (1.6 MB PPT) (744 KB PDF)

Other interesting papers about hypercomputation:

Hypercomputation: computing more than the Turing machine, Toby Ord, 2002.
An introduction to the burgeoning field of hypercomputation – the study of machines that can compute more than Turing machines.

Computing Machines Can’t Be Intelligent (And Turing Said So), Peter Kugel, Computer Science Department, Boston College, 2001.
According to the conventional wisdom, Turing (1950) said that computing machines can be Intelligent. I don’t believe it. I think that what Turing really said was that computing machines computers limited to computing can only fake intelligence.

Toward a Formal Philosophy of Hypercomputation, Selmer Bringsjord and Michael Zenzen, 2002.
A survey of the field of hypercomputation, including discussion of a variety of objections.

Hypercomputation: philosophical issues, B. Jack Copeland, 2003.
A survey of the field of hypercomputation, including discussion of four a priori objections to the possibility of hypercomputation. An exegesis of Turing’s pre- and post-war writings on the mind is given, and Turing’s views on the scope of machines are discussed.

Observational Research on TVs

Maurice Samulski — Fri, 01 Apr 2005 17:37:29 +0000

During a marketing high tech products class I participated in a group project and did some observational research on self promoting television sets for Philips Consumer Electronics. Our goal was to deliver ideas to Philips Consumer Electronics for the promotion of televisions in television shops by observing people who are buying a new TV set.

Paper (142 KB PDF)