Academic


Post Academia

Certifications
  • AWS Certified Big Data - Specialty
    Amazon Web Services, BDS-C
  • AWS Certified Solutions Architect - Associate
    Amazon Web Services, SAA-C
  • AWS Certified Cloud Practitioner
    Amazon Web Services, CLF-C
  • Professional Scrum with Kanban
    Scrum.org, PSK-I
Publications
  • A. Notten, A. Surpatean, B. Sanditov, and J. Jacob, Follow-up: Inventory of the patents and publications of FP7 projects in the field of ICT, European Commission, Digital Single Market Reports and Studies, 2018.
    Data
  • A. Notten, A. Surpatean, B. Sanditov, and J. Jacob, Inventory of the patents and publications of FP7 projects in the field of ICT, European Commission, Digital Single Market Reports and Studies, 2015.
    Data

Master of Science in Artificial Intelligence, Cum Laude

Department of Knowledge Engineering, Maastricht University, The Netherlands
School of Information Technology, Transnational University Limburg
Focus: Machine Learning, Data Mining, Recommender Systems

Publications
  • A. Surpatean, Recommender System for Diverse Educational Programmes: Solving Diverse Recommendation Problems with one Unifying Recommender, Department of Knowledge Engineering, Maastricht University, the Netherlands, 2013.
    Master Thesis
    Recommender systems are everywhere in the digital world, shaping the choices we make, the products we buy, the books we read, or movies we watch. Few recommender systems exist, however, for the academic domain, where they could help students choose courses or academic programs. This thesis focuses on building a recommender system for this academic context, capable of supporting the needs of various types of academic departments.
    The main recommendation methods are analysed: content-based filtering, collaborative filtering, and demographic filtering; and different hybridization techniques are described. The idea of a single unifying model, a hybrid system with a statistical model that incorporates knowledge about items, users, and ratings, simultaneously, is introduced. The unifying hybrid framework is built and evaluated against the non-hybrid systems, using actual academic data from two different types of educational departments.
  • L. Wang, A. Notten, and A. Surpatean, Interdisciplinarity of nano research fields: a keyword mining approach, Scientometrics, vol. 94, pp. 877-892, Springer, 2013.
    Peer Reviewed Journal Article DOI  10.1007/s11192- At Publisher  Springer
    Using a keyword mining approach, this paper explores the interdisciplinary and integrative dynamics in five nano research fields. We argue that the general trend of integration in nano research fields is converging in the long run, although the degree of this convergence depends greatly on the indicators one chooses. Our results show that nano technologies applied in the five studied nano fields become more diverse over time. One field learns more and more related technologies from others. The publication and citation analysis also proves that nano technology has developed to a relatively mature stage and has become a standardized and codified technology.
  • A. Surpatean, E. Smirnov, and N. Manie, Master Orientation Tool, in ECAI 2012 - 20th European Conference on Artificial Intelligence, 27–31 August 2012, Montpellier, France – Including Prestigious Applications of Artificial Intelligence (PAIS-2012) System Demonstrations Track, Montpellier, France, 2012, pp. 995-996.
    Peer Reviewed Conference Paper DOI  10.3233/978-1-6 At Publisher  IOS Press
    This paper describes our work on developing a Master Orientation Tool for University College Maastricht (UCM). UCM Bachelor students use the tool to discover Master programs that fit their academic profiles. The tool includes a memory-based collaborative recommender system. The system memory contains data on academic profiles of UCM alumni students, labeled by the Master programs they have chosen. The tool operates as a collaborative system: given the academic profile of a Bachelor student, it recommends Master programs for that student based on the proximity of her profile to the profiles of the alumni. The Master Orientation Tool allows students to modify their own profiles and thus to explore alternatives in their study and how they influence their Master program possibilities. The tool is operational at UCM since September 2011 and is popular among the students.
  • A. Surpatean, E. Smirnov, and N. Manie, Similarity Functions for Collaborative Master Recommendations, in 5th International Conference on Educational Data Mining, Chania, Greece, 2012, pp. 230-231.
    Peer Reviewed Conference Paper At Publisher  EDM
    A memory-based collaborative system for recommending Master programs has been recently developed for University College Maastricht (UCM). Given the academic profile of a Bachelor student, the system recommends Master programs for that student based on the similarity of her profile to the profiles of the alumni students. The system is operational since September 2011 and is already popular among the UCM students. This paper considers the question of how to improve the quality of Master recommendations. For that purpose we study several academic profile representations and similarity functions. We identify the best representation strategy and show how to combine recommender systems based on different similarity functions to achieve superior Master recommendations.
Conferences
  • 7th International Conference on Prestigious Applications of Intelligent Systems (PAIS-2012),
    at the 20th European Conference on Artificial Intelligence (ECAI 2012), Montpellier, France, 2012.

    Poster Presenter with the Conference Paper
    A. Surpatean, E. Smirnov, and N. Manie, Master Orientation Tool, in ECAI 2012 - 20th European Conference on Artificial Intelligence, 27–31 August 2012, Montpellier, France – Including Prestigious Applications of Artificial Intelligence (PAIS-2012) System Demonstrations Track, Montpellier, France, 2012, pp. 995-996.
    Peer Reviewed Conference Paper DOI  10.3233/978-1-6 At Publisher  IOS Press
    This paper describes our work on developing a Master Orientation Tool for University College Maastricht (UCM). UCM Bachelor students use the tool to discover Master programs that fit their academic profiles. The tool includes a memory-based collaborative recommender system. The system memory contains data on academic profiles of UCM alumni students, labeled by the Master programs they have chosen. The tool operates as a collaborative system: given the academic profile of a Bachelor student, it recommends Master programs for that student based on the proximity of her profile to the profiles of the alumni. The Master Orientation Tool allows students to modify their own profiles and thus to explore alternatives in their study and how they influence their Master program possibilities. The tool is operational at UCM since September 2011 and is popular among the students.
  • The 5th International Conference on Educational Data Mining (EDM2012), Chania, Greece, 2012.
    Poster Presenter with the Conference Paper
    A. Surpatean, E. Smirnov, and N. Manie, Similarity Functions for Collaborative Master Recommendations, in 5th International Conference on Educational Data Mining, Chania, Greece, 2012, pp. 230-231.
    Peer Reviewed Conference Paper At Publisher  EDM
    A memory-based collaborative system for recommending Master programs has been recently developed for University College Maastricht (UCM). Given the academic profile of a Bachelor student, the system recommends Master programs for that student based on the similarity of her profile to the profiles of the alumni students. The system is operational since September 2011 and is already popular among the UCM students. This paper considers the question of how to improve the quality of Master recommendations. For that purpose we study several academic profile representations and similarity functions. We identify the best representation strategy and show how to combine recommender systems based on different similarity functions to achieve superior Master recommendations.
  • Leading in Learning Seminar, Maastricht, the Netherlands, 2011
    Poster Presenter
    A. Surpatean, E. Smirnov, Mining Student and Curriculum Data, Department of Knowledge Engineering, Maastricht University, Maastricht, the Netherlands, 2012.
    Poster Presentation
Achievements
  • Student Program on Entrepreneurship
    Nomination by Studenten Ondernemersprijs;  Finalist
  • Studiesucces Grant, Maastricht University
    Attracted Research Funding
  • Education Prize Nomination, Maastricht University
    Nomination
  • Leading in Learning Grant, Maastricht University
    Attracted Research Funding

Bachelor of Arts in Liberal Arts and Sciences, Cum Laude

University College Maastricht, Maastricht University, The Netherlands
Focus: Computer Science, Math, Artificial Intelligence

Publications
  • A. Surpatean, Non-choreographed Robot Dance, MaRBLe Research Papers, vol. 1, pp. 137-163, 2011.
    Invited Journal Article
    Journal ISBN  9789056813710
    A. Surpatean, Non-choreographed Robot Dance, Department of Knowledge Engineering, Maastricht University, Maastricht, the Netherlands, 2010.
    Original Report
    This paper describes an attempt of teaching the Nao robot to dance on music. This research has tried to move away from the current choreographed approaches to Nao dance, and investigate how to make the robot dance in a non-predefined fashion. Aspects of both music and dance are investigated, and descriptions of how such elements were implemented in practice are presented. Moreover, focus has been put not only on the analysis of music's beat in order to build a dance, but other elements of music as well. The paper concludes by describing aspects that still need to be tackled in the future before the Nao can truly perform a non-choreographed dance.
  • A. Surpatean, Proposing an Individualized Approach for Keyboard Adjustments Advice, University College Maastricht, Maastricht University, the Netherlands, 2010.
    Bachelor Thesis
    Ever since the advent of interactive computing, the keyboard has been the main input device, and until now it proved to be resilient to changes. Recent advances in technology however, most notably the virtual keyboard on touch screens, make it possible to easily change both the key order and the physical shape of the keyboard, under program control. This opens the possibility of tailoring a keyboard to a user's individual needs, potentially making it more usable. The current paper investigates the three main keyboard layouts available, QWERTY, Dvorak, and Colemak, and compares them in a visual manner, in order to uncover whether there do exist differences between these layouts that could classify one as better than others. The analysis is then made on texts from different user types, and on real typing monitored from two students, in order to investigate whether all users would benefit similarly from a change in layout. The claim of this paper is that advice regarding keyboard changes should be given on an individualized basis, and supported by data provided by continuous monitoring of user's typing behavior.
Conferences
  • Curious!?, Maastricht, the Netherlands, 2011
    Poster Presenter
    A. Surpatean, Non-choreographed Robot Dance, MaRBLe Research Papers, vol. 1, pp. 137-163, 2011.
    Invited Journal Article
    Journal ISBN  9789056813710
    A. Surpatean, Non-choreographed Robot Dance, Department of Knowledge Engineering, Maastricht University, Maastricht, the Netherlands, 2010.
    Original Report
    This paper describes an attempt of teaching the Nao robot to dance on music. This research has tried to move away from the current choreographed approaches to Nao dance, and investigate how to make the robot dance in a non-predefined fashion. Aspects of both music and dance are investigated, and descriptions of how such elements were implemented in practice are presented. Moreover, focus has been put not only on the analysis of music's beat in order to build a dance, but other elements of music as well. The paper concludes by describing aspects that still need to be tackled in the future before the Nao can truly perform a non-choreographed dance.
  • New Newer News: The Changing Face of Media, Maastricht, the Netherlands, 2009
    Conference Co-organizer Workshop Organizer & Host of
    A. Surpatean, Privacy in a 2.0 World, in New Newer News: The Changing Face of Media, Maastricht, the Netherlands, 2009.
    Workshop Proceeding
    We live today in a participatory society, where everybody is transformed from passive consumer to creator of information. Some call it a world of user generated content.
    It is though worrying that the user does not always grasp the amount of content that he is generating. We think we are doing a Google search, but our search terms are analyzed and stored. We think we are accessing a simple website, but our browsing patterns are monitored and used for better advertisement placement. We think we share our lives with friends and family, but do we know how public our lives become? The truth of this new world is that the vast majority of our actions result in the creation of electronic data. Some content we share voluntarily, when using applications such as social networking sites. Other information is gathered in the background, by monitoring our actions.
    Although this enables the creation of better services personalized to our needs, it also creates a new set of threats, of which the majority of people are unaware. My workshop will investigate such pitfalls of the 2.0 world. It will not be intended to scare participants away from these technologies, but to make them aware of the issues that might arise when using these new technologies. It will provide a discussion on the amount of information that we are generating, and help participants make informed decisions about how much they want to expose from their private lives.
Achievements
  • Cum Laude
    Distinction
  • Top 3% Award
    Scholarship

High school

Dr. Ioan Mesota National College, Brasov, Romania
Mathematics - Informatics / Mathematics - Informatics bilingual German

Achievements
  • County Olympiad of Computer Science, Brasov, Romania, 12th Grade
    Diploma
  • National Olympiad of Computer Science, Focsani, Romania, 12th Grade
    Diploma
  • American Computer Science League "Continental Contest", 12th Grade
    Diploma
  • Professional Certificate of Computer Science
    Professional Certificate
  • County Olympiad of Computer Science, Brasov, Romania, 11th Grade
    1st Prize
  • National Computer Science Contest "InfoEducatie", Galaciuc, Romania, 11th Grade
    Diploma
  • American Computer Science League "Continental Contest", 11th Grade
    1st Place
  • American Computer Science League "All Star" Contest, Montreal, Canada, 11th Grade
    Diploma
  • Special Award for the American Computer Science League "All Star" Contest, issued by the City hall of Brasov, Romania, 11th Grade
    Special Award
  • Inter-county Computer Science Contest "Stefan Odobleja", Craiova, Romania, 11th Grade
    1st Prize
  • County Olympiad of Computer Science, Brasov, Romania, 10th Grade
    3rd Prize
  • National Olympiad of Computer Science, Bacau, Romania, 10th Grade
    Diploma
  • Diploma of Excellence for the National Olympiad of Computer Science, issued by the School Inspectorate of Brasov County, Romania, 10th Grade
    Diploma of Excellence
  • American Computer Science League "Continental Contest", 10th Grade
    1st Place
  • American Computer Science League "All Star" Contest, Miami, Florida, 10th Grade
    Diploma
  • GR8 Programs Contest "Didactic" Section, Brasov, Romania, 9th Grade
    Diploma
  • GR8 Programs Contest "Games" Section, Brasov, Romania, 9th Grade
    2nd Prize
  • GR8 Programs Contest, Brasov, Romania, 9th Grade
    Special Prize
  • County Olympiad of Computer Science, Brasov, Romania, 9th Grade
    1st Prize