Adaptive kansei search method using user's subjective criterion deviation. - In: International journal of computer vision and image processing, ISSN 2155-6997, Bd. 1 (2011), 1, S. 14-26
Sensibility-vectors (kansei-vectors) are useful for retrieving objects like pictures, music, perfumes, and apparels on the Internet. The sensibility-vector is an array of values, each indicating a degree of feeling or impression represented as sensibility word or kansei word. However, even such an approach leaves a gap between user's subjective sensibility (image, feeling) value and the corresponding one stored in the database. This paper proposes a search method to automatically and adaptively decrease such gaps by estimating a subjective criterion deviation (SCD) of the user's search histories and fuzzy modeling. Conventional methods need tests and questionnaires beforehand to infer user's individual sensibility to his or her instinct or impression. The proposed method automatically decreases such gaps without users' burden caused by such conventional methods as requiring questionnaires. Moreover, this method reflects the dynamic changes in user's preferences. Namely, this method does not need to know user's preferences beforehand with questionnaires. An experiment was conducted by building and using a perfume search system. Experimental data results showed that the proposed method is effective.
Ensuring diversity in a backtrack and GA optimization method for delivery schedule. - In: Seventh International Conference on Signal-Image Technology and Internet-Based Systems (SITIS), 2011, ISBN 978-1-4673-0431-3, (2011), S. 201-208
Modeling, processing, evaluating and refining social processes is a widely deployed in fields like marketing, but becomes more and more a trend in learning systems, too. The higher the degree for formalization in such models, the better the chances to employ Knowledge Engineering methods such as data mining to it to reveal "hidden knowledge" within the data. Here, we introduce a concept to optimize university learning processes. In particular, individual university curricula are subject to a so called "lazy" Data Mining method on students' data and replaces a formerly developed explicit modeling approach ("eager" Data Mining). A formerly developed concept called storyboarding has been applied at a university to model the various ways to study at this university. Along with this storyboard, we formerly developed a data mining technology to estimate success chances of curricula. Here, we discuss chances to improve these results by implementing a student profiling concept that represents the students' individual educational history and a self estimation about intellectual traits and vocational ambitions.
http://dx.doi.org/10.1109/SITIS.2011.15
A simple optimization method based on Backtrack and GA for delivery schedule. - In: IEEE Congress on Evolutionary Computation (CEC), 2011, ISBN 978-1-4244-7834-7, (2011), S. 2790-2797
http://dx.doi.org/10.1109/CEC.2011.5949968
Attitudes of German university students towards the integration of innovation information technology. - In: The international journal of engineering education, ISSN 0949-149X, Bd. 27 (2011), 2, S. 431-446
A data mining method for the optimization of learning processes. - In: Proceeding of the IRAST International Congress on Computer Applications and Computational Science (CACS 2010), ISBN 978-981-086846-8, (2010), S. 77-80
A knowledge engineering method to represent and optimize learning processes and its empirical validation. - In: Sixth International Conference on Signal-Image Technology and Internet Based Systems (SITIS), 2010, ISBN 978-1-4244-9527-6, (2010), S. 203-210
http://dx.doi.org/10.1109/SITIS.2010.43
Evaluation of enriched cyberspace for adaptive support of remote collaboration. - In: Sixth International Conference on Signal-Image Technology and Internet Based Systems (SITIS), 2010, ISBN 978-1-4244-9527-6, (2010), S. 225-232
http://dx.doi.org/10.1109/SITIS.2010.46
Backtrack and restart genetic algorithm to optimize delivery schedule. - In: Sixth International Conference on Signal-Image Technology and Internet Based Systems (SITIS), 2010, ISBN 978-1-4244-9527-6, (2010), S. 85-92
http://dx.doi.org/10.1109/SITIS.2010.24
Proposal and evaluation of adaptive multimedia utilization method for reliable web based collaboration. - In: Fifth International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), 2009, ISBN 978-1-4244-5740-3, (2010), S. 385-392
Due to the geographical distribution, different cognitive capacity, and different domain competency of workers or learners, many misunderstandings can occur during Web based remote collaboration, leading to inefficient discussions and undesired results. - To overcome these problems, ag Multimedia adaptive utilization framework for dependable web based collaboration is proposed and evaluated. This assesses situations of remote users through fusing information of multiple biological sensors and the related contexts such as user profiles. Transmitting and using such information, the system adaptively supports Web based remote collaboration by stressing, warning, and presenting keywords/ summaries in multimedia. - Then, effects of adaptive keyword/summary presentation are evaluated as to cognitive profiles of users such as short term memory capacity and associative learning skills when misunderstanding possibilities are estimated on the Web. These evaluations totally demonstrate the feasibility and usefulness of the proposed method.
http://dx.doi.org/10.1109/SITIS.2009.67
A search method that can dynamically learn user's subjective feeling. - In: Fifth International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), 2009, ISBN 978-1-4244-5740-3, (2010), S. 221-227
http://dx.doi.org/10.1109/SITIS.2009.44