Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 4

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

QUALITY FUNCTION DEPLOYMENT FOR DESIGNING COLLABORATIVE WORKING ENVIRONMENTS

100%

Pankiewicz M.

Information Systems in Management

2015

tom 4

nr 4

276-284

This paper presents quality-oriented approach to designing Collaborative Working Environments (CWE) - socio-technical systems, in which technology is mediating human interactions for purposes of group cooperation. Both technical and social aspects of virtual collaboration are characterized by high level of complexity, therefore process of designing CWE’s should benefit from approach supporting such complexity. It will be shown, how the Quality Function Deployment method, used for managing the development of complex products, can be utilized into the process of designing such systems.

Elo Rating Algorithm for the Purpose of Measuring Task Difficulty in Online Learning Environments

63%

Pankiewicz M. , Bator M.

e-mentor

2019

nr 5 (82)

43-51

The Elo rating algorithm, developed for the purpose of measuring player strength in chess tournaments, has also found application in the context of educational research and has been used for the purpose of measuring both learner ability and task difficulty. The quality of the estimations performed by the Elo rating algorithm has already been subject to research, and has been shown to deliver accurate estimations in both low and high-stake testing situations. However, little is known about the performance of the Elo algorithm in the context of learning environments where multiple attempts are allowed, feedback is provided, and the learning process spans several weeks or even months. This study develops the topic of Elo algorithm use in an educational context and examines its performance on real data from an online learning environment where multiple attempts were allowed, and feedback was provided after each attempt. Its performance in terms of stability of the estimation results in two analyzed periods for two groups of learners with different initial levels of knowledge are compared with alternative difficulty estimation methods: proportion correct and learner feedback. According to the results, the Elo rating algorithm outperforms both proportion correct and learning feedback. It delivers stable difficulty estimations, with correlations in the range 0.87–0.92 for the group of beginners and 0.72–0.84 for the group of experienced learners.

Image annotating tools for agricultural purpose : a requirements study

63%

Bator M. , Pankiewicz M.

Machine Graphics and Vision

2019

tom Vol. 28, No. 1/4

69--77

Images of natural scenes, like those relevant for agriculture, are characterised with a variety of forms of objects of interest and similarities between objects that one might want to discriminate. This introduces uncertainty to the analysis of such images. Requirements for an image annotation tool to be used in pattern recognition design for agriculture were discussed. A selection of open source annotating tools were presented. Advices how to use the software to handle uncertainty and missing functionalities were described.

Color transformation method that preserves the impression of texture in virtual makeover system

63%

Kaczmarczyk J. , Pankiewicz M.

Machine Graphics and Vision

2013

tom Vol. 22, No. 1/4

27--35

The algorithms of color transformation that preserves the impression of texture are used in virtual makeover systems, where maintaining the impression of unaltered texture is important in the process of transforming the color. The content of this paper covers the process of implementing the algorithm of digital picture color transformation with its main objective – minimizing its inﬂuence on the texture structure. The main idea of the presented algorithm is to determine the area in HSV space that consists of the original picture pixels and then, to move it towards the target color in such a way that every color is moved by the same vector, limited only by the fact that the transformation is not always possible. The analysis of the algorithm was conducted based on fragments of real face photographs. Its results were compared on the basis of measures estimated on the run length matrix and the co-occurrence matrix.