| 1. |
- van den Elzen, Stef, et al.
(författare)
-
The Flow of Trust : A Visualization Framework to Externalize, Explore, and Explain Trust in ML Applications
- 2023
-
Ingår i: IEEE Computer Graphics and Applications. - : IEEE Computer Society. - 0272-1716 .- 1558-1756. ; 43:2, s. 78-88
-
Tidskriftsartikel (refereegranskat)abstract
- We present a conceptual framework for the development of visual interactive techniques to formalize and externalize trust in machine learning (ML) workflows. Currently, trust in ML applications is an implicit process that takes place in the user-s mind. As such, there is no method of feedback or communication of trust that can be acted upon. Our framework will be instrumental in developing interactive visualization approaches that will help users to efficiently and effectively build and communicate trust in ways that fit each of the ML process stages. We formulate several research questions and directions that include: 1) a typology/taxonomy of trust objects, trust issues, and possible reasons for (mis)trust; 2) formalisms to represent trust in machine-readable form; 3) means by which users can express their state of trust by interacting with a computer system (e.g., text, drawing, marking); 4) ways in which a system can facilitate users- expression and communication of the state of trust; and 5) creation of visual interactive techniques for representation and exploration of trust over all stages of an ML pipeline.
|
|
| 2. |
- Milutinovic, Goran
(författare)
-
Computational and Visual Tools for Geospatial Multi-Criteria Decision-Making
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Geospatial multi-criteria decision-making usually concerns quasi-continuous choice models, with the number of alternatives constrained only by the limits of the used representation model. This sets high demands on the decision-making methods used in the context. The most commonly used approach in geospatial decision-making is combining a method for assigning criteria weights with an aggregation method. As pairwise comparison of alternatives is not feasible when the number of alternatives is large, the weights are usually assigned to criteria without considering the values or the value ranges of the alternatives, an approach often criticized in the decision analysis literature. Apart from criteria weighting controversy, this approach does not allow for advanced use of interactive visualization in the choice phase of the decision-making process. In this thesis, two alternative methods for geospatial decision-making based on the even swaps method are developed. The first method relies on automation of swaps, which makes this method viable for decision problems with any number of alternatives. The second method emanates from the findings of behavioral decision theory, and combines even swaps with reduction of large data sets through quasi-satisficing, allowing for efficient use of interactive visualization in the choice phase of the decision process. Visualization frameworks for both methods are also developed in the thesis. They include both geo-specific representations, such as interactive maps, and infovis techniques such as graphs, diagrams, scatterplots and parallel coordinates. Two studies concerning the impact of interactive visualization on decision-making are presented in the thesis: a study concerning the impact of interactive visualization on geospatial decision-making, and a study concerning potential effects of visual saliency on decision-making. The results of the first study indicated positive effects of interactive visualization on coherency and consistency in performing trade-offs. The results of the second study show that visual saliency may help decision-makers make better decisions. The work presented in this thesis contributes to method development and the use of interactive visualization in the context of geospatial decision-making.
|
|
| 3. |
- Nanni, Mirco, et al.
(författare)
-
Give more data, awareness and control to individual citizens, and they will help COVID-19 containment
- 2020
-
Ingår i: Transactions on Data Privacy. - : Institut d'Investigació en Intel·ligència Artificial. - 1888-5063 .- 2013-1631. ; 23, s. 1-6
-
Tidskriftsartikel (refereegranskat)abstract
- The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the "phase 2" of the pandemic, when lockdown and other restriction measures are progressively withdrawn, in order to avoid or minimize contagion resurgence. For this purpose, contact-tracing apps are being proposed for large scale adoption by many countries. A centralized approach, where data sensed by the app are all sent to a nation-wide server, raises concerns about citizens' privacy and needlessly strong digital surveillance, thus alerting us to the need to minimize personal data collection and avoiding location tracking. We advocate the conceptual advantage of a decentralized approach, where both contact and location data are collected exclusively in individual citizens' "personal data stores", to be shared separately and selectively (e.g., with a backend system, but possibly also with other citizens), voluntarily, only when the citizen has tested positive for COVID-19, and with a privacy preserving level of granularity. This approach better protects the personal sphere of citizens and affords multiple benefits: it allows for detailed information gathering for infected people in a privacy-preserving fashion; and, in turn this enables both contact tracing, and, the early detection of outbreak hotspots on more finely-granulated geographic scale. The decentralized approach is also scalable to large populations, in that only the data of positive patients need be handled at a central level. Our recommendation is two-fold. First to extend existing decentralized architectures with a light touch, in order to manage the collection of location data locally on the device, and allowthe user to share spatio-temporal aggregates - if and when they want and for specific aims - with health authorities, for instance. Second, we favour a longerterm pursuit of realizing a Personal Data Store vision, giving users the opportunity to contribute to collective good in the measure they want, enhancing self-awareness, and cultivating collective efforts for rebuilding society.
|
|
