Ivo Maly

Creation and Visualization of User Behavior in Ambient Intelligent Environment

Ambient intelligence is a rapidly developing field producing a new generation of applications and services demanding new, more complex strategies for usability testing and evaluation. In this paper, we identify caveats of traditional methods of application usability testing when applied to an ambient intelligent environment and we introduce a method for unified analysis of user behavior using a virtual environment visualization. For the usability testing in ambient environments, we propose to transform data (both data recorded in real settings and data artificially created by experts) into a virtual environment to cope with the following issues: a) overwhelming amount of data, b) proprietary data formats, and c) ethical codices issues. We describe a tool for creation of expert evaluation data and for transformation of data from video recordings and illustrate its use on two cases.

Interactive analytical tool for usability analysis of mobile indoor navigation application

Mobile navigation applications are the ones that must be tested in real environment in order to show their usability problems. Preparation of the study in real environment is complex issue and so is the analysis of the collected data from such study. Therefore we performed usability study of mobile navigation application for visually impaired users and implemented a set of visualization plugins for IVE tool. IVE tool and visualization plug-ins were used for pre-processing and for visual analysis of collected data from the usability study of mobile indoor navigation application. We found that with IVE we were able to find approximately same amount of usability issues as without this tool, but the IVE tool increased the speed of preprocessing and annotation creation i.e. the time necessary for the analysis has been reduced.

Visualization of users' activities in a specific environment

Evaluation of user interface design is usually based on usability testing methods. In this paper we analyzed and described the user behavior in the form of the user model. The user model is built on a data set which was acquired through observation of user behavior. The criterion we use for the evaluation of the usability of interface design is the user cognitive load. We present different tools for visualization, simulation and easier analysis of the user model. Because each of the methods and tools presented use only part of the user model, in the end we present methods on how to use the complete user model to correctly describe user behavior. In order to understand such a complex model we need to have a proper visualization tool. The concept of such a visualization tool is presented at the end of this paper.

An evaluation tool for research of user behavior in a realistic mobile environment

User behavior is significantly influenced by the surrounding environment. Especially complex and dynamically changing environments (like mobile environment) are represented by a wide variety of extraneous variables, which influence the user behavior in an unpredictable and mostly uncontrolled way. For researchers, it is challenging to measure and analyze the user behavior in such environments. We introduce a complex tool—the IVE tool—which provides a unique way of context visualization and synchronization of measured data of various kinds. Thanks to this tool it is possible to efficiently evaluate data acquired during complex usability tests in a mobile environment. The functionality of this tool is demonstrated on the use case “Navigation of visually impaired users in the building with support of a navigation system called NaviTerier.” During the experiment, we focused on collection and analysis of data that may show user stress and which may influence his/her ability to navigate. We analyzed objective data like Galvanic Skin Response parameter (GSR), Heart Rate Variability parameters (HRV) and audio video recordings and also subjective data like the user’s subjective stress feeling and observation of the user’s behavior.

Navigation Dialog of Blind People: Recovery from Getting Lost

Navigation of blind people is different from the navigation of sighted people and there is also difference when the blind person is recovering from getting lost. In this paper we focus on qualitative analysis of dialogs between lost blind person and navigator, which is done through the mobile phone. The research was done in two outdoor and one indoor location. The analysis revealed several areas where the dialog model must focus on detailed information, like evaluation of instructions provided by blind person and his/her ability to reliably locate navigation points.

Navigation Problems in Blind-to-Blind Pedestrians Tele-assistance Navigation

We raise a question whether it is possible to build a large-scale navigation system for blind pedestrians where a blind person navigates another blind person remotely by mobile phone. We have conducted an experiment, in which we observed blind people navigating each other in a city center in 19 sessions. We focused on problems in the navigator’s attempts to direct the traveler to the destination. We observed 96 problems in total, classified them on the basis of the type of navigator or traveler activity and according to the location in which the problem occurred. Most of the problems occurred during the activities performed by the navigator. We extracted a set of guidelines based on analysis of navigation problems and successful navigation strategies. We have partially mapped the problem of tele-assistance navigation to POMDP based dialogue system.

Framework for Visual Analysis of User Behaviour in Ambient Intelligence Environment

Ambient intelligence is a rapidly developing field that is led by the necessity of ubiquitous computing. People are surrounded by computers in most of their daily activities; i.e. in cars, homes, offices and public areas, and supplied by various services on mobile phones, PDAs, or interactive kiosks. There are several projects that demonstrate potentials of ubiquitous computing, e.g. in a museum (Gallud et al., 2007), in a home (i2home, 2009), or in an office (Waibel, 2009). In our case, the ambient intelligence environment consists of two components, a mechanism for detection of user behaviour and an application that supports specific user scenario or set of scenarios (ambient intelligence applications). Along with increased complexity of the systems and user workflows in an ambient intelligence environment, the usability and functionality of both components must be ensured. Traditional approaches of usability testing are suitable for testing individual components in an isolated manner. However, usability of the whole system can significantly differ from the usability of individual components. A reason for testing of individual components is the inability to setup a complete environment of supporting technologies as they are still under development or yet non-existent in early phases of system design. Unfortunately, these phases are the ones where a correct design decisions are crucial, because they influence further development of the whole system. In this paper we introduce a framework for testing applications in ambient intelligence environments. The concept is derived from the methodologies of desktop application usability testing combined with evaluation of user behaviour in an ambient intelligence environment. It is based on our experience with user behaviour recording, which is visualized and investigated mainly in a virtual environment. The visualization serves as a tool for analyzing complex situations and detection of usability issues in ambient intelligence applications. 4

Web applications usability testing with task model skeletons

Usability testing is technique for analysis of the usability problems of applications, but it requires significant effort to prepare the test and especially to analyze data collected during the test. New techniques such as usage of task models were introduced to improve and speed up the test analysis. Unfortunately, only few applications provide the task model. Therefore, we propose a method and tools for partial reconstruction of the task list and the task model called skeleton. This reconstruction is done from the usability experts application walkthroughs. The task model skeleton is generated automatically, but it should provide similar information during the usability data analysis as manually created full-scaled task model. In order to evaluate usage of the task model skeleton we conducted a usability study with the web e-mail client Roundcube. Results show that the task model skeleton can be used as a good substitution for the manually created task model in usability testing when full-scaled task model is not available.