The study presented in the article focuses on keystroke dynamics analysis applied to recognize emotional states and to authenticate users. An overview of some studies and applications in these areas is presented. Then, an experiment is described, i.e. the way of collecting data, extracting features, training classifiers and finding out the most appropriate feature subsets. The results show that it is difficult to indicate a universal sets of features for the defined tasks and the best idea is to individually adapt models to users.
The article presents a research study on recognizing therapy progress among children with autism spectrum disorder. The progress is recognized on the basis of behavioural data gathered via five specially designed tablet games. Over 180 distinct parameters are calculated on the basis of raw data delivered via the game flow and tablet sensors - i.e. touch screen, accelerometer and gyroscope. The results obtained confirm the possibility of recognizing progress in particular areas of development. The recognition accuracy exceeds 80%. Moreover, the study identifies a subset of parameters which appear to be better predictors of therapy progress than others. The proposed method - consisting of data recording, parameter calculation formulas and prediction models - might be implemented in a tool to support both therapists and parents of autistic children. Such a tool might be used to monitor the course of the therapy, modify it and report its results.
Te paper reports current stage of the project Automated Terapy Monitoring for Children with Developmental Disorders of Autism Spectrum (AUTMON), that aims at development of methods and tools to allow for the automatic evaluation of the therapy progress among children with autism. Finding objective measures suitable for evaluating therapy progress would let create a system supporting those who diagnose autism and the therapists working with the children. In future these measures could be also applied as optimization criteria in defning the optimal therapy path. Such tool could be helpful in preparing the therapy plan, choosing the type of tasks and their frequency. It might also follow the therapy course, predict its direction and indicate the points which probably require intervention and changing the plan. Obviously it would never replace a therapist, but make his work more eﬀective. Moreover, it could also support the parents in their eﬀorts to objectively report valuable observations to the therapists, which would be especially important in the case of a limited access to therapy centers.
The paper regards supporting behavioral therapy of autistic children with mobile applications, specifically applied for measuring the child’s progress. A family of five applications is presented, that was developed as an investigation tool within the project aimed at automation of therapy progress monitoring. The applications were already tested with children with autism spectrum disorder. Hereby we analyse children’ experience with the games, as a positive attitude towards the application is the key factor enabling practical application of the solutions in therapy. Two evaluation methods were applied: a behavioral study of video recordings of children interaction with the games and online behavioral tagging performed during measurement sessions. The paper also outlines the main challenges, encountered during sessions with autistic children. The study might be interesting for both researchers and practitioners applying e-technologies in autistics therapy
Purpose The purpose of this paper is to answer the question whether it is possible to recognise the gender of a web browser user on the basis of keystroke dynamics and mouse movements. Design/methodology/approach An experiment was organised in order to track mouse and keyboard usage using a special web browser plug-in. After collecting the data, a number of parameters describing the users’ keystrokes, mouse movements and clicks were calculated for each data sample. Then several machine learning methods were used to verify the stated research question. Findings The experiment showed that it is possible to recognise males and females on the basis of behavioural characteristics with an accuracy exceeding 70 per cent. The best results were obtained while using Bayesian networks. Research limitations/implications The first limitation of the study was the restricted contextual information, i.e. neither the type of web page browsed nor the user activity was taken into account. Another is the narrow scope of the respondent group. Future work should focus on gathering data from more users covering a wider age range and should consider the context. Practical implications Automatic gender recognition could be used in profiling a user to create personalised websites or as an additional feature in automatic identification for security reasons. It might be also considered as a confirmation of declared gender in web-based surveys. Social implications As not all users perceive personalised ads and websites as beneficial, this application requires the analysis of a user perspective to provide value to the consumer without privacy violation. Originality/value Behavioural characteristics, such as mouse movements and keystroke dynamics, have already been used for user authentication and emotion recognition, but applying these data to gender recognition is an original idea.
The paper concerns accuracy of emotion recognition from facial expressions. As there are a couple of ready off-the-shelf solutions available in the market today, this study aims at practical evaluation of selected solutions in order to provide some insight into what potential buyers might expect. Two solutions were compared: FaceReader by Noldus and Xpress Engine by QuantumLab. The performed evaluation revealed that the recognition accuracies differ for photo and video input data and therefore solutions should be matched to the specificity of the application domain.
The article describes the idea of detecting stress among programmers on the basis of keystroke dynamics. An experiment with a group of students of artificial intelligence classes was performed. Two samples of keystroke data were recorded for each case, the first while programming without stress, the second under time pressure. A number of timing and frequency parameters were calculated for each sample. Then statistical analysis was performed to evaluate the significance of keystroke parameters changes. It turned out that some of the defined features might be indicators of being stressed.
In this paper a set of comprehensive evaluation criteria for affect-annotated databases is proposed. These criteria can be used for evaluation of the quality of a database on the stage of its creation as well as for evaluation and comparison of existing databases. The usefulness of these criteria is demonstrated on several databases selected from affect computing domain. The databases contain different kind of data: video or still images presenting facial expressions, speech recordings and affect-annotated words.
The chapter concerns emotional states representation and modeling for software systems, that deal with human affect. A review of emotion representation models is provided, including discrete, dimensional and componential models. The paper provides also analysis of emotion models used in diverse types of affect-aware applications: games, mood trackers or tutoring systems. The analysis is supported with two design cases. The study allowed to reveal, which models are most intensively used in affect-aware applications as well as to identify the main challenge of mapping between the models.
The article describes a research on recognizing emotional states on the basis of keystroke dynamics. An overview of various studies and applications of emotion recognition based on data coming from keyboard is presented. Then, the idea of an experiment is presented, i.e. the way of collecting and labeling training data, extracting features and finally training classifiers. Different classification approaches are proposed to be tested: universal vs. individual models, multiclass vs. two-class. The obtained results reveal which of these approaches are appropriate for the given task. The individual two-class models turn out to be the most accurate.