Experiment on sentiment embedded comparison interface

Objective. In many real-world decision tasks, the information available to the decision maker is incomplete. To account for this uncertainty, we associate a degree of confidence to every decision, representing the likelihood of that decision being correct. In this study, we analyse electroencephalography (EEG) data from 68 participants undertaking eight different perceptual decision-making experiments. Our goals are to investigate (1) whether subject- and task-independent neural correlates of decision confidence exist, and (2) to what degree it is possible to build brain computer interfaces that can estimate confidence on a trial-by-trial basis. The experiments cover a wide range of perceptual tasks, which allowed to separate the task-related, decision-making features from the task-independent ones. Approach. Our systems train artificial neural networks to predict the confidence in each decision from EEG data and response times. We compare the decoding performance with three training approaches: (1) single subject, where both training and testing data were acquired from the same person; (2) multi-subject, where all the data pertained to the same task, but the training and testing data came from different users; and (3) multi-task, where the training and testing data came from different tasks and subjects. Finally, we validated our multi-task approach using data from two additional experiments, in which confidence was not reported. Main results. We found significant differences in the EEG data for different confidence levels in both stimulus-locked and response-locked epochs. All our approaches were able to predict the confidence between 15% and 35% better than the corresponding reference baselines. Significance. Our results suggest that confidence in perceptual decision making tasks could be reconstructed from neural signals even when using transfer learning approaches. These confidence estimates are based on the decision-making process rather than just the confidence-reporting process.

Controlling assistive robots can be challenging for some users, especially those lacking relevant experience. Augmented Reality (AR) User Interfaces (UIs) have the potential to facilitate this task. Although extensive research regarding legged manipulators exists, comparatively little is on their UIs. Most existing UIs leverage traditional control interfaces such as joysticks, Hand-Held (HH) controllers and 2D UIs. These interfaces not only risk being unintuitive, thus discouraging interaction with the robot partner, but also draw the operator’s focus away from the task and towards the UI. This shift in attention raises additional safety concerns, particularly in potentially hazardous environments where legged manipulators are frequently deployed. Moreover, traditional interfaces limit the operators’ availability to use their hands for other tasks. Towards overcoming these limitations, in this article, we provide a user study comparing an AR Head-Mounted Display (HMD) UI we developed for controlling a legged manipulator against off-the-shelf control methods for such robots. This user study involved 27 participants and 135 trials, from which we gathered over 405 completed questionnaires. These trials involved multiple navigation and manipulation tasks with varying difficulty levels using a Boston Dynamics’s Spot, a 7 df Kinova robot arm and a Robotiq 2F-85 gripper that we integrated into a legged manipulator. We made the comparison between UIs across multiple dimensions relevant to a successful human–robot interaction. These dimensions include cognitive workload, technology acceptance, fluency, system usability, immersion and trust. Our study employed a factorial experimental design with participants undergoing five different conditions, generating longitudinal data. Due to potential unknown distributions and outliers in such data, using parametric methods for its analysis is questionable, and while non-parametric alternatives exist, they may lead to reduced statistical power. Therefore, to analyse the data that resulted from our experiment, we chose Bayesian data analysis as an effective alternative to address these limitations. Our results show that AR UIs can outpace HH-based control methods and reduce the cognitive requirements when designers include hands-free interactions and cognitive offloading principles into the UI. Furthermore, the use of the AR UI together with our cognitive offloading feature resulted in higher usability scores and significantly higher fluency and Technology Acceptance Model scores. Regarding immersion, our results revealed that the response values for the AR Immersion questionnaire associated with the AR UI are significantly higher than those associated with the HH UI, regardless of the main interaction method with the former, i.e., hand gestures or cognitive offloading. Derived from the participants’ qualitative answers, we believe this is due to a combination of factors, of which the most important is the free use of the hands when using the HMD, as well as the ability to see the real environment without the need to divert their attention to the UI. Regarding trust, our findings did not display discernible differences in reported trust scores across UI options. However, during the manipulation phase of our user study, where participants were given the choice to select their preferred UI, they consistently reported higher levels of trust compared to the navigation category. Moreover, there was a drastic change in the percentage of participants that selected the AR UI for completing this manipulation stage after incorporating the cognitive offloading feature. Thus, trust seems to have mediated the use and non-use of the UIs in a dimension different from the ones considered in our study, i.e., delegation and reliance. Therefore, our AR HMD UI for the control of legged manipulators was found to improve human–robot interaction across several relevant dimensions, underscoring the critical role of UI design in the effective and trustworthy utilisation of robotic systems.

This paper proposes two validation analyses, namely the risk attitudes and level of confidence for fuzzy multi-criteria decision-making model. Risk attitudes are employed to test the outcomes in dealing with the different decision maker's attitude towards risk and uncertainty. Conversely, confidence analysis are used to test how confidence (i.e., pessimistic, moderate, optimistic, etc.) decision makers make a decision which respect to the difference situation and condition. A case study related to the municipal solid waste disposal decision in the state of Selangor and Kuala Lumpur Federal Territory was used to demonstrate the feasibility of the proposed analysis. The result shows that the proposed analysis can improve the relevance and acceptability of the model. Thus, more confident decision and better solution can be derived concurrently in decision-making process.

Enhancing Humans Trust in Robots through Explanations

Authentication is a ubiquitous task in users' daily lives. The dominant form of user authentication are text passwords. They protect private accounts like online banking, gaming, and email, but also assets in organisations. Yet, many issues are associated with text passwords, leading to challenges faced by both, users and organisations. This thesis contributes to the body of research enabling secure and usable user authentication, benefiting both, users and organisations. To that end, it addresses three distinct challenges. The first challenge addressed in this thesis is the creation of correct, complete, understandable, and effective password security awareness materials. To this end, a systematic process for the creation of awareness materials was developed and applied to create a password security awareness material. This process comprises four steps. First, relevant content for an initial version is aggregated (i.e. descriptions of attacks on passwords and user accounts, descriptions of defences to these attacks, and common misconceptions about password and user account security). Then, feedback from information security experts is gathered to ensure the correctness and completeness of the awareness material. Thereafter, feedback from lay-users is gathered to ensure the understandability of the awareness material. Finally, a formal evaluation of the awareness material is conducted to ensure its effectiveness (i.e. whether the material improves participant's ability to assess the security of passwords as well as password-related behaviour and decreases the prevalence of common misconceptions about password and user account security). The results of the evaluation show the effectiveness of the awareness material: it significantly improved the participants' ability to assess the security of password-related behaviour as well as passwords and significantly decreased the prevalence of misconceptions about password and user account security. The second challenge addressed in this thesis is shoulder-surfing resistant text password entry with gamepads (as an example of very constrained input devices) in shared spaces. To this end, the very first investigation of text password entry with gamepads is conducted. First, the requirements of authentication in the gamepad context are described. Then, these requirements are applied to assess schemes already deployed in the gamepad context and shoulder-surfing resistant authentication schemes from the literature proposed for non-gamepad contexts. The results of this assessment show that none of the currently deployed and only four of the proposals in the literature fulfil all requirements. Furthermore, the results of the assessment also indicate a need for an empirical evaluation in order to exactly gauge the shoulder-surfing threat in the gamepad context and compare alternatives to the incumbent on-screen keyboard. Based on these results, two user studies (one online study and one lab study) are conducted to investigate the shoulder-surfing resistance and usability of three authentication schemes in the gamepad context: the on-screen keyboard (as de-facto standard in this context), the grid-based scheme (an existing proposal from the literature identified as the most viable candidate adaptable to the gamepad context during the assessment), and Colorwheels (a novel shoulder-surfing resistant authentication scheme specifically designed for the gamepad context). The results of these two user studies show that on-screen keyboards are highly susceptible to opportunistic shoulder-surfing, but also show the most favourable usability properties among the three schemes. Colorwheels offers the most robust shoulder-surfing resistance and scores highest with respect to participants' intention to use it in the future, while showing more favourable usability results than the grid-based scheme. The third challenge addressed in this thesis is secure and efficient storage of passwords in portfolio authentication schemes. Portfolio authentication is used to counter capture attacks such as shoulder-surfing or eavesdropping on network traffic. While usability studies of portfolio authentication schemes showed promising results, a verification scheme which allows secure and efficient storage of the portfolio authentication secret had been missing until now. To remedy this problem, the (t,n)-threshold verification scheme is proposed. It is based on secret sharing and key derivation functions. The security as well as the efficiency properties of two variants of the scheme (one based on Blakley secret sharing and one based on Shamir secret sharing) are evaluated against each other and against a naive approach. These evaluations show that the two (t,n)-threshold verification scheme variants always exhibit more favourable properties than the naive approach and that when deciding between the two variants, the exact application scenario must be considered. Three use cases illustrate as exemplary application scenarios the versatility of the proposed (t,n)-threshold verification scheme. By addressing the aforementioned three distinct challenges, this thesis demonstrates the breadth of the field of usable and secure user authentication ranging from awareness materials, to the assessment and evaluation of authentication schemes, to applying cryptography to craft secure password storage solutions. The research processes, results, and insights described in this thesis represent important and meaningful contributions to the state of the art in the research on usable and secure user authentication, offering benefits for users, organisations, and researchers alike.

This study aims to determine the optimal digital literacy possessed by Acces by KAI users and the user interface on train ticket purchase decisions with perceived ease of use as an intervening variable for Millennial and Z Generation Acces by KAI Users in Pasuruan Regency. The sampling technique used is a non-probability sampling method with a puposive sampling sub-technique with a total of 96 respondents. respondents obtained from online questionnaires covering respondents in Pasuruan Regency. This research method uses quantitative methods by analyzing data using descriptive analysis techniques and Path Analysis tests with the help of SPSS version 22. From the results of the study it can be concluded that from the results of the t test, Digital Literacy has a positive and significant effect on Perceive Ease Of Use, User Interface has a positive and significant effect on Perceive Ease Of Use, Digital Literacy has a positive and significant effect on Purchasing Decisions, User Interface has no effect on Purchasing Decisions, Perceive Ease Of Use has a positive and significant effect on Purchasing Decisions. Based on the Sobel Test, Digital Literacy affects Purchasing Decisions through Perceive Ease Of Use as an intervening variable, User Interface affects Purchasing Decisions through Perceive Ease Of Use as an intervening variable.

It takes movie camera operators years of professional training to follow an object in an aesthetically pleasing way, both by classical means (boom, slider) and by drones. As this complex task requires a high workload and situation awareness while controlling the camera, an uncluttered and efficient user interface (UI) is preferred. The emergence of mobile devices and motion control devices incorporating automation made touch-based UIs attractive to operators. Much work has already been done on UI adaptation strategies. However, little work is trying to solve the problem of combining manual control and automation within a UI. Especially with a central premise of minimising occlusion and visual clutter in a cinematic context. We, therefore, conducted a first user study (N=15) to evaluate different design alternatives regarding occlusion and preference. Afterwards, we created a functional prototype of the most promising design. To further reduce the occlusion we applied a progressive reduction adaption strategy. We evaluated the influence of different reduction levels on workload, control, creativity support and precision in a second user study (N=24). While we could reduce the clutter, due to our design decisions we found no negative effects affecting the measured variables.

Past usability studies of metasearch systems have been so far mostly conducted in the academic library context, the results of which might not be applicable to public libraries where the users are much more diverse and generally lack the knowledge about the electronic databases. Using the Hyint 2.0 metasearch system currently available through Taipei Municipal Library as an example, the study proposed a subject-based interface for metasearch system that aims at lowering the cognitive burden for users who are not familiar with online databases. An experimental interface was constructed based on the results of a card sorting study of five reference librarians. A usability study was then conducted, firstly, to compare the performance between the proposed and baseline interfaces; and secondly, to identify usability issues the users might have with the metasearch system. A total of 24 public library users participated in the study, in which they were asked to perform four assigned tasks alternately with the two interfaces. Users’ interactions were logged and their attitudes toward the two interfaces were elicited by the post-search questionnaire. A post-search interview was also conducted with a view to understanding users’ reaction to the metasearch function in general. Furthermore, their search results were judged by the experts as a measurement of system effectiveness. The results show that the proposed interface performed significantly better in all but the search result measure. While in general the users have a favorable attitude toward the meta-search function, seven usability issues were identified for the improvement of the system.

L'A. presente trois articles portant sur des etudes d'utilisateurs d'archives. Les recherches sur les utilisateurs et leurs besoins sont des necessites pratiques dans la perspective de la planification a long terme, et permettent de faire le lien entre les fonctions cle de l'archivistique : evaluation, acquisition, preservation et mise en acces des ressources. La connaissance des differentes communautes d'utilisateurs doit etre appliquee a l'amelioration des services et des programmes, pour une meilleure gestion des frontieres entre les archives et leurs utilisateurs. Il s'agit d'aider les utilisateurs a franchir les obstacles du jargon professionnel et des regles des archivistes, afin de transformer l'espace cloture des archives en un seuil accueillant.

An educator's toolkit for virtual simulation: A usability study

Quickly accessing the contents of a video is challenging for users, particularly for unstructured video, which contains no intentional shot boundaries, no chapters, and no apparent edited format. We approach this problem in the domain of lecture videos though the use of machine learning, to gather semantic information about the videos; and through user interface design, to enable users to fully utilize this new information. First, we use machine learning techniques to gather the semantic information. We develop a system for rapid automatic semantic tagging using a heuristic-based feature selection algorithm called Sort-Merge, by using large initial heterogeneous low-level feature sets (cardinality greater than 1K). We explore applying Sort-Merge to heterogeneous feature sets though two methods: early fusion and late fusion. Each takes different approaches to handling the different kinds of features in the heterogeneous set. We determine the most predictive feature sets for key-frame filters such as “has text”, “has computer source code”, or “has instructor motion”. Specifically we explore the usefulness of Harr Wavelets, Fast Fourier Transforms, Color Coherence Vectors, Line Detectors, Ink Features and Pan/Tilt/Zoom detectors. For evaluation, we introduce a “keeper” heuristic for feature sets, which provides a method of performance comparison against a baseline. Second, we create a user interface to allow the user to make use of the semantic tags we gathered though our computer vision and machine learning process. The interface is integrated into an existing video browser, which detected shot-like boundaries and presented a multitimeline view. The content within shot-like boundaries is represented by frames to which our new interface applies the generated semantic tags. Specifically, we make accessible the semantic concepts of 'text', 'code', 'presenter', and 'person motion.' The tags are detected in the simulated shots using the filters generated with our machine learning approach and are displayed to users using a user-customizable multi-timeline view. We also generate tags based on ASRgenerated transcripts that have been limited to the words provided in the index of the course text book. Each of these occurrences is aligned with the simulated shots. Each spoken word becomes a tag analogous to the visual concepts. A full Boolean algebra over the tags is provided to enable new composite tags such as 'text or code, but no presenter.' Finally, we quantify the effectiveness of our features and our browser through user studies, both observational and task driven. We find that users that use the full suite of tools performed a search task in 60% of the time of users without access to tags. We find that when users are asked to perform search tasks they follow a nearly fixed pattern of accesses, alternating between the use of tags and Keyframes, or between the use of Word Bubbles and the media player. Based on user behavior and feedback, we redesigned the interface to group spatially interface components that are used together, removed un-used components, and redesigned the display of Word Bubbles to match that of the Visual Tags. We found that users strongly preferred the Keyframe tool, as well as both kinds of tags. Users also either found the algebra very useful or not useful at all.

Current authoring environments provide the possibility of developing user interfaces with limited adaptation capacities. The most widely adopted tools follow the responsive design approach and allow developers to obtain user interfaces that can adapt mainly to the screen size and orientation. We present a solution able to support development of user interfaces able to adapt to the various types of contextual events (that can be related to users, devices, environments, and social relationships), with the added possibility of distributing the user interface elements across multiple devices. The context-dependent behavior is modelled through trigger / action rules, and can even be applied to Web applications that were not originally designed to be context-aware. This paper describes the design and main features of the novel authoring environment and reports on a first user study.

Bidirectional Human-Robot Learning: Imitation and Skill Improvement

This study explores the creation of emotion- responsive user interfaces (UIs) that adapt to users' mental states in stressful settings in real time. Utilizing human- computer interaction (HCI) principles and artificial intelligence, it introduces an innovative framework for UIs that adjusts based on fatigue, concentration, and emotional cues. The method incorporates sophisticated facial recognition, eye tracking, and physiological sensors to continuously evaluate users' cognitive and emotional conditions. The adaptive UI system uses machine learning algorithms to optimize cognitive load and improve remote interactions in various high-pressure situations. Through a series of experiments and user studies, notable enhancements in task performance, user satisfaction, and overall cognitive efficiency have been demonstrated. The results underscore the potential of emotion-responsive UIs to transform human-computer interaction, particularly in areas such as healthcare, emergency response, and mission-critical operations. Keywords — HCI, Emotion-Adaptive UI, Cognitive Efficiency, Real-Time Adaptation, Fatigue, Focus, Emotional Expression, Artificial Intelligence, Machine Learning, User Interface, High- Stress Environments, Remote Interaction.

Smallholder decision-making process in technology adoption intention: implications for Dipterocarpus alatus in Northeastern Thailand