Narrow Results

Accelerometer-based gesture recognition facilitates a complementary interaction modality for controlling mobile devices and home appliances. Using gestures for the task of home appliance control requires use of the same device and gestures by different persons, i.e. user independent gesture recognition. The practical application in small embedded low-resource devices also requires high computational performance. The user independent gesture recognition accuracy was evaluated with a set of eight gestures and seven users, with a total of 1120 gestures in the dataset. Twenty-state continuous HMM yielded an average of 96.9% user independent recognition accuracy, which was cross-validated by leaving one user in turn out of the training set. Continuous and discrete five-state HMM computational performances were compared with a reference test in a PC environment, indicating that discrete HMM is 20% faster. Computational performance of discrete five-state HMM was evaluated in an embedded hardware environment with a 104 MHz ARM-9 processor and Symbian OS. The average recognition time per gesture calculated from 1120 gesture repetitions was 8.3 ms. With this result, the computational performance difference between the compared methods is considered insignificant in terms of practical application. Continuous HMM is hence recommended as a preferred method due to its better suitability for a continuous-valued signal, and better recognition accuracy. The results suggest that, according to both evaluation criteria, HMM is feasible for practical user independent gesture control applications in mobile low-resource embedded environments.

The definition and use of multi-valued constant propagation analysis (MVCP), which is an extension of simple constant propagation analysis, is presented in this paper in the context of a user interface reengineering process.

A brief description of the adopted COBOL/CICS user interface reengineering model, which makes use of an Abstract User Interface Description Language (AUIDL) to represent user interface structures and behavior, is also given.

The experimental context is described and results are shown and discussed. Suggestions for further directions of research and investigation are also presented.

This article describes design challenges of a novel concept enabling natural and intuitive video-mediated collaboration. Typical video-mediated communication systems do not enable deictic gestures nor direct drawing with white board markers, thus limiting communication. We present our novel concept for Natural and Intuitive Video-mediated Collaboration (NIVMC). NIVMC was originally developed for design professionals to enable co-operative sketching, but it may also benefit other user groups.

Visualization is an important component of modern computing. By animating the course of an algorithm’s temporal execution, many key features can be elucidated. We have developed a general framework, termed Call-Graph Caching (CGC), for automating the construction of many complex AI algorithms. By incorporating visualization into CGC interpreters, principled animations can be automatically displayed as AI computations unfold.

(1) Systems that support the automatic animation of AI algorithms must address these three design issues:

(2) How to represent AI data structures in a general, uniform way that leads to perspicuous animation and efficient redisplay.

(3) How to coordinate the succession of graphical events.

(4) How to partition AI graphs to provide for separate, uncluttered displays. CGC provides a natural and effective solution to all these concerns.

(5) We describe the CGC method, including detailed examples, and motivate why CGC works well for animation. We discuss the CACHE system, our CGC environment for AI algorithm animation. We demonstrate the animation of several AI algorithms – RETE match, linear unification, arc consistency, chart parsing, and truth maintenance – all of which have been implemented in CACHE. Finally, we discuss the application of these methods to interactive interfaces for intelligent systems, using molecular genetics as an example domain.

We describe a method based on UML activities for the unified specification of collaborative service behavior and local user interfaces. The method enables a model-driven development process, which effectively combines the need to express service collaborations involving several components with the need to provide detailed operations for user interfaces. Our service models use activities as the primary building blocks that encapsulate self-contained functionalities. We show, how a complete distributed system can be decomposed into such building blocks, how this decomposition leads to a separation of user interface concerns from service collaboration concerns, and how they may be combined with an event-driven composition mechanism based on activity parameter nodes. We also demonstrate how different UI frameworks can be supported, and illustrate the method with a case study of a situated collaborative learning service.

Humans can perform stable motion with a sense of stability that involves identifying their center of gravity point with plantar sensory system. By contrast, the stability of a humanoid robot is inferior to that of a human. If the sense of stability of a humanoid robot is presented to a human who operates the robot in real time, the operator can control the robot more stably. However, studies wherein humans recognize the projected center of gravity point with a plantar haptic display are lacking. In this study, we investigated the possibility of estimating the projected center of gravity point of a small humanoid robot from only the foot force information. We propose a plantar haptic display to reproduce the foot reaction force on four points of a single sole as large as the force during human running. We conducted an experiment to verify the estimated center of gravity point using the foot reaction forces of a small robot with and without scaling by a weight ratio between an operator and the robot. The results indicated that it is difficult to estimate the projected center of gravity point without scaling; however, it is possible to estimate the movement of the projected center of gravity point with a maximum error of $\sim 10$mm with scaling.

Nowadays many software development frameworks implement Behavior-Driven Development (BDD) as a mean of automating the test of interactive systems under construction. Automated testing helps to simulate user’s actions on the User Interface and therefore check if the system behaves properly and in accordance to scenarios that describe functional requirements. However, tools supporting BDD run tests on implemented User Interfaces and are a suitable alternative for assessing functional requirements in later phases of the development process. However, even when BDD tests can be written in early phases of the development process they can hardly be used with specifications of User Interfaces such as prototypes. To address this problem, this paper proposes to raise the abstraction level of both system interactive behaviors and User Interfaces by means of a formal ontology that is aimed at supporting test automation using BDD. The paper presents an ontology and an ontology-based approach for automating the test of functional requirements of interactive systems. We demonstrate the feasibility of this ontology-based approach to assess functional requirements in prototypes and full-fledge applications through an illustrative case study of e-commerce applications for buying flight tickets.

Augmented reality (AR) interfaces increasingly utilize artificial intelligence systems to tailor content and experiences to the user. We explore the effects of one such system — a recommender system for online shopping — which allows customers to view personalized product recommendations in the physical spaces where they might be used. We describe results of a $2\times 3$ condition exploratory study in which recommendation quality was varied across three user interface types. Our results highlight potential differences in user perception of the recommended objects in an AR environment. Specifically, users rate product recommendations significantly higher in AR and in a 3D browser interface, and show a significant increase in trust in the recommender system, compared to a web interface with 2D product images. Through semi-structured interviews, we gather participant feedback which suggests AR interfaces perform better due to their ability to view products within the physical context where they will be used.

Tubular continuum robots can follow complex curvilinear paths to reach restricted areas within the body. Using teleoperation, these robots can help minimize incisions and reduce trauma. However, drawbacks include the lack of haptic feedback and a limited view of the situs, often due to camera occlusion. This work presents novel auditory display to enhance interaction with such continuum robots to increase accuracy and path-following efficiency and reduce cognitive workload. We recreate a typical use case with a test environment that simulates a transnasal intervention through the sphenoidal sinus including a simulated continuum robot. Distance information is mapped to changes in a real-time audio synthesizer using sung voice to provide navigation cues. User studies with novice participants and clinicians were performed to evaluate the effects of auditory display on accuracy, task time, path following efficiency, subjective workload, and usability. When using auditory display, participants exhibit significant increase in accuracy, efficiency, and task time compared to visual-only display. Auditory display reduced subjective workload and raised usefulness and satisfaction ratings. The addition of auditory display for augmenting interaction with a teleoperated continuum robot has shown to benefit performance as well as usability. The method could benefit other scenarios in navigated surgery to increase accuracy and reduce workload.

Task models are logical descriptions of the activities to be performed in reaching user's goals. They have shown to be useful for designing, analyzing and evaluating interactive software applications. This chapter introduces the main concepts underlying task models and discusses how they can be represented and, then, used in the various phases of the life cycle.

Different approaches can be applied to assess the usability of a web application. Each one of them presents advantages and drawbacks, as well as cost-benefits trade-offs. This contribution contains a short review of the state-of-the-art in web usability assessment issues, by focusing on a new systemic approach, called "e-usability", designed to deal in a more integrated way with the human-computer interaction, so as to allow a more realistic assessment of web interfaces. The applied methodology is quick and doesn't need any artifact design or evaluation cost.

In this paper, we present the design and implementation of Database User Interface Design Editor which employs the WYSIWYG approach for users to interactively access and manipulate user interface widgets and database widgets to build database interfaces. By binding UIMS techniques with the database primitives, the editor provides a platform to fast prototype UIs and rapidly create reusable graphical constructs for representing database objects. It makes design-test-modify cycle which is universally recognized as the only efficient way to successful UI design an easier task by supporting two design modes – development mode arid simulation mode. The simulation mode allows users to visualize the actual behaviour of the interface under development at any time without having to compile and run the interface codes created. Users can switch between these two modes.