Machine learning-based assessment tool for imbalance and vestibular dysfunction with virtual reality rehabilitation system

Background and objective

Dizziness is a major consequence of imbalance and vestibular dysfunction. Compared to surgery and drug treatments, balance training is non-invasive and more desired. However, training exercises are usually tedious and the assessment tool is insufficient to diagnose patient's severity rapidly.

Methods

An interactive virtual reality (VR) game-based rehabilitation program that adopted Cawthorne–Cooksey exercises, and a sensor-based measuring system were introduced. To verify the therapeutic effect, a clinical experiment with 48 patients and 36 normal subjects was conducted. Quantified balance indices were measured and analyzed by statistical tools and a Support Vector Machine (SVM) classifier.

Results

In terms of balance indices, patients who completed the training process are progressed and the difference between normal subjects and patients is obvious.

Conclusions

Further analysis by SVM classifier show that the accuracy of recognizing the differences between patients and normal subject is feasible, and these results can be used to evaluate patients’ severity and make rapid assessment.     

GeoVR: a web-based tool for virtual reality presentation from 2D GIS data

A tool called GeoVR has been designed and developed under a client/server architecture to enable the interactive creation of a 3D scene and virtual reality modeling language (VRML) model from 2D spatial data by integrating Internet geographical information system (GIS) and HTML programming. The client front-end of this tool provides an HTML form to set properties for building 3D scenes, while the server back-end supported by off-the-shelf software: ArcView Internet Map Server and ArcView 3D Analyst through Avenue programming, processes the parameters and generates a 3D scene. This 3D scene is then transformed into a VRML model, which, together with its legend, is sent back to the VRML-enabled WWW browser for display and navigation. It is demonstrated that this tool, not only automates the conversion of the conventional 2D GIS data into VRML, but also adapts the current GIS 3D capabilities to the increasingly popular Web environment. The development of GeoVR offers new opportunities for geoscientists to build applications that benefit from virtual reality presentation based upon the existing GIS spatial databases.     

Identifying students’ mathematical skills from a multiple-choice diagnostic test using an iterative technique to minimise false positives

There is anecdotal evidence that a significant number of students studying computing related courses at degree level have difficulty with sub-GCE mathematics. Testing of students’ skills is often performed using diagnostic tests and a number of computer-based diagnostic tests exist, which work, essentially, by testing one specific diagnostic skill at a time.     

Learning science in a virtual reality application: The impacts of animated-virtual actors’ visual complexity

As the technology in computer graphics advances, Animated-Virtual Actors (AVAs) in Virtual Reality (VR) applications become increasingly rich and complex. Cognitive Theory of Multimedia Learning (CTML) suggests that complex visual materials could hinder novice learners from attending to the lesson properly. On the other hand, previous studies have shown that visual complexity correlates with presence and may increase the perceived affective quality of the virtual world, towards an optimal experience or flow. Increasing these in VR applications may promote enjoyment and higher cognitive engagement for better learning outcomes. While visually complex materials could be motivating and pleasing to attend to, would they affect learning adversely? We developed a series of VR presentations to teach second-year psychology students about the navigational behaviour of Cataglyphis ants with flat, cartoon, or lifelike AVAs. To assess learning outcomes, we used Program Ratings, which measured perception of learning and perceived difficulty, and retention and transfer tests. The results from 200 students did not reveal any significant differences in presence, perceived affective quality, or learning outcomes as a function of the AVA’s visual complexity. While the results showed positive correlations between presence, perceived affective quality and perception of learning, none of these correlates with perceived difficulty, retention, or transfer scores. Nevertheless, our simulation produced significant improvements on retention and transfer scores in all conditions. We discuss possible explanations and future research directions.     

Learning and teaching about scientific models with a computer-modeling tool

The study presents efforts to support pre-service primary school teachers in learning and teaching about scientific models, and discusses the impact of these efforts on their understandings. We provided pre-service primary school teachers with a module on computer modeling and studied the effects of this experience on their abilities to construct viable scientific models with a computer-modeling tool, namely, Model-It [Metcalf, J. S., Krajcik, J., & Soloway, E. (2000). MODEL-IT: A Design Retrospective. In M. J. Jacobson & R. B. Kozma (Eds.), Innovations in Science and Mathematics Education (pp. 77–115). Mahwah, NJ: Lawrence Erlbaum Associates], in order to teach a sixth-grade science lesson. The results of the study showed that Model-It, through its scaffolds (i.e., Plan, Build, and Test), enabled the majority of pre-service teachers to build models that were structurally correct, but simplistic. The participants showed a tendency to teach science using more often the explorative modeling method than the expressive method, and only few of them employed both methods in their lessons. In essence, Model-It effectively scaffolded pre-service teachers’ first modeling experiences and enabled them to quickly build and test their models as well as reflect on the viability of their models. However, according to the results, teachers need extensive learning experiences in order to achieve a comprehensive understanding of the process of scientific modeling in science.     

Promoting collaborative skills in online university: comparing effects of games,mixed reality,social media,and other tools for ICT-supported pedagogical practices

ABSTRACT

This article analyses the development of collaborative skills through nine tools for information and communication technologies (ICT)-supported pedagogical practices, which are used in online universities. Using survey data for 930 online students at the Open University of Catalonia and partial least squares path modelling estimation techniques, three main findings emerged from the study. First, collaborative skills are directly explained by gamification and the use of mixed reality and social media in a socio-technical online learning context. Second, other tools for ICT-supported pedagogical practices (media content, wikis, open educational resources, personal webpages, personal cloud, and sharing files with fellow students and lecturers on the cloud) are not significant on collaborative skills development, when compared to use of games, mixed reality, and social media. Third, the analysis of indirect effects suggests that all four socio-technical factors (ICT, learning tasks, students, and organisation) existing in online university play a decisive, positive and significant role in collaborative skills development. Finally, these results are shown in science, technology, engineering, and mathematics (STEM) and non-STEM studies. Thus, gamification, mixed reality, and sharing files are significant ICT-supported pedagogical practices in STEM studies. On the other hand, gamification is the only significant tool in non-STEM studies. Results are very useful for new approaches to design a framework for learning-team effectiveness in computer-supported collaborative learning.     

GenUTest: a unit test and mock aspect generation tool

Unit testing plays a major role in the software development process. What started as an ad hoc approach is becoming a common practice among developers. It enables the immediate detection of bugs introduced into a unit whenever code changes occur. Hence, unit tests provide a safety net of regression tests and validation tests which encourage developers to refactor existing code with greater confidence. One of the major corner stones of the agile development approach is unit testing. Agile methods require all software classes to have unit tests that can be executed by an automated unit-testing framework. However, not all software systems have unit tests. When changes to such software are needed, writing unit tests from scratch, which is hard and tedious, might not be cost effective. In this paper we propose a technique which automatically generates unit tests for software that does not have such tests. We have implemented GenUTest, a prototype tool which captures and logs interobject interactions occurring during the execution of Java programs, using the aspect-oriented language AspectJ. These interactions are used to generate JUnit tests. They also serve in generating mock aspects—mock object-like entities, which enable testing units in isolation. The generated JUnit tests and mock aspects are independent of the tool, and can be used by developers to perform unit tests on the software. Comprehensiveness of the unit tests depends on the software execution. We applied GenUTest to several open source projects such as NanoXML and JODE. We present the results, explain the limitations of the tool, and point out direction to future work to improve the code coverage provided by GenUTest and its scalability.     

The effects of an interactive videodisc training program in classroom observation skills used as a teaching tool and as a learning tool

In higher education, instruction is typically teacher-directed through traditional lecture formats and assignments with predetermined criteria. Through hypermedia-based materials, new ways of learning are possible based on learner control and self-directed instruction; such approaches require personal goal-setting, nonlinear exploration of materials, context-based problem solving, and progress monitoring. For students to learn in new ways, instructors have to teach in new ways. Teachers cannot simply take new hypermedia applications and implement them within existing approaches if higher level outcomes are to be realized. The findings in this study are consistent with previous research studies which demonstrate equal or better learning using hypermedia-based instructional materials when students are allowed learner control. If the learning profile for each student determines the effective use of an application, then hypermedia is best implemented as a learning tool.     

Design and management of innovation laboratories: Toward a performance assessment tool

There is a strong emergence of new spaces to foster innovation all over the world (Fablabs, Living Labs and Design Factories, among others). Past experiences have shown these types of projects involving “innovation laboratories” are at risk of not succeeding in their goals. Although several studies have tackled the problem of design, development and sustainability of innovation laboratories, there is still a gap in understanding how the capabilities and performance of these environments are affected by the strategic intentions at the early stages of design and functioning. Throughout this work, eight frameworks from the literature that analyze innovation laboratories are identified and compared. Then, based on both literature and the authors' experience, an updated framework is proposed as the basis for a guidance tool for researchers and practitioners aiming to assess or to adapt an existing project. As part of the operationalization process of the framework, a maturity grid‐based assessment tool is proposed to evaluate the maturity degree of an innovation laboratory. Afterwards, to evaluate the viability and to integrate the perception of innovation laboratory managers, an exploratory study with answers from fifteen laboratories from five different countries is performed. Insights and implications for emerging and already existent projects of innovation laboratories are then discussed.     

Focusing on content reusability and interoperability in a personalized hypermedia assessment tool

This paper presents the development of a modularized hypermedia testing tool, called iAdaptTest, based entirely on e-learning specifications and discusses how this architecture improves the reusability and the interoperability of the learning data. All the categories of data,—that is—topics, user profiles, testing data, adaptive rules, and testing results are coded in XML format complying with Topic Maps, IMS LIP and IMS QTI. The data are stored in distinct files and can be independently shared across different educational applications. The paper concludes with an evaluation study concerning the creation of formative and summative assessments for adult seminars. Through focused interviews, the participants of the study identified the ability to share information and the multi-criteria adaptation options as the most important features of the system. Further, in the second phase of the evaluation the files produced were shared with other educational applications and thus it was verified that the learning data could be imported and rendered correctly.     

Human factors and qualitative pedagogical evaluation of a mobile augmented reality system for science education used by learners with physical disabilities

Technology-enhanced learning, employing novel forms of content representation and education service delivery by enhancing the visual perception of the real environment of the user, is favoured by proponents of educational inclusion for learners with physical disabilities. Such an augmented reality computer-mediated learning system has been developed as part of an EU funded research project, namely the CONNECT project. The CONNECT project brings together schools and science centres, and produces novel information and communication technologies based on augmented reality (AR) and web-based streaming and communication, in order to support learning in a variety of settings. The CONNECT AR interactive learning environment can assist users to better contextualize and reinforce their learning in school and in other settings where people learn (i.e. science centres and home). The CONNECT concept and associated technologies encourage users to visit science centres and perform experiments that are not possible in school. They can also build on these experiences back at school and at home with visual augmentations that they are communicated through web-based streaming technology. This paper particularly focuses on a user-centred evaluation approach of human factors and pedagogical aspects of the CONNECT system, as applied to a special needs user group. The main focus of the paper is on highlighting the human factors issues and challenges, in terms of wearability and technology acceptance, while elaborating on some qualitative aspects of the pedagogical effectiveness of the instructional medium that AR technology offers for this group of learners.

The ObReco-360°: a new ecological tool to memory assessment using 360° immersive technology

Virtual Reality - One important feature of a neuropsychological test is its ecological validity, which defines how much patients’ test scores are linked to real-life functioning. However,...     

The development of a theoretical framework and design tool for process usability assessment

The purpose of usability engineering is to facilitate the deployment of new products by decreasing development costs and improving the quality of systems. This paper will discuss the development and delivery of a unique, theoretically based software tool that provides engineers and designers with easy access to the most recent advances in human-machine interface design. This research combines several theoretical views of the interaction process into a hybrid model. Based on this model, a software tool was produced that allows engineers to model the human interaction process within their design. The system then provides feedback on the interaction process through items such as: the amount of mental effort required by a user, the degree to which the system conforms to human capabilities, the expected time to complete the interaction, where potential human error may occur, as well as potential misunderstandings or points of confusion to the users. The designer may then use this information to improve the design of the system. Validation of this technique indicates that the hybrid model produces accurate predictions of usability attributes and that the technique transfers from the laboratory to the real world.     

The development of a theoretical framework and design tool for process usability assessment

The purpose of usability engineering is to facilitate the deployment of new products by decreasing development costs and improving the quality of systems. This paper will discuss the development and delivery of a unique, theoretically based software tool that provides engineers and designers with easy access to the most recent advances in human-machine interface design. This research combines several theoretical views of the interaction process into a hybrid model. Based on this model, a software tool was produced that allows engineers to model the human interaction process within their design. The system then provides feedback on the interaction process through items such as: the amount of mental effort required by a user, the degree to which the system conforms to human capabilities, the expected time to complete the interaction, where potential human error may occur, as well as potential misunderstandings or points of confusion to the users. The designer may then use this information to improve the design of the system. Validation of this technique indicates that the hybrid model produces accurate predictions of usability attributes and that the technique transfers from the laboratory to the real world.     

Assessing work-related body-part discomfort: Current strategies and a behaviorally oriented assessment tool

Work-related body-part discomfort has been assessed for a variety of purposes in both experimental and applied research. In a number of these studies, ‘discomfort’ is assessed using a body map and a rating, or ranking, procedure. Sometimes the assessed values are subjected to direct statistical investigation; at other times the assessed values are used to derive indices of discomfort which are then subjected to statistical study. However, the construct of ‘discomfort’ is rarely clearly defined. Thus, depending on the nature of the investigation, the respondent's perceptions, and the instructions provided, it may incorporate a variety of physical sensations including pain, fatigue, tension, and tingling. This paper describes ways in which work-related body-part discomfort has been defined, assessed, and used. It concludes with a tool for assessing work-related body-part discomfort. This tool includes a body map and scales for assessing the severity, frequency, and duration of work-related body-part discomfort, and incorporates many of the key features identified in this literature review.     

Design and implementation of a quantitative risk assessment software tool for Singapore road tunnels

This paper presents an interesting approach to develop a quantitative risk assessment (QRA) software tool for road tunnels. It first introduces a QRA model for road tunnels, consisting of event trees, fault trees and consequence estimation models. The model is developed by taking into account the unique characteristics of Singapore road tunnels. The paper proceeds to describe design of the QRA software tool based on the QRA model by means of the object oriented design (OOD) method and eXtensible Markup Language (XML) technique. The XML files are used to store the numerous tree structures in the proposed model thus making the programming much more efficiently and effectively. The QRA software tool is robust and flexible such that users can easily add or modify the event trees, fault trees and the consequence estimation models. An application to Singapore road tunnels has been carried out to assess the robustness and effectiveness of the QRA software tool.     

Immersive virtual reality as an empirical research tool: exploring the capability of a machine learning model for predicting construction workers’ safety behaviour

Virtual Reality - In recent years, research has found that people have stable predispositions to engage in certain behavioural patterns to work safely or unsafely, which vary among individuals as a...     

Learning a Generative Model for Multi‐Step Human‐Object Interactions from Videos

Creating dynamic virtual environments consisting of humans interacting with objects is a fundamental problem in computer graphics. While it is well‐accepted that agent interactions play an essential role in synthesizing such scenes, most extant techniques exclusively focus on static scenes, leaving the dynamic component out. In this paper, we present a generative model to synthesize plausible multi‐step dynamic human‐object interactions. Generating multi‐step interactions is challenging since the space of such interactions is exponential in the number of objects, activities, and time steps. We propose to handle this combinatorial complexity by learning a lower dimensional space of plausible human‐object interactions. We use action plots to represent interactions as a sequence of discrete actions along with the participating objects and their states. To build action plots, we present an automatic method that uses state‐of‐the‐art computer vision techniques on RGB videos in order to detect individual objects and their states, extract the involved hands, and recognize the actions performed. The action plots are built from observing videos of everyday activities and are used to train a generative model based on a Recurrent Neural Network (RNN). The network learns the causal dependencies and constraints between individual actions and can be used to generate novel and diverse multi‐step human‐object interactions. Our representation and generative model allows new capabilities in a variety of applications such as interaction prediction, animation synthesis, and motion planning for a real robotic agent.     

Learning styles assessment and theoretical origin in an E-learning scenario: a survey

The performance of the learners in E-learning environments is greatly influenced by the nature of the posted E-learning contents. In such a scenario, the performance of the learners can be enhanced by posting the suitable E-learning contents to the learners based on their learning styles. Hence, it is very essential to have a clear knowledge about various learning styles in order to predict the learning styles of different learners in E-learning environments. However, predicting the learning styles needs complete knowledge about the learners past and present characteristics. Since the knowledge available about learners is uncertain, it can be resolved through the use of Fuzzy rules which can handle uncertainty effectively. The core objective of this survey paper is to outline the working of the existing learning style models and the metrics used to evaluate them. Based on the available models, this paper identifies Felder–Silverman learning style model as the suitable model for E-learning and suggests the use of Fuzzy rules to handle uncertainty in learning style prediction so that it can enhance the performance of the E-learning system.     

Design and implementation of a t-way test data generation strategy with automated execution tool support

To ensure an acceptable level of quality and reliability of a typical software product, it is desirable to test every possible combination of input data under various configurations. However, due to the combinatorial explosion problem, exhaustive testing is practically impossible. Resource constraints, cost factors, and strict time-to-market deadlines are some of the main factors that inhibit such a consideration. Earlier research has suggested that a sampling strategy (i.e., one that is based on a t-way parameter interaction) can be effective. As a result, many helpful t-way sampling strategies have been developed and can be found in the literature.Several advances have been achieved in the last 15 years, which have, in particular, served to facilitate the test planning process by systematically minimizing the test size required (based on certain t-way parameter interactions). Despite this significant progress, the integration and automation of strategies (from planning process to execution) are still lacking. Additionally, strategizing to sample (and construct) a minimum test set from the exhaustive test space is an NP-complete problem; that is, it is often unlikely that an efficient strategy exists that could regularly generate an optimal test set. Motivated by these challenges, this paper discusses the design, implementation, and validation of an efficient strategy for t-way testing, the GTWay strategy. The main contribution of GTWay is the integration of t-way test data generation with automated (concurrent) execution as part of its tool implementation. Unlike most previous methods, GTWay addresses the generation of test data for a high coverage strength (t > 6).