Microsoft (Ireland)

This paper presents the application of an effective EEG-based brain-computer interface design for binary control in a visually elaborate immersive 3D game. The BCI uses the steady-state visual evoked potential (SSVEP) generated in response to phase-reversing checkerboard patterns. Two power-spectrum estimation methods were employed for feature extraction in a series of offline classification tests. Both methods were also implemented during real-time game play. The performance of the BCI was found to be robust to distracting visual stimulation in the game and relatively consistent across six subjects, with 41 of 48 games successfully completed. For the best performing feature extraction method, the average real-time control accuracy across subjects was 89%. The feasibility of obtaining reliable control in such a visually rich environment using SSVEPs is thus demonstrated and the impact of this result is discussed.

Accurate detection of somatic mutations is still a challenge in cancer analysis. Here we present NeuSomatic, the first convolutional neural network approach for somatic mutation detection, which significantly outperforms previous methods on different sequencing platforms, sequencing strategies, and tumor purities. NeuSomatic summarizes sequence alignments into small matrices and incorporates more than a hundred features to capture mutation signals effectively. It can be used universally as a stand-alone somatic mutation detection method or with an ensemble of existing methods to achieve the highest accuracy.

In the two decades since the establishment of the 2030 Agenda, the world has faced significant challenges to achieve the 17 Sustainable Development Goals (SDGs). Before COVID-19, the SDGs were not on track to be achieved, and disruptions in implementation resulting from the pandemic have had significant effects, turning back years of progress. The pandemic has highlighted the essential nature of digital technologies in advancing the SDGs, continuing education, including higher education, social, and commercial activities, as well as enabling people to participate in society, democracy, and the economy during crises. As humanity enters this new period and begins to reset after the ‘great pause’, it is imperative to reconsider how the digital revolution has affected progress, especially in realizing the SDGs. Digital inclusion and connectivity inform and are essential to achieve all of the Goals. This article builds on the Just Digital Ethical Framework conceptualized by the authors in O’Sullivan et al. published in Nature Communications, which argues that four strategic drivers (digital capabilities, technology, infrastructure, and governance) are imperative to complete all of the 17 SDGs. It takes the Just Digital Ethical Framework to the next critical step, in which there needs to be a new SDG dedicated to these four drivers. This article is an exploratory study that uses a systems thinking approach and presents an 18th SDG called Digital Connection. Digital Connection focuses on the equitable distribution of digital wealth guided by the drivers. Understanding the relationship between these drivers and how they operate, where they are used, the pace of change, and systems’ ability to adapt are essential for sustainable development and to address the challenges that face society equitably and fairly.

While the technological revolution is accelerating, digital poverty is undermining the Sustainable Development Goals. This article introduces a justice-oriented digital framework which considers how fair access to digital capabilities, commodities, infrastructure, and governance can reduce global inequality and advance the SDGs.

Machine learning technologies are increasingly being applied in many different domains in the real world. As autonomous machines and black-box algorithms begin making decisions previously entrusted to humans, great academic and public interest has been spurred to provide explanations that allow users to understand the decision-making process of the machine learning model. Besides explanations, Interactive Machine Learning (IML) seeks to leverage user feedback to iterate on an ML solution to correct errors and align decisions with those of the users. Despite the rise in explainable AI (XAI) and Interactive Machine Learning (IML) research, the links between interactivity, explanations, and trust have not been comprehensively studied in the machine learning literature. Thus, in this study, we develop and evaluate an explanation-driven interactive machine learning (XIML) system with the Tic-Tac-Toe game as a use case to understand how a XIML mechanism improves users’ satisfaction with the machine learning system. We explore different modalities to support user feedback through visual or rules-based corrections. Our online user study (n = 199) supports the hypothesis that allowing interactivity within this XIML system causes participants to be more satisfied with the system, while visual explanations play a less prominent (and somewhat unexpected) role. Finally, we leverage a user-centric evaluation framework to create a comprehensive structural model to clarify how subjective system aspects, which represent participants’ perceptions of the implemented interaction and visualization mechanisms, mediate the influence of these mechanisms on the system’s user experience.

This article presents a review of the evolution of automatic post-editing, a term that describes methods to improve the output of machine translation systems, based on knowledge extracted from datasets that include post-edited content. The article describes the specificity of automatic post-editing in comparison with other tasks in machine translation, and it discusses how it may function as a complement to them. Particular detail is given in the article to the five-year period that covers the shared tasks presented in WMT conferences (2015-2019). In this period, discussion of automatic post-editing evolved from the definition of its main parameters to an announced demise, associated with the difficulties in improving output obtained by neural methods, which was then followed by renewed interest. The article debates the role and relevance of automatic post-editing, both as an academic endeavour and as a useful application in commercial workflows.

Current software practice places a strong emphasis on unit testing, to the extent that the amount of test code produced on a project can exceed the amount of actual application code required. This illustrates the importance of testability as a feature of software. In this paper we investigate whether it is possible to improve a program's testability using an automated refactoring approach. We conduct a quasi-experiment where we create a small application that scores poorly using a proven cohesion metric, LSCC. Using our automated refactoring platform, Code-Imp, this application is automatically refactored using the LSCC metric to guide the search for better solutions. To evaluate the results, a number of industrial software engineers were asked to write test cases for the application both before and after refactoring and compare the relative difficulty involved. The results were interesting though inconclusive, and suggest that further work is required.

It is generally accepted that intrinsic student motivation is a critical requirement for effective learning but formal learning in school places a huge reliance on extrinsic motivation to focus the learner. This reliance on extrinsic motivation is driven by the pressure on formal schooling to ‘deliver to the test’. The experience of the use of ICT in formal learning is marked with a naive and largely unfulfilled assumption that it would of itself promote a ‘game-changing’ shift in student motivation. This study investigates the effectiveness of a team-based, technology-mediated model called Bridge21 to encourage intrinsic student motivation. The data for the study come from 425 secondary school students, average age 16 years, who participated in workshops of 3.5 days in duration. The workshops took place in an out-of-school learning environment in one academic year. Bridge21 seeks to provide a vehicle to allow the transfer of control of learning from the teacher to the team and in this way to encourage and promote student autonomy. The principal findings reported in this paper are that participation in the workshops had a direct positive impact on the students’ perceptions around their learning and on their intrinsic motivation to learn.

There have been calls for decades by many educational writers and commentators for a new model of learning to facilitate what is generally described as twenty-first-century learning. Central to this challenge is the required shift in responsibility for who leads and owns the learning – from teacher to student. Such a shift requires a pragmatic pedagogical model to facilitate the transfer of control and ownership of learning. Vygotsky’s ‘more able other’ identified the peer as a key figure in learning. Teamwork facilitates project-based learning and, when mediated with technology, proves an effective partner in creating an engaging and autonomous learning experience. This paper describes the rationale for the design of a team-based model of twenty-first-century learning, particularly drawing upon the team-based learning model of the World Scout Movement. Results from a year-long study of the implementation of the model in an out-of-school context with 288 second-level students are presented. The authors argue that Bridge21 is a candidate learning model for effective, implementable, twenty-first-century, team-based learning.

PURPOSE: Assistive technology (AT) enables and promotes inclusion and participation, especially for persons with a disability, ageing populations, and those with non-communicable diseases. AT is essential for generating collaborative learning environments, inclusive of students with a range of specific needs and required supports. However, many teachers lack the training, resources, and skills to use AT in the class. This study uses a systems thinking approach to consider teachers AT needs in the Irish classroom. METHODS: Three hundred and five teachers completed an online survey, and 10 took part in semi-structured focus groups. The survey examined teachers experiences with AT, their training needs, and the context within which they need support. RESULTS: Teachers reported low levels of AT knowledge, skills, and confidence. Many described limited access to training and support for AT use. Results also reveal non-systems thinking, whereby there is no meaningful linking across the main strategic drivers of AT - policy, products, provision, and personnel, to support the people at the centre of the AT system - between these and the contextual factors that influence their effectiveness. CONCLUSION: An AT system which is easy to navigate, which has policies and provision that supports educators, and has expert personnel on hand to support teachers, is crucial if AT is to become embedded in Irish classrooms. This research shows that a comprehensive AT system in education should include policies, practices, personnel, and products that interact to support people to engage easily and successfully with AT in the classroom.IMPLICATIONS FOR REHABILITATIONDescribes current trends in how teachers are engaging with Assistive Technology.Describes the current trends in disabilities in Irish classroom and teachers requirements for support.Understand the system challenges facing teachers attempting to use Assistive Technology.Support the development of Assistive Technology training for teachers which are informed by teachers needs.Inform the development and improving policies and processes for common situations.

SUMMARY Over the past several years, the use of optical fibre cables as ground motion sensors has become a central topic for seismologists, with successful applications of distributed acoustic sensing (DAS) in various key fields such as seismic monitoring, structural imaging and source characterization. DAS response is a combination of both instrument response and cable-ground coupling, with the latter having a strong, spatially variable, but yet largely unquantified effect. This limits the application of a large number of staple seismological techniques (e.g. earthquake magnitude estimation, waveform tomography) that can require accurate knowledge of a signal's amplitude and frequency content. Here we present a method for accurately simulating a DAS cable and its ground coupling. The scheme is based on molecular dynamic-like particle-based numerical modelling, allowing the investigation of the effect of varying DAS-ground coupling scenarios. We start by computing the full strain field directly, for each pair of neighbouring particles in the model. We then define a virtual DAS cable, embedded within the model and formed by a single string of interconnected particles. This allows us to control all aspects of the cable-ground coupling and their properties at an effective granular level through changing the bond stiffness and bond types (e.g. non-linearity) for both the cable and the surrounding medium. Arbitrary cable geometries and heterogeneous materials can be accommodated at the desired scale of investigation. We observe that at the meter scale, the cable-ground coupling and local site effects can substantially alter the recorded signal. We find that the stiffness of the thin layer of material to which the cable is coupled has the strongest effects, selectively amplifying portions of the wave train and contributing to substantial phase delays. These differences show that cable coupling and local site effects should be considered both when designing a DAS deployment and analysing its data when either true or along-cable relative amplitudes and/or frequencies are considered. The codes developed herein for calculating full waveform DAS responses and coupling are made publicly available.

Abstract Minecraft Education is a digital game-based learning platform that is thought to support the development of twenty-first century competencies and skills. The purpose of this study is to explore primary students’ experiences of using Minecraft Education during an innovative national project-based initiative. The initiative had two phases: 1) educational episodes for teachers and students on how to use the platform and 2) a national competition that required students to re-imagine a sustainable version of their community. We used a mixed-methods design with a sample of classes taking part in the initiative. First, third to sixth class students ( N = 173) completed a survey that examined: 1) learning opportunities with Minecraft Education, 2) ease of use, 3) usefulness, and 4) enjoyment. Eight focus group interviews were then conducted with a subsample of sixth class students ( n = 30). Students indicated that 1) there were good opportunities for learning with Minecraft Education, particularly for creativity and collaboration, 2) the platform was easy to use and useful and, 3) using Minecraft Education was enjoyable. Thematic analysis of the qualitative data identified five themes: ‘collaboration’, ‘opportunities for creativity’, ‘immersive learning environment’, ‘student engagement’, and ‘technology and digital skills’. This research highlights the value of innovative project-based learning activities with Minecraft Education for supporting student learning.

In a translation workflow, machine translation (MT) is almost always followed by a human post-editing step, where the raw MT output is corrected to meet required quality standards. To reduce the number of errors human translators need to correct, automatic post-editing (APE) methods have been developed and deployed in such workflows. With the advances in deep learning, neural APE (NPE) systems have outranked more traditional, statistical, ones. However, the plethora of options, variables and settings, as well as the relation between NPE performance and train/test data makes it difficult to select the most suitable approach for a given use case. In this article, we systematically analyse these different parameters with respect to NPE performance. We build an NPE "roadmap" to trace the different decision points and train a set of systems selecting different options through the roadmap. We also propose a novel approach for APE with data augmentation. We then analyse the performance of 15 of these systems and identify the best ones. In fact, the best systems are the ones that follow the newly-proposed method. The work presented in this article follows from a collaborative project between Microsoft and the ADAPT centre. The data provided by Microsoft originates from phrase-based statistical MT (PBSMT) systems employed in production. All tested NPE systems significantly increase the translation quality, proving the effectiveness of neural post-editing in the context of a commercial translation workflow that leverages PBSMT.

Statistical machine learning techniques for data classification usually assume that all entities are i.i.d. (independent and identically distributed). However, real-world entities often interconnect with each other through explicit or implicit relationships to form a complex network. Although some graph-based classification methods have emerged in recent years, they are not really suitable for complex networks as they do not take the degree distribution of network into consideration. In this paper, we propose a new technique, Modularity Kernel, that can effectively exploit the latent community structure of networked entities for their classification. A number of experiments on hypertext datasets show that our proposed approach leads to excellent classification performance in comparison with the state-of-the-art methods.

In this paper, we consider how the development of targeted ransomware has affected the dynamics of ransomware negotiations to better understand how to respond to ransomware attacks. We construct a model of ransomware negotiations as an asymmetric non-cooperative two-player game. In particular, our model considers the investments that a malicious actor must make in order to conduct a successful targeted ransomware attack. We demonstrate how imperfect information is a crucial feature for replicating observed real-world behaviour. Furthermore, we present optimal strategies for both the malicious actor and the target, and demonstrate how imperfect information results in a non-trivial optimal strategy for the malicious actor.

Minecraft Education is a popular digital game-based learning platform designed for use in educational settings. This study explores teachers’ experiences of using Minecraft Education as an educational tool to foster the development of key competencies and skills in students. Semi-structured interviews with Irish primary school teachers (N = 11) were conducted during a national project-based initiative involving Minecraft Education in primary schools called Ireland’s Future is MINE. Thematic analysis identified six major themes: encourages student collaboration, supports creativity, students as active participants in their learning, inclusive educational tool, supports curricular content, and barriers to use. Findings emphasise how the platform can be used in the classroom to support the development of skills and competencies students need to succeed in the future while simultaneously supporting curricular content. In addition, the platform can enable learning conditions that are more inclusive and equitable for all students. External technological barriers to use need to be addressed to realise the full potential of the platform in a classroom setting. The paper concludes with a series of recommendations and implications relating to the use of Minecraft Education in primary school classrooms.

Abstract Minecraft is a popular digital game‐based learning (DGBL) tool used in learning environments around the world. With increasing emphasis on evidence‐informed practice and policymaking in educational systems, this paper systematically reviews the evidence base behind the use of Minecraft in improving academic, cognitive, motivational‐affective and social outcomes. We searched seven databases and other secondary sources up until February 2024. Pre‐post intervention studies that evaluated the use of Minecraft (randomised, non‐randomised and single‐group studies) in children, adolescents and young adults were included. Twenty‐nine studies satisfied our inclusion criteria. Studies primarily investigated Minecraft as a tool to improve cognitive ( n = 7) and academic ( n = 16) outcomes. Studies reported positive effects on spatial thinking ( n = 2), creativity ( n = 3), critical thinking ( n = 1), mathematics ( n = 5), science ( n = 4) and language ( n = 2). However, all studies included in this review had a medium or high risk of bias. Therefore, while Minecraft demonstrates good potential in improving these outcomes, effects need to be replicated in more rigorous studies. Suggestions for future research are discussed. This review provides timely evidence for educators, school leaders and policymakers regarding the use of DGBL with Minecraft.

This paper is a position statement. There are important requirements on software development engineers that go beyond the normal academic qualifications and technical skills, and which quite often receive a lower priority in education and training.

How often do tags recur? How hard is predicting tag recurrence? What tags are likely to recur? We try to answer these questions by analysing the RSDC08 dataset, in both individual and collective settings. Our findings provide useful insights for the development of tag suggestion techniques etc.

Purpose The purpose of this study is to examine the intra‐organisational diffusion of management innovations, taking Six Sigma as an example. Design/methodology/approach The study focuses on Six Sigma implementation among companies operating in Ireland. It makes use of a theoretical framework, which posits that multinational firms act as a diffusion mechanism for Six Sigma. The analysis of Six Sigma implementation consists of an online survey to which 132 firms responded. Subsequently, a qualitative analysis of Six Sigma implementation was conducted through semi‐structured interviews with 13 respondents. Findings The results show that roughly half of respondent firms use Six Sigma. These firms are typically large US multinationals, which have used Six Sigma for at least three years. Intra‐organisational diffusion does exist. Multinationals do act as a diffusion mechanism – with the adoption of Six Sigma at US headquarters level and then the diffusion of the practice internally to the Irish subsidiary and subsequently to suppliers and finally other local firms. However, the role of traditional diffusion mechanisms is also highlighted. Firms adopt Six Sigma in response to competitive pressure and for cost/efficiency reasons. Originality/value The research shows how organisations influence one another in the implementation of Six Sigma as a management concept, and at the same time this can be seen as a specific example of the dissemination of management concepts in general.