Search

Adaptive user interfaces enable the display of user-specific, relevant information in complex interactive systems. The user experience on platforms can be improved by taking the user's needs (goals, system experience, etc.) and design preferences (in terms of design shapes) into account. In a Germany-wide online survey, n = 1,044 young people (pupils and university students) aged between 14 and 35 were asked about their design shape preferences. The results show that, overall, the shape of the circle appears to be the most attractive for young people (14–35 years) and that gender and age have the greatest influence on design shape preferences. While men and generally older people (19–35 years, university students) prefer basic shapes to more complex shapes, women and generally younger people (14–19 years, pupils) find complex shapes more attractive than basic ones. The identification of preferences with regard to design shapes can provide developers of interactive systems with information for the design of (adaptive) user interfaces. [ABSTRACT FROM AUTHOR]

(1) Background: Public transport has a vital role to play in creating sustainable, accessible societies. Accessible and inclusive, door-to-door public transport systems with low barriers to use benefit everyone, increasing the mobility of citizens and improving independence. As the industry strives towards multi-modal and Mobility as a Service (MaaS) concepts, there is a need to delve deep into the needs and perceptions of transport user's door-to-door journeys to find ways to improve. Accordingly, in order to increase the sustainability of MaaS, improving accessibility and understanding service user perceptions are of utmost importance. However, there is a scarcity of research within national transport services to determine unmet user needs to increase the accessibility and autonomy of door-to-door journeys. This research aims to investigate if it is possible to improve the door-to-door journey experience for public transport travellers, increasing the accessibility and the perception of autonomy via technology, and by doing so, providing a more sustainable alternative to road transport. It focuses on understanding service users of Ireland's National Rail service, Irish Rail, to create key improvements in interactive systems. (2) Methods: The study applies a user-centred mixed-methods methodology using surveys (N = 316) and co-design workshops (four workshops N = 15). The research collected deep insights into the mindsets and needs of service users, showing the potential to improve this door-to-the-door customer journey. Key improvements for interactive systems were outlined. Experience maps were designed, leading to a Conceptual Design for a travel assistant to aid the service user throughout the door-to-door journey. (3) Results: Travellers' autonomy and the sense of freedom they experience can be improved, mainly if their needs across the complete door-to-door customer journey are supported. Highlighted areas for action include information, accessibility, personal security, ticketing, comfort, facilities, and anxiety. (4) Conclusions: This research reiterates the need for national transport and MaaS providers to prioritise service users' perspectives when developing sustainable services. Co-designing is recommended as a means of achieving this. [ABSTRACT FROM AUTHOR]

Practitioners of multi-objective optimization currently lack open tools that provide decision support through knowledge discovery. There exist many software platforms for multi-objective optimization, but they often fall short of implementing methods for rigorous post-optimality analysis and knowledge discovery from the generated solutions. This paper presents Mimer, a multi-criteria decision support tool for solution exploration, preference elicitation, knowledge discovery, and knowledge visualization. Mimer is openly available as a web-based tool and uses state-of-the-art web-technologies based on WebAssembly to perform heavy computations on the client-side. Its features include multiple linked visualizations and input methods that enable the decision maker to interact with the solutions, knowledge discovery through interactive data mining and graph-based knowledge visualization. It also includes a complete Python programming interface for advanced data manipulation tasks that may be too specific for the graphical interface. Mimer is evaluated through a user study in which the participants are asked to perform representative tasks simulating practical analysis and decision making. The participants also complete a questionnaire about their experience and the features available in Mimer. The survey indicates that participants find Mimer useful for decision support. The participants also offered suggestions for enhancing some features and implementing new features to extend the capabilities of the tool. [ABSTRACT FROM AUTHOR]

The acquisition and analysis of high-quality sensor data constitute an essential requirement in shaping the development of fully autonomous driving systems. This process is indispensable for enhancing road safety and ensuring the effectiveness of the technological advancements in the automotive industry. This study introduces the Interaction of Autonomous and Manually Controlled Vehicles (IAMCV) dataset, a novel and extensive dataset focused on intervehicle interactions. The dataset, enriched with a sophisticated array of sensors such as lidar, cameras, inertial measurement unit/Global Positioning System, and vehicle bus data acquisition, provides a comprehensive representation of real-world driving scenarios that include roundabouts, intersections, country roads, and highways, recorded across diverse locations in Germany. Furthermore, the study shows the versatility of the IAMCV dataset through several proof-of-concept use cases. First, an unsupervised trajectory clustering algorithm illustrates the dataset’s capability in categorizing vehicle movements without the need for labeled training data. Second, we compare an online camera calibration method with the Robot Operating System-based standard, using images captured in the dataset. Finally, a preliminary test employing the YOLOv8 object-detection model is conducted, augmented by reflections on the transferability of object detection across various lidar resolutions. These use cases underscore the practical utility of the collected dataset, emphasizing its potential to advance research and innovation in the area of intelligent vehicles. [ABSTRACT FROM AUTHOR]

Chatbots have revolutionized human-computer interactions in various fields, driven by advancements in Artificial Intelligence. Similarly, gamification techniques have emerged as innovative methods to engage users and enhance experiences. This paper presents an analysis of the trends, applications, methods, and challenges associated with chatbots, with a particular emphasis on their capability to generate customized gamification solutions for industrial 5.0 environments. These environments are characterized by the increased use of technologies - such as Virtual and Augmented Reality - driven by the digital transformation of Industry 4.0 (I4.0). As Industry 5.0 (I5.0) builds upon I4.0, emphasizing human-technology collaborations and coexistence of humans and advanced technologies, the role of chatbots and gamification in this context becomes even more compelling. Within this research, various gamification applications and chatbot architectures, ranging from rule-based to generative models, are identified to assess their suitability for the specific needs of industrial 5.0 environments. The primary objective of this study is to explore the potential of leveraging chatbot assistance to enhance gamification experiences by considering employee specific characteristics, workplace technologies, and other relevant factors. By examining the advancements and obstacles in this field, this study aims to explore the potential of chatbots for increasing the effectiveness of gamification strategies. This integration is anticipated to lead to more immersive and personalized experiences, increased employee satisfaction, positive work environment, and enhanced skill development and performance. However, several challenges such as security, user acceptance and the need for continuous adaptation must be addressed to ensure the successful implementation of chatbot-driven gamification in I5.0 environments. The navigation through these challenges holds the key to unlocking the full potential of these transformative technologies and methods, paving the way for a more engaging and enriching work environment. [ABSTRACT FROM AUTHOR]

Command and control rooms are socio-technical systems that gather many devices and software of different types and aim at supporting groups of operators to manage missions and systems collaboratively. They include interactive systems, which particularly support operators in controlling the local or remote systems. These interactive systems are the very place where human–system integration can take place. It is thus important to design, develop, test, certify and deploy them very carefully. Moreover, designing these interactive systems requires addressing the needs of the group of users involved in common tasks for which communication, cooperation and production are mediated by computers. This paper proposes a model-based approach for the design and development of usable and reliable socio-technical interactive systems. This approach takes into account the sociotechnical aspects of the interactions between operators and systems in a command and control room. The paper presents the results of the application of the approach to the model-based development of collaborative applications for the management of collision risks between satellites and space objects. [ABSTRACT FROM AUTHOR]

We demonstrate and reflect on a rebuilding and electronic engineering approach to augment and electrify a Lego brick model. Concretely, we turn the not musically playable Lego Grand Piano into a functioning musical instrument as a MIDI keyboard with 25 keys and a sustain pedal. Our proposed solution is unobtrusive, flexible, and reversible. We only use off-the-shelf components and instead of soldering we take advantage of the bricks’ interlocking mechanism together with wires and self-adhesive copper tape, which also keeps the costs and required skills for our approach low. Two live performances evidenced by videos showed the practical and musical applicability. We created and reflected on an extensive step-by-step documentation of the whole transformation process which we offer for potential reuse purposes. Overall, our approach to electrify a brick-built model and turning it into an interactive musical interface was successful, insightful and has the potential to be expanded, but needs further elaboration with other brick-built models and for different application purposes than musical instruments. Thus, we explicitly invite researchers, designers, engineers, tinkerers and makers who engage themselves in electrified and interactive brick-built models to get inspired by our approach, replicate and advance it.

E-learning has established itself as a new alternative to conventional learning styles to accomplish the goal of education and learning for everyone. The classroom learning style is based on a “one size fits all” approach because, in a typical classroom environment, an instructor has to deal with several students at the same time. A similar problem goes along with the traditional learning management systems in which every student must learn the course devised by the instructor, within a specific timeline and achieve specific objectives, despite students’ preferences and capabilities. The recent global pandemic has pushed educational institutes worldwide to recourse to an “online-only” mode of education and teaching delivery which has raised many challenges that need to be addressed. The existing e-learning systems fail to fulfill the expectations of a learner or an instructor in certain ways including the style of content delivery, mode of teaching, an adaptation of learner style that doesn’t match with the teaching style, the content type, and above all the e-learning lacks to provide the e-mentoring capability to deal with the challenges a learner and an instructor’s face during the learning process. This research aims to develop personalized learning by incorporating an intelligent e-mentor. The proposed e-mentor-based learning model is capable of customizing a course for individuals by automatically adapting it to their unique learning styles, preferences, abilities, existing knowledge, and expectations from the course. The outcome of the proposed model shows that e-mentoring not only increased learner satisfaction but also enhanced the learning process making it a preferred choice.

The paper presents a framework for interactive control of multi robots using mixed reality interfaces. The proposed approach can operate with both single and multi-robot systems, including interaction with industrial manipulators, mobile robots, and unmanned aerial vehicles (UAV). The human–robot interface allows both interactive and physical interaction with the robot. Particular attention is paid to a visualisation of the robots' intent during control. The presented framework has Robotic Operation System (ROS) as a core that can be connected to any robot and mixed reality interface. This allows us to make framework scalable and connect several different mixed reality devices and multiple heterogeneous robots. In the implementation part we connected our framework with Microsoft HoloLens, collaborative robot KUKA IIWA, mobile platform Plato, UAV designed on the basis of dji f450. The proposed framework was tested experimentally with real experimental setups mentioned above. The results showed the capabilities of the mixed reality system for interactive control of different robots' type. [ABSTRACT FROM AUTHOR]

AbstractRhythm can create a sense of structure or order, making it easier for users to understand and navigate interactive systems, thereby making user engagement more enjoyable and motivating. Recently, designers are increasingly interested in integrating rhythm into the design of interactive systems. However, the existing literature on this topic is fragmented, making it difficult for designers to find comprehensive guidance. This paper presents the first literature review of rhythm research for designing an interactive system based on the PRISMA method. Through an analysis of 59 papers based on the critical review method (e.g., research through design), we identify six research genres and provide a map to help future researchers locate their research position. Because there is currently no clear classification framework to guide designers in integrating rhythm into interactive systems, we propose a classification framework that includes six design qualities: three human rhythm-driven qualities and three computer rhythm-driven qualities based on the literature review. This classification framework provides a foundation for designers to regulate rhythm in interactive systems. In addition, we discuss emerging issues related to rhythm genres and rhythm classification framework and design qualities. We reflect on the effectiveness of our proposed framework by revisiting previous works on designing interactive systems, and provide potential directions for future research in this area. Overall, this paper aims to provide comprehensive guidance for designers who wish to integrate rhythm into the design of interactive systems, and to advance the understanding of the role of rhythm in interactive system design. [ABSTRACT FROM AUTHOR]

This research introduces a novel approach to optimizing control policies for waste cranes operating at waste-to-energy plants. Although previous methods forced people to define evaluation functions for automation, such design works in actual environments can often be challenging due to limited sensors and design difficulties. This paper aims to establish a methodology that achieves automation by having people respond to interactive pairwise comparison queries, which is relatively simple compared to design work. On the other hand, considering such automation, it becomes imperative to address the increased sample cost associated with slow crane operation and the complexities of decision-making due to waste inhomogeneity. Our proposed Preferential Bayesian Policy Optimization (PBPO) optimizes control policies with a small number of queries using Preference-based Bayesian optimization (PbBO) and mitigates the difficulty of decision-making by providing human evaluators who have an option to skip queries. We also incorporate a query synthesis mechanism to enhance query efficiency that generates a new preference relation from the skipped queries. PBPO’s effectiveness was validated with a scattering task employed in previous studies. Experimental results with simulated evaluators show the effectiveness of the PBPO and query synthesis. Furthermore, results with actual human evaluators indicate that our proposed method performs as well as the Bayesian optimization (BO) method, which requires an evaluation function.

Designing interactive prototypes involves multiple tools and skills. In addition, several design cycles are required to iterate through idea generation, evaluation of design alternatives, and development. Consequently, prototyping tools should offer flexibility and adaptability to allow designers to quickly test and evaluate different ideas, design alternatives, materials, interactions, etc. To meet these requirements, we designed Protobject – a rapid prototyping tool aimed at making the early stages of prototyping interactive products more flexible. Protobject allows designers to reinvent and reuse existing objects for prototyping purposes by making them interactive. After introducing the features of Protobject and discussing the differences with similar tools, we present a user evaluation through two workshop sessions held in Milan during Brera Design Days and attended by 22 people. The results suggest that Protobject facilitates cooperation between people with different skills by allowing them to envision interactive prototypes together.

Electroencephalography is a technique, which allows to capture brain activity. Devices BCI (Brain-Computer Interface) are being used to evaluate the UX (User eXperience). We present a study where was designed an experiment using the OPENBCI device. The experiment consisted of capturing the brain activity to analyse the data of a group of people (women; men) when they interacted with a classic game called Snake. Therefore, the study designed two interaction ways. First interaction involved a traditional interaction with computer and keyboard. The second interaction involve the use of NFC cards and a mobile device. Also, were applied questionnaires, such as: SAM (Self-Assessment Manikin), NASA-TLX and SUS (System Usability Scale), to compare the information recollected through of the BCI, which consistency with the data was reflected. [ABSTRACT FROM AUTHOR]

Abstract Intrusion Detection System (IDS) is a critical cybersecurity task that involves monitoring network traffic for malicious activity and taking appropriate action to stop it. However, insufficient training data or improperly chosen thresholds often limit the accuracy of such systems, resulting in high false‐positive rates. To improve the accuracy of an IDS, blockchain technology can be used as it provides a secure, decentralized, immutable ledger that can track suspicious activity over time and also identify intrusions globally. In this paper, the authors propose a novel methodology to improve the accuracy of blockchain‐based IDS. The approach combines different intrusion detection algorithms using a blockchain‐integrated architecture. It is based on the fusion principle and weighted votes, which the authors used to determine their results. The authors tested the system on DARPA 99 and MIT‐Lincoln Labs datasets using accuracy and false‐positive rate as their two metrics. The system achieved 92.6% accuracy and 7.4% false‐positive rates, indicating that the proposed system significantly increases the accuracy while reducing the false‐positive rate, opening up new opportunities for the development of highly accurate networks.

Stochastic Model Predictive Control (SMPC) has attracted increasing attention for autonomous driving in recent years, since it enables collision-free maneuvers and trajectory planning and can deal with uncertainties in a non-conservative way. Many promising strategies have been proposed on how to use SMPC to select appropriate maneuvers and plan safe trajectories in uncertain environments. The limitation of these approaches is that they focus on scenarios where only one vehicle is controlled by SMPC and is, thus, reacting to the surrounding vehicles; however, the surrounding vehicles do not react to the SMPC-controlled vehicle, which means there is no mutual interaction. However, when multiple autonomous vehicles are driving on the road, each individual vehicle will take the behavior of the other surrounding vehicles into account and adjust its individual decisions accordingly in trajectory planning. This paper, therefore, examines in simulations how the interactive control system of multiple SMPC-controlled vehicles behave based on a Distributed SMPC (DSMPC) framework. For a three-lane highway scenario, we first investigate the effects of the risk parameter of the collision avoidance probabilistic constraint on non-interactive and interactive vehicle systems and provide insights into how to parameterize the controllers in interactive vehicle systems. [ABSTRACT FROM AUTHOR]

Conversational recommender systems aim to interactively support online users in their information search and decision-making processes in an intuitive way. With the latest advances in voice-controlled devices, natural language processing, and AI in general, such systems received increased attention in recent years. Technically, conversational recommenders are usually complex multi-component applications and often consist of multiple machine learning models and a natural language user interface. Evaluating such a complex system in a holistic way can therefore be challenging, as it requires (i) the assessment of the quality of the different learning components, and (ii) the quality perception of the system as a whole by users. Thus, a mixed methods approach is often required, which may combine objective (computational) and subjective (perception-oriented) evaluation techniques. In this paper, we review common evaluation approaches for conversational recommender systems, identify possible limitations, and outline future directions towards more holistic evaluation practices. [ABSTRACT FROM AUTHOR]

The article shows that functioning of big companies is usually connected with accomplishing a great deal of various projects, whose management requires such tools that give an opportunity to organize project work. It is recommended to integrate systems of decision-making support with systems operating at the enterprise, which can increase the speed of data processing, search for alternative decisions and their impact on project management. It is possible to improve the process of project management at the enterprise by introducing new technologies and tools providing objective analysis of data with plotting a model of moving events and resolving problems dealing with the quality of estimating project solutions. Therefore, the information system should be used as a tool supporting decision-making aimed at collecting, optimizing, analyzing data, finding errors at present and forecasting further steps in project development. The system of decision-making support is an interactive automated system, whose goal is to help the user apply data and mechanisms for identification and settlement of problems in the adequate way. The efficient and wide use of software has become one of key factors of development and success of companies in conditions of fierce competition.

With the aim to give an overview of the most recent discoveries in the field of socially engaging interactive systems, the present paper discusses features affecting users' acceptance of virtual agents, robots, and chatbots. In addition, questionnaires exploited in several investigations to assess the acceptance of virtual agents, robots, and chatbots (voice only) are discussed and reported in the Supplementary material to make them available to the scientific community. These questionnaires were developed by the authors as a scientific contribution to the H2020 project EMPATHIC (http://www.empathic-project.eu/), Menhir (https://menhir-project.eu/), and the Italian-funded projects SIROBOTICS (https://www.exprivia.it/it-tile-6009-si-robotics/) and ANDROIDS (https://www.psicologia.unicampania.it/android-project) to guide the design and implementation of the promised assistive interactive dialog systems. They aimed to quantitatively evaluate Virtual Agents Acceptance (VAAQ), Robot Acceptance (RAQ), and Synthetic Virtual Agent Voice Acceptance (VAVAQ).

Intrusion Detection System (IDS) is a critical cybersecurity task that involves monitoring network traffic for malicious activity and taking appropriate action to stop it. However, insufficient training data or improperly chosen thresholds often limit the accuracy of such systems, resulting in high false‐positive rates. To improve the accuracy of an IDS, blockchain technology can be used as it provides a secure, decentralized, immutable ledger that can track suspicious activity over time and also identify intrusions globally. In this paper, the authors propose a novel methodology to improve the accuracy of blockchain‐based IDS. The approach combines different intrusion detection algorithms using a blockchain‐integrated architecture. It is based on the fusion principle and weighted votes, which the authors used to determine their results. The authors tested the system on DARPA 99 and MIT‐Lincoln Labs datasets using accuracy and false‐positive rate as their two metrics. The system achieved 92.6% accuracy and 7.4% false‐positive rates, indicating that the proposed system significantly increases the accuracy while reducing the false‐positive rate, opening up new opportunities for the development of highly accurate networks. In this paper, the authors propose a novel methodology to improve the accuracy of blockchain‐based intrusion detection and prevention systems, which is based on combining different intrusion detection algorithms and using a blockchain‐integrated architecture. The authors tested the system on DARPA 99 and MIT‐Lincoln Labs datasets using accuracy and false‐positive rate as their two metrics. The system achieved 92.6% accuracy and 7.4% false‐positive rate, indicating that the proposed system significantly increases the accuracy while reducing the false‐positive rate, opening up new opportunities for the development of highly accurate networks. [ABSTRACT FROM AUTHOR]

Interactive computing with Jupyter Notebooks has transformed the state of the art of scientific research computing. Users can perform a multitude of computational tasks in real time, including data cleansing, analysis, visualization, and postprocessing, with Jupyter Notebooks. Additionally, the ability to write and execute code and include supporting text and images in the same document has made it popular for use in scholarly articles and teaching. These capabilities complement the batch computing services provided by high-performance computing centers exposed through traditional science gateways. However, integrating Jupyter into science gateways and other advanced computing ecosystems introduces new challenges related to scalability, collaboration, and reproducibility. In this article, we discuss the Scalable Interactive Computing (Scinco) project, an open source platform for scalable, reproducible, interactive scientific computing designed to be run in academic computing centers and incorporated into science gateways. We describe the prime features, architecture, deployment choices, and challenges of Project Scinco. [ABSTRACT FROM AUTHOR]

Technological advances have facilitated new approaches to support different needs in healthcare environments. In particular, in the field of rehabilitation therapies, we can find software applications that have been developed to support the performance of specific exercises, often with different customization options. However, there are still many gaps that need to be addressed to provide more and better global solutions. In this article, we present a novel system aimed at physiotherapists, which allows them to create new rehabilitation exercises designed to meet the specific needs of their patients. This implies the creation of individualized therapies that contribute to a better and faster recovery of patients. The system consists of a virtual 3D environment with a 3D skeleton representing the patient. The physiotherapist can interact with the skeleton to design the desired postures that the patient should practice according to their personal limitations. The system allows physiotherapists to compose a complete and personalized set of exercises. Alternatively, the physiotherapist may also create the postures by means of a motion sensing device using motion- and voice-based interaction. Both options pose research challenges that the authors have addressed to provide the solution presented in this paper. [ABSTRACT FROM AUTHOR]

It is important to promote assistive technologies to improve quality of life. The proposed SmartAbility Android Application recommends assistive technologies for people with reduced physical abilities, by focussing on actions that can be performed independently. The SmartAbility Application uses Android built-in sensors, e.g., accelerometer and gyroscope and application programming interfaces (APIs) to detect physical abilities, e.g., head movements and blowing and recommend suitable assistive technologies. This is supported by a MySQL database that stores assistive technologies and mappings between abilities. The underpinning research is the SmartAbility Framework that culminates the knowledge obtained during previously feasibility trials and usability evaluations. The Application was evaluated by pupils (n = 18) at special educational needs schools with physical conditions, including cerebral palsy, autism and Noonan syndrome, and assessed through the NASA Task Load Index (TLX) and System Usability Scale (SUS). Analysis using the Adjective Rating Scale highlighted that the Application achieves "Good Usability". The SmartAbility Application demonstrates that built-in sensors of Android devices and their APIs, can detect actions that users perform, e.g., head movements and speaking. The Application contains a database where assistive technologies are mapped to physical abilities, in order to provide suitable recommendations. It will be disseminated to assistive technology charities and manufacturers and be used by healthcare professionals as part of the rehabilitation process. Future developments of SmartAbility include the creation of a second Application designed specifically to recommend assistive technologies for the education sector, based on users' physical and cognitive abilities. Assistive technology is any item, equipment or piece of software designed to increase, maintain or improve the functional capabilities of people with disabilities. SmartAbility should be introduced into rehabilitation to promote awareness of assistive technologies that are suitable for the physical abilities of the user. Our research highlighted that physical abilities can be detected using built-in sensors of Android devices, e.g. accelerometer and gyroscope. Involvement of the intended user community during evaluations is essential to ensure that a smartphone application is suitable for people with reduced physical abilities. Assistive technologies can support the rehabilitation of people with reduced physical abilities by providing increased independence and improved quality of life. [ABSTRACT FROM AUTHOR]

Many fields of study still face the challenges inherent to the analysis of complex multidimensional datasets, such as the field of computational biology, whose research of infectious diseases must contend with large protein-protein interaction networks with thousands of genes that vary in expression values over time. In this paper, we explore the visualization of multivariate data through CroP, a data visualization tool with a coordinated multiple views framework where users can adapt the workspace to different problems through flexible panels. In particular, we focus on the visualization of relational and temporal data, the latter being represented through layouts that distort timelines to represent the fluctuations of values across complex datasets, creating visualizations that highlight significant events and patterns. Moreover, CroP provides various layouts and functionalities to not only highlight relationships between different variables, but also dig-down into discovered patterns in order to better understand their sources and their effects. These methods are demonstrated through multiple experiments with diverse multivariate datasets, with a focus on gene expression time-series datasets. In addition to a discussion of our results, we also validate CroP through model and interface tests performed with participants from both the fields of information visualization and computational biology.

Intelligent question-answering (QA) systems have witnessed increased interest in recent years, particularly in their ability to facilitate information access, data interpretation or decision support. The wind energy sector is one of the most promising sources of renewable energy, yet turbines regularly suffer from failures and operational inconsistencies, leading to downtimes and significant maintenance costs. Addressing these issues requires rapid interpretation of complex and dynamic data patterns under time-critical conditions. In this article, we present a novel approach that leverages interactive, natural language-based decision support for operations & maintenance (O&M) of wind turbines. The proposed interactive QA system allows engineers to pose domain-specific questions in natural language, and provides answers (in natural language) based on the automated retrieval of information on turbine sub-components, their properties and interactions, from a bespoke domain-specific knowledge graph. As data for specific faults is often sparse, we propose the use of paraphrase generation as a way to augment the existing dataset. Our QA system leverages encoder-decoder models to generate Cypher queries to obtain domain-specific facts from the KG database in response to user-posed natural language questions. Experiments with an attention-based sequence-to-sequence (Seq2Seq) model and a transformer show that the transformer accurately predicts up to 89.75% of responses to input questions, outperforming the Seq2Seq model marginally by 0.76%, though being 9.46 times more computationally efficient. The proposed QA system can help support engineers and technicians during O&M to reduce turbine downtime and operational costs, thus improving the reliability of wind energy as a source of renewable energy.

Despite the fact that task-oriented conversation systems have received much attention from the dialogue research community, only a handful of them have been studied in a real-world manufacturing context using industrial robots. One stumbling block is the lack of a domain-specific discourse corpus for training these systems. Another difficulty is that earlier attempts to integrate natural language interfaces (such as chatbots) into the industrial sector have primarily focused on task completion rates. When designing a dialogue system for social robots, the user experience is prioritized above industrial robots. To overcome these challenges, we provide the Industrial Robots Domain Wizard-of-Oz dataset (IRWoZ), a fully-labeled discourse dataset covering four robotics domains. It delivers simulated discussions between shop floor workers and industrial robots, with over 401 dialogues, to promote language-assisted Human-Robot Interaction (HRI) in industrial settings. Small talk concepts and human-to-human conversation strategies are provided to support human-like answer generation and give a more natural and adaptable dialogue environment to increase user experience and engagement. Finally, we propose and evaluate an end-to-end Task-oriented Dialogue for Industrial Robots (ToD4IR) using two types of pre-trained backbone models: GPT-2 and GPT-Neo, on the IRWoZ dataset. We performed a series of trials to validate ToD4IR’s performance in a real manufacturing context. Our experiments demonstrate that ToD4IR outperforms three downstream task-oriented dialogue tasks, i.e., dialogue state tracking, dialogue act generation, and response generation, on the IRWoZ dataset. Our source code of ToD4IR and the IRWoZ dataset is accessible at https://github.com/lcroy/ToD4IR for reproducible research.

Teaching English for Specific Purposes is a challenging endeavor, especially during a pandemic that forced a new teaching/learning paradigm. The present paper aims to highlight the online tools and platforms that have been useful in order to provide an efficient and enjoyable learning experience. Considering the learning styles of the students and the skills needed for future engineers to become competitive on the labor market, we have comprised a series of sample activities that may be considered examples of good practice.