Abstract:This paper proposes an investigation onto the physiological and/or cognitive effects that VR, as a technology-enabled learning platform, may have on industrial design students when used as a medium for content creation, with the goal of identifying optimal experience thresholds. This will be accomplished through the adoption of a mixed methodology, with a user-centered design (UCD) focus, designed to evaluate both the value of the technology as a tool for abstract expression and, from task-based exercises in virtual environments (VEs), identify optimal experience thresholds through analysis of the physiological and/or cognitive load variability among different user’s. Perception of value will be sought by means of primary sourced qualitative data, while physiological and cognitive quantitative data will derive from experiments. Once all data is collected, both strands of information will be combined to design, prototype and evaluate an optimal VR experience with the objective of assessing its validity, and consequently establish a set of guidelines that may be used to develop a future instructional framework.

Abstract:This paper represents a piece of PhD research in Product Design conducted at a Neonatal Intensive Care Unit (NICU). This research focused on the issues around the interaction process between people and complex technological systems. Specifically, one of the objectives is as follows: what could be a valuable contribution of Cognitive Ergonomics to designing complex human-system interactions? The healthcare sector was chosen as an application field characterized by a high level of complexity, while Cognitive Ergonomics was the approach. The desk research on Cognitive Ergonomics has proposed a set of Cognitive Ergonomics Components: subjectivity, functionality, perception, decision-making, mental workload, error, and interaction. According to the literature review, these are essential components of Cognitive Ergonomics, and it was assumed that these components are useful for the analysis of the interaction between human and complex technological systems. This article relates the experience of field research conducted at a Neonatal Intensive Care Unit (NICU) that aimed to apply these components to analyze the interaction between the healthcare professionals, visitors, and the NICU equipment to prove or disprove the hypothesis eventually. The field research was organized as shadowing the doctors and nurses in their environment, clarifying specific moments of interaction with short interviews. The observations were synthesized according to the Cognitive Ergonomics components, allocating findings to the analysis steps proposed in the hypothesis. The paper concludes with reflections on the experience performed using the components as a human-system interaction analysis tool.

Abstract:This paper presents and discusses the results of a future forecast study involving Higher Education educators from the field of industrial design and neighbouring. Participants were asked to imagine teaching and learning situations twenty years ahead, in a future where Virtual Reality (VR) technology and the design studio are harmoniously integrated. The aim was to project how the maturation of the technology and possible subsequent widespread adoption could affect design activity and design studio dynamics. While answering an online questionnaire, participants had to hypothesise uses or applications of the technology, the potential consequential behaviours derived from it and broader implications. Their answers hint at six areas where the technology is relevant to design. Behaviour wise, they envision students more engaged in research and creation, demonstrating a deeper level of knowledge over the variables influencing their projects and a proneness for collaborative or cooperative work. This change in dynamics contrasts with more cautious views who discern that a growing digital footprint weakens the relation with materials and sensibility development towards medium and process. These, combined with a lesser amount of real-world interactions, are perceived as undermining student maturity or growth. All of these and more hint at implications in the design process, pedagogy, curriculum, teacher and student dynamics and role repositioning, showing that integrating VR may have ramifications stretching far beyond the design studio context.

Abstract:The classification problem of imbalanced data is a popular issue in the field of machine learning in recent years. For imbalanced data, traditional classification algorithms tend to classify minority class samples into majority class, which result in the misclassification of many minority samples by the classifier. For imbalanced data classification problems, this paper proposes a Density Based Safe Level Synthetic Minority Oversampling TEchnique (DB-SLSMOTE). First, the algorithm clusters minority samples through Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Then, the Safe Level Synthetic Minority Oversampling TEchnique (Safe-Level-SMOTE) is utilized for clusters of any shape discovered by DBSCAN. It is followed that the processed data is classified by Random Forest (RF). The experimental results show that the DB-SLSMOTE algorithm can effectively improve the classification performance of RF for minority samples in imbalanced data.

Abstract:As one of common diseases among elderly, stroke often leads to motor impairment and even serious disability. Post-stroke rehabilitation is of great importance to restore the motor function and improve the life quality of stroke survivors. This study therefore sets out to propose a hybrid system based on brain-computer interface and virtual reality, which can provide various training programs including action observation, motor imagery and physical therapy for post-stroke patients with different motor control levels and training demands The present work offers new insights into the way in which the conventional rehabilitation programs can be turned into innovative and interactive training experiences with advanced technologies to make optimal rehabilitation outcomes for stroke survivors. Copyright (C) 2020 The Authors.

Abstract:This article explores collaborative research in the fields of user experience and design for healthcare. In particular, it explores methods of cognitive ergonomics to apply them to the analysis of best practices in design for healthcare. Specifically, the interest lies in analyzing cognitive aspects of interaction and the way it impacts user experience with various categories of healthcare products. These products were categorized based on the research on future trends in healthcare, consumer behaviors, and design of medical devices. The methods applied to analyzing best practices were developed based on the literature review on cognitive ergonomics and adapted to industrial design practice. The aim of the analysis was to test the new method, described in the article, on the identified categories of medical products and observe what the tangible elements of cognitive interaction are. The article concludes with presenting a canvas that visualizes the overall interaction process, highlighting the strengths and issues in the cognitive aspects of interaction.

Abstract:Chinese Shanshui is a landscape painting document mainly drawing mountain and water, which is popular in Chinese culture. However, it is very challenging to create this by general people. In this paper, we propose an interactive and generative approach to automatically generate the Chinese Shanshui painting documents based on users' input, where the users only need to sketch simple lines to represent their ideal landscape without any professional Shanshui painting skills. This sketch-to-Shanshui translation is optimized by the model of cycle Generative Adversarial Networks (GAN). To evaluate the proposed approach, we collected a large set of both sketch data and Chinese Shanshui painting data to train the model of cycle-GAN, and developed an interactive system called Shanshui-DaDA (i.e., Design and Draw with AI) to generate Chinese Shanshui painting documents in real-time. The experimental results show that this system can generate satisfied Chinese Shanshui painting documents by general users. © 2019 IEEE.

Abstract:In the large amount of available data, information insensitive to faults in historical data interferes in gear fault feature extraction. Furthermore, as most of the fault diagnosis models are learned from offline data collected under single/fixed working condition only, this may cause unsatisfactory performance for complex working conditions (including multiple and unknown working conditions) if not properly dealt with. This paper proposes a transfer learning-based fault diagnosis method of gear faults to reduce the negative effects of the abovementioned problems. In the proposed method, a cohesion evaluation method is applied to select sensitive features to the task with a transfer learning-based sparse autoencoder to transfer the knowledge learnt under single working condition to complex working conditions. The experimental results on wind turbine drivetrain diagnostics simulator show that the proposed method is effective in complex working conditions and the achieved results are better than those of traditional algorithms.

Abstract:The Public Healthcare Sector is experiencing a profound crisis due to socio-dynamic changes (Parameswaran&Raijmakers, 2010) difficult to manage, such as demographic aging and population growth. Furthermore, if we consider the new alternative approaches in disease management and the growing participation of patients in healthcare decision making (Vahdat et al., 2014), deep considerations and paradigmatic shifts in the way healthcare professionals design, produce and use the medical products are needed. The growing interest in the potential of Design approaches, from which to draw consolidated models of thought and creative and divergent practices (Chamberlain, 2015) to respond to fundamental challenges for the health of our society, has recently expanded from the dimension of products and services. This represents an unmissable opportunity for the Design Discipline to switch from a Product-Centered model to a Human-Centered model where the user is placed in the center of the process and the product expands into product/service with a systemic perspective. The introduction of Service Design in medical settings requires a multilevel approach that analyzes the complexity of the system, in which the nature of the problems intersects with economic and social dynamics too. From this point of view, the methodologies of Service Design offer conceptual models that help to focus the design action on the User Experience, considering all the characteristics of the service in a structured way and openly thinking about the individual components without losing the holistic view. According to this new perspective and given the growing relevance of services in the contemporary economy, in the corporate strategies and in the public sector, the academic approach to Service Design and the Service Design Education in the context of Healthcare need to be revised through a better definition of design competencies (Morelli&Götzen, 2017). In the light of these considerations, this paper describes the didactic experience held within an International Master of Science in Product Design at Sapienza University of Rome, where the students have experimented the methods of the Service Design (Stickdorn et al., 2011) to respond to the problem of designing the User Experience (Norman, 2004) in a Public Healthcare Context. The aim was to transfer to the students the skills useful for achieving a Service and Social Innovation (Manzini, 2015) in the field of Public Healthcare through the development of a Design Proposal of a product/service that would provide a new User Experience for the Pediatric Emergency Room of the local public Hospital 'Policlinico Umberto I’ by taking into consideration its social, economic and technological long-term sustainability. In order to reach that goal, the didactic activities were organized as a three-step process (Research, Design, Develop) each with their own tools that have supported students in learning, thinking, analyzing, understanding, and evaluating all the stages of the design process. The course finalized at a set of Design Proposals demonstrating the potential of Design Discipline to bring improvements to the Public Healthcare Services Sector thanks to its creative and divergent thinking and to the development of effective Users Experiences.

Abstract:©2020 IEEE In this paper, a fault diagnosis method combining one-dimensional convolutional neural network (1DCNN) and random forest (RF), which is called 1DCNN-RF, is proposed for rotating machinery gearbox. This method uses 1DCNN to extract features from the collected multiple sensor signals, and then uses RF algorithm for classification. Compared to the existing approaches, this algorithm can improve the accuracy of fault diagnosis for rotating machinery gearbox. Finally, experiments are conducted on the Wind Tfirbine Drivetrain Diagnostic Simulator (WTDDS) to show the effectiveness of the proposed scheme.

Abstract:The research aims to share the results from the “Warm Up” Workshop—an experimental project held by PhD Product Design students from Sapienza University of Rome in collaboration with St. Petersburg University (SPbU)—involving students from SPbU’s Graphic Design Master Degree Program. The objective is to apply the topics of Design for Social Innovation and Design for Public Space to investigate the opportunities for new sociability in the social context of Vasilyevsky Island in St. Petersburg. The experimental aspect of the workshop is due to the fusion of methods and approaches typical of Product Design, such as human-centered design (HCD), and the Avant-Garde heritage of the Russian School. By illustrating their concepts of products/services, the students have developed a new practice within the fields of Product Design and User Experience. The final result is to serve a hypothetical urban regeneration in terms of Social Innovation, designing the user experiences as storyboards with the classical structure of “before and after” that would narrate the final change in users’ behaviors.

Abstract:©2020 IEEE Previous research results have emphasized the influence of avatar representations on user perception in virtual environments, including presence and embodiment. It has been reported that realistic hands present a strong sense of presence and body ownership, while there is a controversy about the sense of agency. This paper investigates the influence of virtual hand representation on user perception and the association between the sense of body ownership and agency. An experiment based on virtual reality was designed with hand representations of different levels of realism to collect users’ perception data through questionnaires, and the Spearman correlation was adopted to analyze the relationship between body ownership and agency. The results show that realistic hand induces the higher sense of presence and body ownership, but there is no significant difference in the sense of agency. Moreover, a positive correlation between body ownership and agency in virtual environments was found.

Abstract:Amidst the COVID-19, the use of technology in the learning environment was no longer a matter of choice. Forced by circumstance, educators had to adapt in order to see the academic year through. While for some, already used to an online modality, it was business as always, for others was the start of a journey through unfamiliar territory. This study inserts itself in such context. It presents and discusses results gathered through an online questionnaire about the perceptions and personal experiences of design educators in Higher Education (HE) caught in this move from in-class face-to-face onto online teaching. Objectively, it portrays how this shift impacted their ability to teach, the compromises made or alternatives sought, and views towards a more technologically enabled future in HE. From a more extensive reliance on Learning Management Systems (LMS), changes in the learning environment, and perspectives of near-future uses of Virtual Reality (VR) in distance education, this study covers uses of technology but also the identification of pain points influencing the overall experience, as well as positive perceptions and significant changes made to the learning environment.

Abstract:© 2020 IEEE. WebVR technology is widely used as a visualization approach to display virtual objects on 2D webpages. Much of the current literature on virtual object manipulation on the 2D screen pays particular attention to task performance, but few studies focus on users' psychological feedback and no literature aims at its relationship with task performance. This paper compares manipulation modes with different degrees of freedom (DoF) in translation and rotation on WebVR to explore users' workload and presence by self-reported data, and task performance by measuring completion time and error rate. The experiment results present that the increase of DoF is associated with lower perceived workload, while people may feel a higher level of presence during tasks. Additionally, this study only finds a positive correlation between workload and efficiency, and a negative correlation between presence and efficiency, which means that when feeling less workload or more presence, people tend to spend less time to complete translation and rotation tasks on WebVR.

Abstract:Electroencephalogram (EEG) signal analysis, which is widely used for human-computer interaction and neurological disease diagnosis, requires a large amount of labeled data for training. However, the collection of substantial EEG data could be difficult owing to its randomness and non-stationary. Moreover, there is notable individual difference in EEG data, which affects the reusability and generalization of models. For mitigating the adverse effects from the above factors, transfer learning is applied in this field to transfer the knowledge learnt in one domain into a different but related domain. Transfer learning adjusts models with small-scale data of the task, and also maintains the learning ability with individual difference. This paper describes four main methods of transfer learning and explores their practical applications in EEG signal analysis in recent years. Finally, we discuss challenges and opportunities of transfer learning and suggest areas for further study. (c) 2020 Elsevier B.V. All rights reserved.

Abstract:Data-driven based rolling bearing fault diagnosis has been widely investigated in recent years. However, in real-world industry scenarios, the collected labeled samples are normally in a different data distribution. Moreover, the features of bearing fault in the early stages are extremely inconspicuous. Due to the above mentioned problems, it is difficult to diagnose the incipient fault under different scenarios by adopting the conventional data-driven methods. Therefore, in this paper a new unsupervised rolling bearing incipient fault diagnosis approach based on transfer learning is proposed, with a novel feature extraction method based on a statistical algorithm, wavelet scattering network, and a stacked auto-encoder network. Then, the geodesic flow kernel algorithm is adopted to align the feature vectors on the Grassmann manifold, and the k-nearest neighbor classifier is used for fault classification. The experiment is conducted based on two bearing datasets, the bearing fault dataset of Case Western Reserve University and the bearing fault dataset of Xi'an Jiaotong University. The experiment results illustrate the effectiveness of the proposed approach on solving the different data distribution and incipient bearing fault diagnosis issues.

Abstract:Deep transfer learning (DTL) has developed rapidly in the field of motor imagery (MI) on brain-computer interface (BCI) in recent years. DTL utilizes deep neural networks with strong generalization capabilities as the pre-training framework and automatically extracts richer and more expressive features during the training process. The goal of this paper is utilizing the DTL to classify MI electroencephalogram (EEG) signals on the premise of a small data set. The publicly available dataset III of the second BCI competition is applied in both the training part and testing part to evaluate the effectiveness of the proposed method. Firstly in the process, finite impulse response (FIR) filter and wavelet transform threshold denoising method are used to remove redundant signals and artifacts in EEG signals. Then, the continuous wavelet transform (CWT) is utilized to convert the one-dimensional EEG signal into a two-dimensional time-frequency amplitude representation as the input of the pre-trained convolutional neural network (CNN) for classifying two types of MI signals. Employing the input data of 140 trials for training, the final classification accuracy rate reaches 96.43%%. Compared with the results of some superior machine learning models using the same data set, the accuracy and Kappa value of this DTL model are better. Therefore, the proposed scheme of MI EEG signal classification based on the DTL method offers preferably empirical performance.

Abstract:With the requirements for safety and stability of rotating machinery, its fault diagnosis is significantly important. To diagnose simultaneous faults of gearbox and bearing in rotating machinery under different working conditions, an improved algorithm based on cohesion-based feature selection and improved back-propagation multi-label learning (BP-MLL) is proposed in this paper. Cohesion evaluation technique is applied to construct a low-dimensional feature vector by selecting high sensitivity parameters in a high-dimensional vector from time and frequency domain. Improved BP-MLL neural network algorithm considers correlation between labels and adopts ReLU as activation function. To show the effectiveness of the proposed method, hardware experiments are conducted on wind turbine drivetrain diagnostics simulator (WTDDS) for simultaneous fault diagnosis. The experiment reveals that the proposed method can achieve better results than conventional methods under six performance evaluation metrics.

Abstract:In this paper, an improved simultaneous fault diagnostic algorithm with cohesion-based feature selection and improved backpropagation multilabel learning (BP-MLL) classification is proposed to localize and diagnose different simultaneous faults on gearbox and bearings in rotating machinery. Cohesion evaluation algorithm selects high sensitivity feature parameters from time and frequency domain in high-dimensional vectors to construct low-dimensional feature vectors. The BP-MLL neural network is utilized for fault diagnosis by classifying the feature vectors. An effective global error function is proposed in BP-MLL neural network by modifying distance function to improve both generalization ability and fault diagnostic ability of full-labeled and nonlabeled situations. To demonstrate the effectiveness of the proposed method, simultaneous fault diagnosis experiments are conducted via wind turbine drivetrain diagnostics simulator (WTDDS). The experiment results show that the proposed method has better overall performance compared with conventional BP-MLL algorithm and some other learning algorithms.

Abstract:Virtual object manipulation as a key feature has been studied in virtual reality (VR) environments. Previous studies highlighted user experience on three basic types of virtual object manipulation, translation, rotation and scaling. However, prior literature mainly studied task performance in manipulation modes with different degrees of freedom (DoF), and few studies assessed user experience by evaluating the psychological response, such as mental workload on these three basic manipulation types in virtual environments. This paper compared manipulation modes with 1DoF and 3DoF to assess users' mental workload as a critical indicator of user experience by electroencephalogram (EEG) measurement and questionnaires in manipulation tasks on the webpage with VR effects (also known as WebVR). By applying signal processing and statistical methods to analyze EEG data from ten subjects, the results demonstrated that the participants generally perceive less mental workload by 1DoF manipulation modes than 3DoF on WebVR. Besides, this study also found some different results between objective and subjective data.