ABSTRACT
Simulating real-world experiences in a safe environment has made virtual human medical simulations a common use case for research and interpersonal communication training. Despite the benefits virtual human medical simulations provide, previous work suggests that users struggle to notice when virtual humans make potentially life-threatening verbal communication mistakes inside virtual human medical simulations. In this work, we performed a 2x2 mixed design user study that had learners (n = 80) attempt to identify verbal communication mistakes made by a virtual human acting as a nurse in a virtual desktop environment. A virtual desktop environment was used instead of a head-mounted virtual reality environment due to Covid-19 limitations. The virtual desktop environment experience allowed us to explore how frequently learners identify verbal communication mistakes in virtual human medical simulations and how perceptions of credibility, reliability, and trustworthiness in the virtual human affect learner error recognition rates. We found that learners struggle to identify infrequent virtual human verbal communication mistakes. Additionally, learners with lower initial trustworthiness ratings are more likely to overlook potentially life-threatening mistakes, and virtual human mistakes temporarily lower learner credibility, reliability, and trustworthiness ratings of virtual humans. From these findings, we provide insights on improving virtual human medical simulation design. Developers can use these insights to design virtual simulations for error identification training using virtual humans.
ABSTRACT
As the COVID-19 pandemic rampages across the world, the demands of video conferencing surge. To this end, real-time portrait segmentation becomes a popular feature to replace backgrounds of conferencing participants. While feature-rich datasets, models and algorithms have been offered for segmentation that extract body postures from life scenes, portrait segmentation has yet not been well covered in a video conferencing context. To facilitate the progress in this field, we introduce an open-source solution named PP-HumanSeg. This work is the first to construct a large-scale video portrait dataset that contains 291 videos from 23 conference scenes with 14K fine-labeled frames and extensions to multi-camera teleconferencing. Furthermore, we propose a novel Self-supervised Connectivity-aware Learning (SCL) for semantic segmentation, which introduces a self-supervised connectivity-aware loss to improve the quality of segmentation results from the perspective of connectivity. And we propose an ultra-lightweight model with SCL for practical portrait segmentation, which achieves the best trade-off between IoU and the speed of inference. Extensive evaluations on our dataset demonstrate the superiority of SCL and our model.
ABSTRACT
The ongoing coronavirus pandemic has accelerated the adoption of AI-powered task-oriented chatbots by businesses and healthcare organizations. Despite advancements in chatbot platforms, implementing a successful and effective bot is still challenging and requires a lot of manual work. There is a strong need for tools to help conversation analysts quickly identify problem areas and, consequently, introduce changes to chatbot design. We present a visual analytics approach and tool for conversation analysts to identify and assess common patterns of failure in conversation flows. We focus on two key capabilities: path flow analysis and root cause analysis. Interim evaluation results from applying our tool in real-world customer production projects are presented.
ABSTRACT
In order to effectively combat Air Pollution, it is necessary for the government and the community to work together. Easily comprehensible visualizations can play a major role in drawing public attention and spreading awareness about seemingly intangible air pollution. Considering the widespread usage of Android-based devices, in this paper, we propose an Augmented Reality based application called AiR, to help users to visualize pollutants in the air and to create an immersive user experience. It aims to interactively engage a wide variety of users and create awareness without overwhelming them with data. AiR visualizes 12 pollutants [PM10, PM2.5, NO, NO2, NOx, CO, SO2,O-3,NH3, C6H6, (CH3)C6H5 and (CH3)(2)C6H5] through unique models. We demonstrate our application on pollution data by CPCB from various weather stations across India collected over the initial lockdown period due to COVID-19 in India.
ABSTRACT
Time series forecasts are ubiquitous, ranging from daily weather forecasts to projections of pandemics such as COVID-19. Communicating the uncertainty associated with such forecasts is important, because it may affect users' trust in a forecasting model and, in turn, the decisions made based on the model. Although there exists a growing body of research on visualizing uncertainty in general, the important case of visualizing prediction uncertainty in time series forecasting is under-researched. Against this background, we investigated how different visualizations of predictive uncertainty affect the extent to which people follow predictions of a time series forecasting model. More specifically, we conducted an online experiment on forecasting occupied hospital beds due to the COVID-19 pandemic, measuring the influence of uncertainty visualization of algorithmic predictions on participants' own predictions. In contrast to prior studies, our empirical results suggest that more salient visualizations of uncertainty lead to decreased willingness to follow algorithmic forecasts.
ABSTRACT
COVID-19 is a severe global epidemic in human history. Even though there are particular medications and vaccines to curb the epidemic, tracing and isolating the infection source is the best option to slow the virus spread and reduce infection and death rates. There are three disadvantages to the existing contact tracing system: 1. User data is stored in a centralized database that could be stolen and tampered with, 2. User's confidential personal identity may be revealed to a third party or organization, 3. Existing contact tracing systems [1] [2] only focus on information sharing from one dimension, such as location-based tracing, which significantly limits the effectiveness of such systems. We propose a global COVID-19 information sharing and risk notification system that utilizes the Blockchain, Smart Contract, and Bluetooth. To protect user privacy, we design a novel Blockchain-based platform that can share consistent and non-tampered contact tracing information from multiple dimensions, such as location-based for indirect contact and Bluetooth-based for direct contact. Hierarchical smart contract architecture is also designed to achieve global agreements from users about how to process and utilize user data, thereby enhancing the data usage transparency. Furthermore, we propose a mechanism to protect user identity privacy from multiple aspects. More importantly, our system can notify the users about the exposure risk via smart contracts. We implement a prototype system to conduct extensive measurements to demonstrate the feasibility and effectiveness of our system.
ABSTRACT
Spinal Cord injury (SCI) significantly affects all parts of life, and mental illness and social isolation are common and often undetected after discharge from traditional care. Mobile health and sensor monitoring have emerged as convenient and beneficial supplements to clinical care, even more so with restricted in-person health care during COVID-19. We apply these in SCI to collect and analyze in-situ active self-report as well as passive sensor data from personal smartphones to infer results and correlations between their psychosocial and physical well-being. We have applied Autoregressive Integrated Moving Average (ARIMA) to understand time dependent relationships between depression severity, social interaction, and community mobility, and explored clustering analysis and parallel predictive models to inform just-in-time adaptive interventions. Preliminary analyses suggest that smartphones, as a symptom monitoring tool and to deliver an in-situ individualized intervention have potential to positively impact depression severity and community participation after SCI.
ABSTRACT
Madel-Driven Engineering (MDE) advocates the use of models and their transformations, to better understand software systems and to increase the degree of automation across the software development process. However, with the increasing complexity of modern software systems, distributed development teams, and increasing time pressure for developing these systems, there is a need to collaborate more quickly when building and analyzing models. Furthermore, the COVID-19 pandemic has forced classroom-based software projects to organizational-level software systems to rely on virtual (web-based) collaborative development environments. Therefore, real-time collaborative modelling remains no longer an option but becomes a necessity for MDE too. In our previous work, we introduce a framework, tColab, which uses Eclipse Che workspaces to enable web-based collaborative modelling. However, with real-time collaboration, modelling conflicts can arise and their resolution goes beyond what is possible with the collaborative environment facilitated by an Eclipse Che workspace. In this paper, we extend our tColab framework for building modelling language editors as Visual Studio (VS) Code extensions. These VS Code extensions are well supported by widely used platforms such as VS Code IDE, Eclipse Theta IDE, and the Eclipse Che platform. Furthermore, to facilitate real-time collaboration using these VS Code extensions and to enable conflict-free modelling, we explore two possible solutions - the VS Code Live Share extension and the Teletype CRDTs (conflict-free replicated data types) library. Finally, we provide a prototypical VS Code extension for the TGRL (Textual Goal-oriented Requirement Language) as a proof-of-concept of our extended framework and demonstrate conflict-free collaborative modelling for TGRL using the Live Share extension.
ABSTRACT
After a break in 2020, this year the 15th edition of the workshop Models@run.time is held at the 24th International Conference on Model Driven Engineering Languages and Systems. The workshop takes place virtually due to the Covid-19 pandemic on the 11th of October 2021. The workshop is organized by Sebastian Glitz, Antonio Bucchiarone and Nelly Bencomo. Here, we present some highlights of the workshop.
ABSTRACT
The COVID-19 pandemic did not only dramatically impact the personal and social lives, for many academics, it also demanded immediate changes to the way their courses are taught. While a pragmatic approach is to do conventional lectures via video streaming platforms, much more may be done to educate students also in a remote setting properly. This particularly holds true for practice-oriented and technology-engaging courses. This paper describes our experience of transforming an in-person Master level class on model-driven software engineering into a distance learning one. We describe the structure, the content, the teaching and examination format, and the used platforms in detail. We critically reflect on our experiences and report the feedback gained by a post-class student evaluation. We believe this paper provides meaningful lessons learned and best practices for other educators challenged with the task of teaching similar courses in a remote setting. With this paper, we publish an openly available Github repository that features all course content including sample solutions for all practical lab assignments.
ABSTRACT
The COVID-19 pandemic has presented unprecedented challenges across the world and universities are not saved either. Standard classroom activities in COVID era are even more challenging, with the primary challenge being ensuring physical distancing. We present a smart classroom system, BubbleNet, that attempts to relax these challenges. BubbleNet leverages cost-effective (similar to$30) IoT nodes with motion sensors. The IoT nodes collaborate with each other via OpenThread - the latest open-source mesh networking protocol released by Google. In this paper, we present the development and demonstration of BubbleNet for monitoring physical distancing rules in a classroom.
ABSTRACT
In this demo paper, we feature HealthDist, an innovative system that is an additional asset in the fight against the COVID-19 pandemic. HealthDist utilizes context (e.g., weather conditions), location (e.g., crowded areas), and user preferences to provide safe pedestrian paths which decrease the exposure to the virus causing COVID-19. Its modular design, consisting of four components, reduces the time and resources needed to provide accurate localization and indoor-outdoor path recommendations that satisfy the user's preferences. We demonstrate interactively using smartphones how HealthDist can provide real time navigation information within a university campus and illustrate the reduction of the COVID-19 exposure risk while satisfying the constraints defined by the user.
ABSTRACT
Vital signs are important parameters that can reflect people's physiological status and help physicians provide medical advice. Remote Photoplethysmography (rPPG) is a fast, low-cost and convenient method to remotely collect biometric data, and requires only a facial video recorded using a smartphone or other camera. Remote medical service provisioning proved to be a dire need during the COVID-19 pandemic. To leverage the cloud-based medical advice provisioning platform of Your Doctors Online, we propose a rPPG methodology to measure people's Heart Rate (HR) and Heart Rate Variability (HRV) based on a facial video recorded by the users using a smartphone. We validate our model on the TokyoTech remote PPG dataset.
ABSTRACT
Unraveling human mobility patterns is critical for understanding disease spread and implementing effective controls during large-scale disease outbreaks such as the COVID-19 pandemic. Given the urgency associated with such situations, it is important to leverage on the common existing digital infrastructures that can be readily activated for disease outbreak analytics. We introduce an integrated system for disease outbreak investigation using data from Wi-Fi sessions. The system offers outbreak analytics, simulation, and visualization capabilities to assist in the identification of infection hot-spots and in contact-tracing exercises. The system has been developed and experimentally deployed for research purposes on a large local university campus in Singapore.
ABSTRACT
The COVID-19 pandemic poses new challenges in providing safe pedestrian navigation information that helps to reduce the risk of severe illness due to the highly contagious nature of the virus. In this paper, we present an innovative system, dubbed HealthDist, which utilizes the context (e.g., weather conditions), location (e.g., crowded areas) and user's preferences to support safe mobility. It consists of four modules that allow efficient contact tracing, social distancing, and isolation. HealthDist's modular design reduces the time and resources needed to provide accurate localization for measuring density in common spaces and measuring potential infection exposure, and recommend outdoor and indoor paths satisfying the user's preferences. HealthDist's initial deployment within a university campus demonstrated its capability to provide real time navigation information that reduces the COVID-19 exposure risk while at the same time satisfying the constraints defined by the user.
ABSTRACT
Using multiple monitors is commonly thought to improve productivity, but this is hard to check experimentally. We use a survey, taken by 101 practitioners of which 80% have coded professionally for at least 2 years, to assess subjective perspectives based on experience. To improve validity, we compare situations in which developers naturally use different setups-the difference between working at home or at the office, and how things changed when developers were forced to work from home due to the Covid-19 pandemic. The results indicate that using multiple monitors is indeed perceived as beneficial and desirable. 19% of the respondents reported adding a monitor to their home setup in response to the Covid-19 situation. At the same time, the single most influential factor cited as affecting productivity was not the physical setup but interactions with co-workers-both reduced productivity due to lack of connections available at work, and improved productivity due to reduced interruptions from co-workers. A central implication of our work is that empirical research on software development should be conducted in settings similar to those actually used by practitioners, and in particular using workstations configured with multiple monitors.
ABSTRACT
In the early months of 2020, the COVID-19 pandemic suddenly transformed the way the world works and collaborates. With all work-related travel abruptly curtailed and most company professionals and academics working from home, the daily work environment shifted to an ecosystem enabled by online communication and collaboration tools. In 2021, workflows continue to evolve for both universities and corporations - to better support R&D, education, and ideation. This panel will discuss how COVID-19-inspired innovation ecosystems have changed - for better or worse - university-company collaborations. Panelists will share personal observations, challenges, results, and ideas for the future.
ABSTRACT
Due to the global pandemic, in March 2020 we in academia and industry were abruptly forced into working from home. Yet teaching never stopped, and neither did developing software, fixing software, and expanding into new markets. Demands for flexible ways of working, responding to new requirements, have never been so high. How did we manage to continue working, when we had to suddenly switch all communication to online and virtual forms of contact? In this short paper we describe how Ocuco Ltd., a medium-sized organization headquartered in Ireland, managed our software development teams - distributed throughout Ireland, Europe, Asia and America during the COVID-19 pandemic. We describe how we expanded, kept our customers happy, and our teams motivated. We made changes, some large, such as providing emergency financial support;others small, like implementing regular online social pizza evenings. Technology and process changes were minor, an advantage of working in globally distributed teams since 2016, when development activities were coordinated according to the Scaled Agile Framework (SAFe). The results of implementing the changes were satisfying;productivity went up, we gained new customers, and preliminary results from our wellness survey indicate that everyone feels extremely well-supported by management to achieve their goals. However, the anonymised survey responses did show some developers' anxiety levels were slightly raised, and many are working longer hours. Administering this survey is very beneficial, as now we know, so we can act.
ABSTRACT
The COVID-19 pandemic presented itself as a challenge for separate societal sectors. On the information technology (IT) standpoint, it does include the maintenance of the infrastructure required to hold collaborative activities that went to happen online;the implementation of projects in a scenario of uncertainty;and keep the software engineering and information security best practices in place. This article presents the context of a data science team organized as a skunk works group composed of professionals with experience in both the industry and academia, located in an IT department working with a team of seasoned data engineers. At the time the pandemic started, the relatively new data science team was positioning itself as a Center of Excellence in Advanced Analytics. With the pandemic, it had to keep up with the expectations from the stakeholders;manage current and upcoming data science projects within the methodology practiced in IT;and maintain a high level in the quality of service delivered. This article discusses how did the COVID-19 pandemic affected the team productivity and its practices as well as the lessons learned with it.