Human-centered Research Research Articles

Performance Analysis of Deep Learning based Human Activity Recognition Methods

Human Activity Recognition (HAR) is one of the most important branches of human-centered research activities. Along with the development of artificial intelligence, deep learning techniques have gained remarkable success in computer vision. In recent years, there is a growing interest in Human Activity Recognition systems applied in healthcare, security surveillance, and human motion-based activities. A HAR system is essentially made of a wearable device equipped with a set of sensors (like accelerometers, gyroscopes, magnetometers, heart-rate sensors, etc.). Different methods are being applied for improving the accuracy and performance of the HAR system. In this paper, we implement Artificial Neural Network (ANN), and Convolutional Neural Network (CNN) in combination with Long Short-term Memory (LSTM) methods with different layers and compare their outputs towards the accuracy in the HAR system. We compare the accuracy of different HAR methods and observed that the performance of our proposed model of CNN 2 layers with LSTM 1 layer is the best.

Understanding Design Approaches and Evaluation Methods in mHealth Apps Targeting Substance Use: Protocol for a Systematic Review.

BackgroundSubstance use and use disorders in the United States have had significant and devastating impacts on individuals and communities. This escalating substance use crisis calls for urgent and innovative solutions to effectively detect and provide interventions for individuals in times of need. Recent mobile health (mHealth)–based approaches offer promising new opportunities to address these issues through ubiquitous devices. However, the design rationales, theoretical frameworks, and mechanisms through which users’ perspectives and experiences guide the design and deployment of such systems have not been analyzed in any prior systematic reviews.ObjectiveIn this paper, we systematically review these approaches and apps for their feasibility, efficacy, and usability. Further, we evaluate whether human-centered research principles and techniques guide the design and development of these systems and examine how the current state-of-the-art systems apply to real-world contexts. In an effort to gauge the applicability of these systems, we also investigate whether these approaches consider the effects of stigma and privacy concerns related to collecting data on substance use. Lastly, we examine persistent challenges in the design and large-scale adoption of substance use intervention apps and draw inspiration from other domains of mHealth to suggest actionable reforms for the design and deployment of these apps.MethodsFour databases (PubMed, IEEE Xplore, JMIR, and ACM Digital Library) were searched over a 5-year period (2016-2021) for articles evaluating mHealth approaches for substance use (alcohol use, marijuana use, opioid use, tobacco use, and substance co-use). Articles that will be included describe an mHealth detection or intervention targeting substance use, provide outcomes data, and include a discussion of design techniques and user perspectives. Independent evaluation will be conducted by one author, followed by secondary reviewer(s) who will check and validate themes and data.ResultsThis is a protocol for a systematic review; therefore, results are not yet available. We are currently in the process of selecting the studies for inclusion in the final analysis.ConclusionsTo the best of our knowledge, this is the first systematic review to assess real-world applicability, scalability, and use of human-centered design and evaluation techniques in mHealth approaches targeting substance use. This study is expected to identify gaps and opportunities in current approaches used to develop and assess mHealth technologies for substance use detection and intervention. Further, this review also aims to highlight various design processes and components that result in engaging, usable, and effective systems for substance use, informing and motivating the future development of such systems.International Registered Report Identifier (IRRID)DERR1-10.2196/35749

Progressing Towards a Human-Centric Approach in Cancer Research.

Despite the advancement in research methodologies and technologies for cancer research, there is a high rate of anti-cancer drug attrition. In this review, we discuss different conventional and modern approaches in cancer research and how human-centric models can improve on the voids conferred by more traditional animal-centric models, thereby offering a more reliable platform for drug discovery. Advanced three-dimensional cell culture methodologies, along with in silico computational analysis form the core of human-centric cancer research. This can provide a holistic understanding of the research problems and help design specific and accurate experiments that could lead to the development of better cancer therapeutics. Here, we propose a new human-centric research roadmap that promises to provide a better platform for cancer research and drug discovery.

A Scientific Research Information System via Intelligent Blockchain Technology for the Applications in University Management

The scientific research information system plays an essential role in improving management efficiency and promoting technological innovation in universities. With the increasing computational demand for human-centric research management, blockchain technology, with distributed storage, consensus sharing, and security traceability, has efficiently assisted the research information system in dealing with various issues such as big-data scale, information security, interconnection, rapid response, and private security. A novel scientific information system framework based on intelligent blockchain technology is proposed to promote university scientific research’s information level and management efficiency. Moreover, four smart data contracts, including data collection, verification, sharing, and supervision, are custom-designed under an efficient scientific research information system. Those intelligent contracts provide reliable data security and traceability algorithms to guarantee the practical application of the scientific research information system. The results show that the constructed system can relieve the centralized storage pressure of scientific research information and solve the cross-subject sharing obstacle of massive safety data among different systems. Thereby, the system increases the transparency of scientific evaluation and realizes the credible supervision of scientific research information, which provides a way to promote the innovative application of blockchain technology in scientific research management in colleges and universities.

Low-Cost Thermohygrometers to Assess Thermal Comfort in the Built Environment: A Laboratory Evaluation of Their Measurement Performance

A thermohygrometer is an instrument that is able to measure relative humidity and air temperature, which are two of the fundamental parameters to estimate human thermal comfort. To date, the market offers small and low-cost solutions for this instrument, providing the opportunity to bring electronics closer to the end-user and contributing to the proliferation of a variety of applications and open-source projects. One of the most critical aspects of using low-cost instruments is their measurement reliability. This study aims to determine the measurement performance of seven low-cost thermohygrometers throughout a 10-fold repeatability test in a climatic chamber with air temperatures ranging from about −10 to +40 °C and relative humidity from approximately 0 to 90%. Compared with reference sensors, their measurements show good linear behavior with some exceptions. A sub-dataset of the data collected is then used to calculate two of the most used indoor (PMV) and outdoor (UTCI) comfort indexes to define discrepancies between the indexes calculated with the data from the reference sensors and the low-cost sensors. The results suggest that although six of the seven low-cost sensors have accuracy that meets the requirements of ISO 7726, in some cases, they do not provide acceptable comfort indicators if the values are taken as they are. The linear regression analysis suggests that it is possible to correct the output to reduce the difference between reference and low-cost sensors, enabling the use of low-cost sensors to assess indoor thermal comfort in terms of PMV and outdoor thermal stress in UTCI and encouraging a more conscious use for environmental and human-centric research.

A multi-dimensional analysis of conclusions in research articles: Variation across disciplines

Research article sections, particularly the introductions, have received considerable scholarly attention over the years. However, linguistic strategies in the conclusion sections of research articles (RAs) remain under-researched. In light of this, we aspired to add to such scholarship by examining linguistic variation in RA conclusions across six disciplines. A multi-dimensional analysis of conclusions was conducted by using Biber’s (1988) dimensions. Analytical results indicate that the conclusion writers in natural sciences and social sciences exhibit significant differences along D1 (Involved and Informational Discourse), D2 (Narrative and Non-Narrative), and D4 (Overt Expression of Persuasion). The findings suggest that conclusions from all six disciplines tend to use possibility modals (e.g., can) and prediction modals (e.g., will) to evaluate studies and to refer to future research directions. Additionally, conclusions in education and sociology tend to contain more interaction and persuasion elements than those in natural sciences, indicating a more human-centered research approach to soft sciences. On the other hand, conclusions in natural sciences are more information-condensed and procedure-oriented than those in social sciences. This study adds to the growing knowledge of RA sections and contributes to the study and teaching of EAP and ESP.

Supporting Remote Experimentation Through Computer-Mediated Communication

With the emergence of COVID-19 and the resultant reduction in direct personal contact, we were faced with a novel challenge of how to conduct studies that involved both semi-structured elicitation of detailed cognitive information and the evaluation of software interfaces and algorithms. We leveraged distributed communication technologies to support data collection across three separate human-computer interaction studies. We describe these studies in terms of specific computer-mediated communication methods and features and how we used them. We also present lessons learned, potential risks and detriments of using such approaches, (e.g., connectivity dependence, reduced ability to observe non-verbal cues, and diminished interpersonal interaction), along with how the research community can compensate for the shortcomings of distributed data collection in human-centered research.

Human-centered AI and robotics

Robotics has a special place in AI as robots are connected to the real world and robots increasingly appear in humans everyday environment, from home to industry. Apart from cases were robots are expected to completely replace them, humans will largely benefit from real interactions with such robots. This is not only true for complex interaction scenarios like robots serving as guides, companions or members in a team, but also for more predefined functions like autonomous transport of people or goods. More and more, robots need suitable interfaces to interact with humans in a way that humans feel comfortable and that takes into account the need for a certain transparency about actions taken. The paper describes the requirements and state-of-the-art for a human-centered robotics research and development, including verbal and non-verbal interaction, understanding and learning from each other, as well as ethical questions that have to be dealt with if robots will be included in our everyday environment, influencing human life and societies.

A Research Cluster's Vision for a Pilot Factory in the South East Technological University of Ireland

A research activity proposed for the South East Technological University (SETU), Waterford in Ireland from its CONNEXIONS Catalyst pathway grant is the development of an interdisciplinary research cluster within INSYTE, which spans the schools of Business, Education, Science, Engineering and Industry. It aims to co-evolve cutting-edge models of educational delivery. This research cluster has emerged from the work of the INSYTE Centre located in the INSYTE-Cooley Research Lab (ICRL) in the Digitization Hub of the Luke Wadding Library at SETU, Waterford. Educational techniques have evolved over the past decades and these advances have not necessarily filtered down to various disciplines, e.g. engineering. The focus of this research cluster is to have the ‘Learner’ at the center of the ‘Learning Experience’ and to wrap the technology around them. This in turn, will increase the adoption and usage of such technologies. It will do this by cross-fertilization of knowledge over diverse domains to produce customised human-centred solutions for communities. Equality, diversity and inclusion are critical strands in this research. This paper shows that the European Union (EU) is supportive of changes in education required to close the skills gap in engineering and to enable reskilling to support Industry 5.0. In addition to the creation of cutting-edge models of educational delivery the vision of this multidisciplinary human centered research cluster is the establishment of a state-of-the-art pilot factory as an Irish national initiative in SETU, Waterford.

Measuring the Impact of Human-Centered Design Research

Background/Objective: Human-centered design (HCD) is an approach to research that aims to facilitate participant engagement in research studies. Research Jam is the Patient Engagement Core of the Indiana Clinical and Translational Sciences Institute (Indiana CTSI) that applies HCD to health research. The objective of this project is to assess the impact and efficacy of the HCD approach in health research. This project follows-up with previous investigators who have completed a project with Research Jam to measure impact on investigators’ attitudes towards HCD and participant engagement as well as the efficacy and implementation of the project-specific tools and deliverables that resulted from the work with Research Jam. 
 Project Methods: A survey was developed in Qualtrics and sent to investigators (N=34) from Research Jam’s portfolio of completed projects (2015-2020). Five follow-up interviews were conducted and analyzed in NVivo.
 Results: Survey response rate was 50%. Of the projects listed by the investigators, 89% had deliverables that were reported as feasible and relevant to the target audience. Long-term sustainability of the deliverables showed room for improvement. For all projects, 81% were reported to have helped the investigator learn how to better engage with participants to inform their subsequent research.
 Potential Impact: These findings demonstrate that HCD produces deliverables that are feasible and relevant to target audiences, and health researchers view HCD as a useful method to engage more directly with research participants. These results can serve as a guide for Research Jam to continue to refine processes, such as improving long-term sustainability of the deliverables, and to direct future projects.

HIEQLab, a facility to support multi-domain human-centered research on building performance and environmental quality

Researches on building performances and environmental quality can be performed through different approaches, including dynamic numerical simulations, in-field studies, full scale test facilities and living labs. Researches performed through full scale test facilities allow carrying out studies under controlled realistic conditions, directly involving the final users. Such approach can significantly improve the scientific research on energy efficient and healthy buildings by fostering a synergistic and user-centered innovation process. Within this context, at Politecnico di Torino, the TEBE group (Technology, Energy, Building and Environment) has designed and is realizing a full-scale facility, aimed at implementing researches on building Indoor Environmental Quality (IEQ) and energy performance. The facility will enable multi-domain studies, including thermal, air quality, acoustic and lighting aspects, involving the final user in the research process. The paper describes the features of the facility and the challenges it was conceived to face.

Human-Centered Design Science Research Evaluation for Gamified Augmented Reality

As augmented reality (AR) and gamification design artifacts for education proliferate in the mobile and wearable device market, multiple frameworks have been developed to implement AR and gamification. However, there is currently no explicit guidance on designing and conducting a human-centered evaluation activity beyond suggesting possible methods that could be used for evaluation. This study focuses on human-centered design evaluation pattern for gamified AR using Design Science Research Methodology (DSRM) to support educators and developers in constructing immersive AR games. Specifically, we present an evaluation pattern for a location-based educational indigenous experience that can be used as a case study to support the design of augmented (or mixed) reality interfaces, gamification implementations, and location-based services. This is achieved through the evaluation of three design iterations obtained in the development cycle of the solution. The holistic analysis of all iterations showed that the evaluation process could be reused, evolved, and its complexity reduced. Furthermore, the pattern is compatible with formative and summative evaluation and the technical or human-oriented types of evaluation. This approach provides a method to inform the evaluation of gamified AR apps. At the same time, it will enable a more approachable evaluation process to support educators, designers, and developers.

Human-centered implementation research: a new approach to develop and evaluate implementation strategies for strengthening referral networks for hypertension in western Kenya

BackgroundHuman-centered design (HCD) is an increasingly recognized approach for engaging stakeholders and developing contextually appropriate health interventions. As a component of the ongoing STRENGTHS study (Strengthening Referral Networks for Management of Hypertension Across the Health System), we report on the process and outcomes of utilizing HCD to develop the implementation strategy prior to a cluster-randomized controlled trial.MethodsWe organized a design team of 15 local stakeholders to participate in an HCD process to develop implementation strategies. We tested prototypes for acceptability, appropriateness, and feasibility through focus group discussions (FGDs) with various community stakeholder groups and a pilot study among patients with hypertension. FGD transcripts underwent content analysis, and pilot study data were analyzed for referral completion and reported barriers to referral. Based on this community feedback, the design team iteratively updated the implementation strategy. During each round of updates, the design team reflected on their experience through FGDs and a Likert-scale survey.ResultsThe design team developed an implementation strategy consisting of a combined peer navigator and a health information technology (HIT) package. Overall, community participants felt that the strategy was acceptable, appropriate, and feasible. During the pilot study, 93% of referrals were completed. FGD participants felt that the implementation strategy facilitated referral completion through active peer engagement; enhanced communication between clinicians, patients, and health administrators; and integrated referral data into clinical records. Challenges included referral barriers that were not directly addressed by the strategy (e.g. transportation costs) and implementation of the HIT package across multiple health record systems. The design team reflected that all members contributed significantly to the design process, but emphasized the need for more transparency in how input from study investigators was incorporated into design team discussions.ConclusionsThe adaptive process of co-creation, prototyping, community feedback, and iterative redesign aligned our implementation strategy with community stakeholder priorities. We propose a new framework of human-centered implementation research that promotes collaboration between community stakeholders, study investigators, and the design team to develop, implement, and evaluate HCD products for implementation research. Our experience provides a feasible and replicable approach for implementation research in other settings.Trial registrationClinicaltrials.gov, NCT02501746, registration date: July 17, 2015,

Ubermag: Toward More Effective Micromagnetic Workflows

Computational micromagnetics has become an essential tool in academia and industry to support fundamental research and the design and development of devices. Consequently, computational micromagnetics is widely used in the community, and the fraction of time researchers spend performing computational studies is growing. We focus on reducing this time by improving the interface between the numerical simulation and the researcher. We have designed and developed a human-centred research environment called Ubermag. With Ubermag, scientists can control an existing micromagnetic simulation package, such as OOMMF, from Jupyter notebooks. The complete simulation workflow, including definition, execution, and data analysis of simulation runs, can be performed within the same notebook environment. Numerical libraries, co-developed by the computational and data science community, can immediately be used for micromagnetic data analysis within this Python-based environment. By design, it is possible to extend Ubermag to drive other micromagnetic packages from the same environment.

Leveraging Design Thinking for Pharmaceutical Digital Marketing

Worldwide, the time spent online and in digital media has been increasing, thus becoming the primary source of health and medical information. This phenomenon is driving all business, including the pharmaceutical industry, in gearing toward digital marketing strategies. Developing countries like Thailand still extend existing laws to regulate digital media despite the differences with traditional media, and consumers face the risks of buying drugs illegally and products that overclaim despite stringent pre-approval regulations on drug marketing. This study utilizes design thinking as a human-centric research method to propose appropriate and practical digital marketing guidelines for the pharmaceutical industry, using 53 informants. The problems were that consumers face persuasive risks and the need for reliable sources of drug information. The current regulatory process places a high burden on regulators and the laws that enforce it. However, several new digital strategies such as unbranded information and targeted marketing are not covered by existing laws. Regulations on teleconsultation are also needed, but no legislation currently exists for such activities. And finally, experts have articulated four domains as follows: eRegulations, e-Information sources, and e-Consultation to provide easy access to professionals, and e-Ethics, a supportive mechanism toward ethical drug marketing

Row-by-Column, Plexiglass & Zoom, Oh My! A K-12 COVID-19 Storm / A Pilot

We are 21 years into the 21st century, and educational practices across North America were woefully unprepared to ‘flip the switch’ to online learning; at times no education occurred at all, not online or onsite. The COVID-19 pandemic disruptor storm peeled off the layers of blindfolds time accrued in an instant. Issues included three areas. Area one—unpreparedness: digital illiteracy relative to online learning and corresponding teaching models, equity issues pertaining to internet access and computer access, platforms that varied and were unreliable. Area two—inconsistent: (if any) guidelines on how to teach onsite, or those from a disease control group dictating a six-foot distancing, masks, plexiglass, and row-by-column with eyes facing forward (back to a 19th century teaching didactic model), and smaller class sizes. Area three-time/space continuum: the combining of online and onsite, teaching loads, and maintenance. This ‘alpha’ research study tried to capture a historic moment in time. A Human-centered Research Design (HcRD) protocol with three techniques to mitigate bias was used: (1) online survey, (2) focused interviews, and (3) crowd-sourced photographic content across two countries—USA and Canada as a convenience sample. The findings will reveal a ‘just-in-time’ snap shot of the tactics used pre- and current-, as well as ideas for post-pandemic—this research’s differentiator. The storm of COVID-19 played unprecedented havoc on schools across North America, but there are important learnings and these, along with some insights will be shared.

From Liminal Labor to Decent Work: A Human-Centered Perspective on Sustainable Tourism Employment

In its sustainable tourism agenda for 2030, the UN World Tourism Organization has embraced three United Nations Sustainable Development Goals. One of these, specifically SDG 8, highlights the need to pursue decent work and growth. Nevertheless, despite the growing recognition of this target and although there is a growing number of writings lamenting the precarity characterizing many tourism-related jobs, the topic of tourism-related work continues to receive sparse attention in the considerable volume of academic literature on tourism and sustainability. This paper attempts to redress this neglect. First, by providing a review of extant studies on tourism labor, we seek to explain why this research lacuna continues to exist. We then examine organizational and technological aspects of tourism governance, which hinder attempts to establish decent work and improve dignity in the tourism industry worldwide. By acknowledging the volatile and liminal status of tourism work and future labor market prospects, we arrive at the following question: what should sustainable tourism work look like? This leads us to suggest that the development of a human-centered research agenda, which focuses on workers’ agency and resources, offers a promising research avenue for expanding on the tourism and sustainability research agenda.

Concept of an Ontology for Automated Vehicle Behavior in the Context of Human-Centered Research on Automated Driving Styles

In the human-centered research on automated driving, it is common practice to describe the vehicle behavior by means of terms and definitions related to non-automated driving. However, some of these definitions are not suitable for this purpose. This paper presents an ontology for automated vehicle behavior which takes into account a large number of existing definitions and previous studies. This ontology is characterized by an applicability for various levels of automated driving and a clear conceptual distinction between characteristics of vehicle occupants, the automation system, and the conventional characteristics of a vehicle. In this context, the terms ‘driveability’, ‘driving behavior’, ‘driving experience’, and especially ‘driving style’, which are commonly associated with non-automated driving, play an important role. In order to clarify the relationships between these terms, the ontology is integrated into a driver-vehicle system. Finally, the ontology developed here is used to derive recommendations for the future design of automated driving styles and in general for further human-centered research on automated driving.

Toward a Formal Scholarly Understanding of Blockchain-Mediated Decentralization: A Systematic Review and a Framework

This work analyses blockchain-mediated decentralization based on a systematic review of the scholarly understanding of the term ‘decentralization’ across multiple disciplines from computer to political sciences, examining how its various meanings are reflected in popular discourse on blockchains and distributed ledgers. The paper aims to capture the rigorous cross-domain understanding of decentralization and its most important features, and to map the commonalities and differences between it and some closely related concepts such as distribution, disintermediation and peer-to-peer (P2P). Across all domains, decentralization appears to be used as a solution to problems requiring non-trivial coordination across heterogeneous stakeholders. Blockchain-mediated decentralization appears to have unique characteristics reflecting an idiosyncratic set of authority-related values prevalent in so-called ‘crypto’ online communities. Within blockchain space, the article argues against the binary positioning of ‘decentralization’ and ‘centralization’, proposing a dialectical approach and arguing that a system’s authority allocation is a quality positioned on a spectrum between purely decentralized and completely centralized, noting how a blockchain set-up could simultaneously both have facets that are significantly centralized and others that are not. The authors document their systematic review findings and propose a framework for understanding blockchain-mediated decentralization, suggesting a definition, and outlining new directions for further human-centric research into distributed ledger technologies and for designing decentralized ecosystems.

UMoDT: an unobtrusive multi-occupant detection and tracking using robust Kalman filter for real-time activity recognition

Human activity recognition (HAR) is an important branch of human-centered research. Advances in wearable and unobtrusive technologies offer many opportunities for HAR. While much progress has been made in HAR using wearable technology, it still remains a challenging task using unobtrusive (non-wearable) sensors. This paper investigates detection and tracking of multi-occupant HAR in a smart-home environment, using a novel low-resolution Thermal Vision Sensor (TVS). Specifically, the research presents the development and implementation of a two-step framework, consisting of a Computer Vision-based method to detect and track multiple occupants combined with Convolutional Neural Network (CNN)-based HAR. The proposed algorithm uses frame difference over consecutive frames for occupant detection, a set of morphological operations to refine identified objects, and features are extracted before applying a Kalman filter for tracking. Laterally, a 19-layer CNN architecture is used for HAR and afterward the results from both methods are fused using time interval-based sliding window. This approach is evaluated through a series of experiments based on benchmark Thermal Infrared datasets (VOT-TIR2016) and multi-occupant data collected from TVS. Results demonstrate that the proposed framework is capable of detecting and tracking 88.46% of multi-occupants with a classification accuracy of 90.99% for HAR.