Human-centered Systems Research Articles

Development of a Human-Centric System Using an IoT-Based Socially Embedded Robot Partner

Recently, the increasing social isolation of the elderly has caused major social problems, such as loneliness and the progression of dementia. A human-centric system could be a solution to these problems and promote coexistence with humans. Therefore, we aimed to develop a robot system using smart devices, which are essential for the Internet of things (IoT) technology, to provide services, such as information support and monitoring. As the development and application of smart devices become more sophisticated, a hyperconnected society will finally be realized through the development of smart-device-centered robots and their connection to peripheral devices. A hyperconnected society is one in which people, things, and data are connected. Personal mobility is developing and converging with robotic technology to the point where a large mobile robot can board a person. These robot technologies can be connected to wireless networks to provide organically connected services. In the era of Society 5.0, the connection among smart devices, robot systems, and mobility technology is still developing and will be a new paradigm in the development of human-centric systems in the future. Therefore, this study introduces the creation of a human-centric system using a robot system and a mobility system based on the IoT. Finally, we present several examples of the effectiveness of the proposed system and discuss its applicability.

A human-centred systems manifesto for smart digital immersion in Industry 5.0: a case study of cultural heritage

A human-centred systems manifesto for smart digital immersion in Industry 5.0: a case study of cultural heritage

Executive-centered AI? Designing predictive systems for the public sector.

Recent policies and research articles call for turning AI into a form of IA ('intelligence augmentation'), by envisioning systems that center on and enhance humans. Based on a field study at an AI company, this article studies how AI is performed as developers enact two predictive systems along with stakeholders in public sector accounting and public sector healthcare. Inspired by STS theories about values in design, we analyze our empirical data focusing especially on how objectives, structured performances, and divisions of labor are built into the two systems and at whose expense. Our findings reveal that the development of the two AI systems is informed by politically motivated managerial interests in cost-efficiency. This results in AI systems that are (1) designed as managerial tools meant to enable efficiency improvements and cost reductions, and (2) enforced on professionals on the 'shop floor' in a top-down manner. Based on our findings and a discussion drawing on literature on the original visions of human-centered systems design from the 1960s, we argue that turning AI into IA seems dubious, and ask what human-centered AI really means and whether it remains an ideal not easily realizable in practice. More work should be done to rethink human-machine relationships in the age of big data and AI, in this way making the call for ethical and responsible AI more genuine and trustworthy.

Inflammatory bowel disease (IBD)-specific immune cell recruitment and response can be modulated with anti-TNF-α therapies in the human Colon Intestine-Chip

Abstract Objective: Inflammatory bowel disease (IBD) is a complex inflammatory disease, for which few effective therapies exist. The goal of our current work was to show: i) that such a complex, immune cell-driven pathogenesis could be captured on Emulate’s human Colon Intestine-Chips; and ii) that this could be used as a novel human-centric system to support IBD drug development including anti-TNF-α antibodies. Methods: PBMCs were perfused through the vascular (bottom) channel in untreated ‘resting’ or cytokine-‘primed’ Colon Intestine-Chips. Clinically relevant IBD drugs, including anti-TNF-α antibodies (Humira and Cimzia), as well as dexamethasone and AJM300 were administered through the vascular channel during PBMC administration. Total cell recruitment, effluent biomarker secretion (cytokines, calprotectin, C-reactive protein), and barrier function were analyzed for 72 hours. Results: α4β7 +‘gut-tropic’ PBMCs (monocytes, CD4 +, CD8 +, and NK cells) preferentially adhered and transmigrated in a cytokine priming-dependent manner. These PBMCs released clinically relevant IBD cytokines and biomarkers and induced barrier disruption, a hallmark of IBD. Anti-TNF-α antibodies and AJM300 caused reduced PBMC recruitment, inflammatory response and barrier disruption >90%. Dexamethasone had more modest effects, as expected. Conclusion: The human Colon Intestine-Chip can both model complex immune cell-driven IBD and validate effects of clinically relevant IBD drugs. This system could provide predictive validity for pre-clinical development of new IBD drugs.

Revising human-systems engineering principles for embedded AI applications.

The recent shift from predominantly hardware-based systems in complex settings to systems that heavily leverage non-deterministic artificial intelligence (AI) reasoning means that typical systems engineering processes must also adapt, especially when humans are direct or indirect users. Systems with embedded AI rely on probabilistic reasoning, which can fail in unexpected ways, and any overestimation of AI capabilities can result in systems with latent functionality gaps. This is especially true when humans oversee such systems, and such oversight has the potential to be deadly, but there is little-to-no consensus on how such system should be tested to ensure they can gracefully fail. To this end, this work outlines a roadmap for emerging research areas for complex human-centric systems with embedded AI. Fourteen new functional and tasks requirement considerations are proposed that highlight the interconnectedness between uncertainty and AI, as well as the role humans might need to play in the supervision and secure operation of such systems. In addition, 11 new and modified non-functional requirements, i.e., "ilities," are provided and two new "ilities," auditability and passive vulnerability, are also introduced. Ten problem areas with AI test, evaluation, verification and validation are noted, along with the need to determine reasonable risk estimates and acceptable thresholds for system performance. Lastly, multidisciplinary teams are needed for the design of effective and safe systems with embedded AI, and a new AI maintenance workforce should be developed for quality assurance of both underlying data and models.

Cross-task cognitive workload recognition using a dynamic residual network with attention mechanism based on neurophysiological signals

Background and ObjectiveEvaluation of human cognitive workload (CW) helps improve the user experience of human-centered systems. To provide a continuous estimation of the CW, we built a CW recognizer that maps human electroencephalograms (EEGs) to discrete CW levels with deep learning tools. However, the EEG distribution varies when humans perform different cognitive tasks. There is thus a question on the capacity for generalizing the CW recognizer across tasks. In this study, we examined the CW's performance when it was trained and tested on two EEG databases corresponding to different human-machine tasks. MethodsA novel deep neural network-based EEG recognizer, dynamic residual network with attention mechanism (DRNA-Net), is proposed in the present study. By taking advantage of recurrent networks, the DRNA-Net further incorporates a self-attention mechanism in discovering robust EEG patterns across different cognitive tasks. ResultsWe designed an experiment that applied a multidimensional N-back task to induce the CW that consists of visual and auditory memory tasks. We validated the cross-task generalization capability of the DRNA-Net based on the EEG features extracted from the N-back task and a public database. The results show that the DRNA-Net achieves classification accuracy and Macro-F1 values are 0.6055 and 0.6067, respectively. ConclusionsThe performance of the DRNA-Net indicates that it has a certain ability of cross-task cognitive workload classification, which outperforms several shallow learners and deep convolutional neural networks under various conditions of the feature subsets.

Can Action Research Methods Help Address the Digital Social sustainability Gap?: An Evaluation and Refinement of the ENRICHER Methodology using PAR

The digital social sustainability gap narrative (O'Neill, and Stapleton 2022) endeavours to address the digital social sustainability gap by using digital technology for social benefit i.e. opening up dark archives in the digital cultural heritage area. It raises issues of the interoperability between institutions for knowledge sharing, thereby breaking the disciplinary silos and also breaking the data silos within institutions. It argues for multidisciplinary collaborations, the valorisation of tacit knowledge of co-researchers so that technology does not replace the work of the human but forms a beneficial human machine symbiosis. Further it provides an insight into the ethos-centric perspective of the ENRICHER method developed by the INSYTE-Cooley Research Lab (I-CRL). This study uses an experimental technique within the Participation Action Research (PAR) methodology to valorise human tacit knowledge and intellectual capacity so that they are placed at the heart of the development process. Action research with a combination of the Human Centered Systems (HCS) approach to systems development are combined so that a multidisciplinary group with diverse world views can collaborate to create a new human centered framework for the digitisation of cultural heritage.

Artificial Intelligence and the World Wide Web: Brain and friend?

This paper looks at artificial intelligence (AI) and society and posits the idea of AI on the World Wide Web as a brain comparing it to the human brain. It frames the WWW as ‘friend’ to all and follows this disturbing train of thought. It speaks to tacit knowledge and tools and compares the work, skill knowledge of the librarians/curators to that of the artisan crafts person. It positions the work of the INSYTE-Cooley Research lab at the heart of this situation.Furthermore, it speaks of an ‘altered reality’ where a dangerous disconnection is occurring, where people are becoming observers of reality because of the abstraction that the screen provides. This spectator view is desensitizing people to what is happening in front of them and will be further fueled by the creation of the ‘metaverse’ in the future.It speaks of the danger of AI going from judgement to calculation without employing human reason and of the danger of humans becoming a passive audience. In this techno centric world it speaks of the amplified importance of tacit knowledge and the development of Human Centered Systems (HCS). It echoes Michael Cooleys thoughts on technology and the place of humanity within a techno-centric world. It speaks of the ethical and moral obligations to society and the danger of disregarding them.

Spatial Decision Support Systems with Automated Machine Learning: A Review

Many spatial decision support systems suffer from user adoption issues in practice due to lack of trust, technical expertise, and resources. Automated machine learning has recently allowed non-experts to explore and apply machine-learning models in the industry without requiring abundant expert knowledge and resources. This paper reviews recent literature from 136 papers, and proposes a general framework for integrating spatial decision support systems with automated machine learning as an opportunity to lower major user adoption barriers. Challenges of data quality, model interpretability, and practical usefulness are discussed as general considerations for system implementation. Research opportunities related to spatially explicit models in AutoML, and resource-aware, collaborative/connected, and human-centered systems are also discussed to address these challenges. This paper argues that integrating automated machine learning into spatial decision support systems can not only potentially encourage user adoption, but also mutually benefit research in both fields—bridging human-related and technical advancements for fostering future developments in spatial decision support systems and automated machine learning.

Development and evaluation of M + 1-way classification mechanism realized through identifying foreign patterns

In this study, we are concerned with a new design methodology of M + 1-way classification mechanism. The intent is to reduce the cost of error prediction caused by insufficient evidence. The study is motivated by the notion of three-way decisions, which has been successfully used in various application areas to build human-centric systems. In contrast to traditional multiple classifications, one additional class is added into the proposed architecture to represent the reject decision made on foreign patterns, which exhibit significant differences compared to the patterns used for constructing the classification models. A collection of information granules is constructed on the basis of available experimental evidence to form a compact and interpretable representation of the feature space occupied by the native patterns. The patterns located outside the regions occupied by these information granules are identified and filtered out prior to classification while only the native patterns are subject to classification. The proposed methodology leads to a human-centric and human-interactive construct in which the rejected patterns need further processing. Different distance functions are utilized in the construction of information granules. The performance of the proposed architecture is evaluated involving one synthetic dataset and a collection of publicly available datasets.

Machine learning techniques for emotion detection and sentiment analysis: current state, challenges, and future directions

ABSTRACT Emotion detection and Sentiment analysis techniques are used to understand polarity or emotions expressed by people in many cases, especially during interactive systems use. Recognizing users’ emotions is an important topic for human–computer interaction. Computers that recognize emotions would provide more natural interactions. Also, emotion detection helps design human-centred systems that provide adaptable behaviour change interventions based on users’ emotions. The growing capability of machine learning to analyze big data and extract emotions therein has led to a surge in research in this domain. With this increased attention, it becomes essential to investigate this research area and provide a comprehensive review of the current state. In this paper, we conduct a systematic review of 123 papers on machine learning-based emotion detection to investigate research trends along many themes, including machine learning approaches, application domain, data, evaluation, and outcome. The results demonstrate: 1) increasing interest in this domain, 2) supervised machine learning (namely, SVM and Naïve Bayes) are the most popular algorithms, 3) Text datasets in the English language are the most common data source, and 4) most research use Accuracy to evaluate performance. Based on the findings, we suggest future directions and recommendations for developing human-centred systems.

Human-Centered Design of a Collaborative Robotic System for the Shoe-Polishing Process

Demand for automated processes in the manufacturing industry is now shifting toward flexible, human-centered systems that combine productivity and high product quality, thus combining the advantages of automated and robotic systems with the high-value-added skills of operators and craftsmen. This trend is even more crucial for small and medium-sized enterprises operating in the “Made in Italy” fashion industry. The paper presents the study, simulation, and preliminary testing of a collaborative robotic system for shoe polishing that can reduce manual labor by limiting it to the finishing stage of the process, where the aesthetic result is fully achieved, with a benefit also in terms of ergonomics for the operator. The influence of process parameters and design solutions are discussed by presenting preliminary test results and providing hints for future developments.

Mist and Edge Computing Cyber-Physical Human-Centered Systems for Industry 5.0: A Cost-Effective IoT Thermal Imaging Safety System

While many companies worldwide are still striving to adjust to Industry 4.0 principles, the transition to Industry 5.0 is already underway. Under such a paradigm, Cyber-Physical Human-centered Systems (CPHSs) have emerged to leverage operator capabilities in order to meet the goals of complex manufacturing systems towards human-centricity, resilience and sustainability. This article first describes the essential concepts for the development of Industry 5.0 CPHSs and then analyzes the latest CPHSs, identifying their main design requirements and key implementation components. Moreover, the major challenges for the development of such CPHSs are outlined. Next, to illustrate the previously described concepts, a real-world Industry 5.0 CPHS is presented. Such a CPHS enables increased operator safety and operation tracking in manufacturing processes that rely on collaborative robots and heavy machinery. Specifically, the proposed use case consists of a workshop where a smarter use of resources is required, and human proximity detection determines when machinery should be working or not in order to avoid incidents or accidents involving such machinery. The proposed CPHS makes use of a hybrid edge computing architecture with smart mist computing nodes that processes thermal images and reacts to prevent industrial safety issues. The performed experiments show that, in the selected real-world scenario, the developed CPHS algorithms are able to detect human presence with low-power devices (with a Raspberry Pi 3B) in a fast and accurate way (in less than 10 ms with a 97.04% accuracy), thus being an effective solution (e.g., a good trade-off between cost, accuracy, resilience and computational efficiency) that can be integrated into many Industry 5.0 applications. Finally, this article provides specific guidelines that will help future developers and managers to overcome the challenges that will arise when deploying the next generation of CPHSs for smart and sustainable manufacturing.

Dismantling traditional approaches: community-centered design in local government

Can community-centered design practice create a space to channel creativity into building community, dismantle power structures, and facilitate conversations to create equitable opportunities? This paper investigates how methodologies and tools like community-centered design, qualitative interrogations, and emotional intelligence can give practitioners the tools to reimagine constituents’ relationships with their municipalities. Using community-centered design practice and principles, the author imagines how practitioners can break down privileged perspectives and invite marginalized communities into policy-centered decision-making. While design practice can be an exclusive bubble, just like policy, the intersection of the two has led many cities worldwide to embrace human-centered design. And although Human-centered design can challenge sterile processes, it is often unable to tackle the complexities of power hoarding, marginalization, and other challenges faced by local governments. As a result, it limits design practitioners from approaching obstinate problems and centers power on practitioners’ positionality and decision-making, instead of the communities and individuals impacted by the systemic inadequacies. This paper questions the same by investigating the role of design practitioners in the public sector and community-centered design. Policymaking cannot be innovative or thoughtful without design. Design interrogation in government should embrace vulnerability, transparency, and intentionality. This paper highlights how community-centered designers have the ability and sensitivity to challenge complacent institutions and their lack of human-centered systems. Using case studies from three U.S. cities (Philadelphia, New York, and Baltimore), this paper explores how design gives us mechanisms that can activate a government by the people, of the people, and for the people.

'Tidy' and 'messy' management alters natural enemy communities and pest control in urban agroecosystems.

Agroecosystem management influences ecological interactions that underpin ecosystem services. In human-centered systems, people’s values and preferences influence management decisions. For example, aesthetic preferences for ‘tidy’ agroecosystems may remove vegetation complexity with potential negative impacts on beneficial associated biodiversity and ecosystem function. This may produce trade-offs in aesthetic- versus production-based management for ecosystem service provision. Yet, it is unclear how such preferences influence the ecology of small-scale urban agroecosystems, where aesthetic preferences for ‘tidiness’ are prominent among some gardener demographics. We used urban community gardens as a model system to experimentally test how aesthetic preferences for a ‘tidy garden’ versus a ‘messy garden’ influence insect pests, natural enemies, and pest control services. We manipulated gardens by mimicking a popular ‘tidy’ management practice–woodchip mulching–on the one hand, and simulating ‘messy’ gardens by adding ‘weedy’ plants to pathways on the other hand. Then, we measured for differences in natural enemy biodiversity (abundance, richness, community composition), and sentinel pest removal as a result of the tidy/messy manipulation. In addition, we measured vegetation and ground cover features of the garden system as measures of practices already in place. The tidy/messy manipulation did not significantly alter natural enemy or herbivore abundance within garden plots. The manipulation did, however, produce different compositions of natural enemy communities before and after the manipulation. Furthermore, the manipulation did affect short term gains and losses in predation services: the messy manipulation immediately lowered aphid pest removal compared to the tidy manipulation, while mulch already present in the system lowered Lepidoptera egg removal. Aesthetic preferences for ‘tidy’ green spaces often dominate urban landscapes. Yet, in urban food production systems, such aesthetic values and management preferences may create a fundamental tension in the provision of ecosystem services that support sustainable urban agriculture. Though human preferences may be hard to change, we suggest that gardeners allow some ‘messiness’ in their garden plots as a “lazy gardener” approach may promote particular natural enemy assemblages and may have no downsides to natural predation services.

The Industry 5.0 framework: viability-based integration of the resilience, sustainability, and human-centricity perspectives

Industry 5.0 is a combination of organisational principles and technologies to design and manage operations and supply chains as resilient, sustainable, and human-centric systems. While the general notion of Industry 5.0 has been elaborated, its implications for future operations and supply chains remain underexplored. This paper contributes to the conceptualisation of Industry 5.0 from the perspective of viability. We contextualise a framework of Industry 5.0 through the lens of the viable supply chain model, the reconfigurable supply chain, and human-centric ecosystems. Our study uncovers the major dimensions that characterise Industry 5.0 as a technological-organisational framework. First, the major technological principles of Industry 5.0 are collaboration, coordination, communication, automation, data analytics processing, and identification. Second, Industry 5.0 covers four areas: organisation, management, technology, and performance assessment. Third, Industry 5.0 spans three levels: society level, network level, and plant level. Last but not least, Industry 5.0 frames a new triple bottom line: resilient value creation, human well-being, and sustainable society. We provide a definition of Industry 5.0 and discuss its implications by elaborating on the understanding of value in Industry 5.0, which spans the dimensions of profit, people, and society. We also discuss open research areas.

A human-centred workstation in industry 4.0 for balancing the industrial productivity and human well-being

Cyber-physical productions systems (CPPS) play a fundamental role in the fourth industrial revolution along with human centred design. The consideration of these two factors leads to the concept of human centred cyber-physical production systems (H-CPPSs), which are defined as systems that support humans, machines, and software to integrate virtual and physical worlds. H-CPPS are not intended to substitute for human operators but rather to support and augment their capabilities and ensure their well-being. Limited information currently exists about workstation design from an ergonomic perspective and a proper method for including a workstation in a H-CPPS. This paper proposes a methodology that allows identification of industrial requirements and ergonomic considerations for establishing guidelines to integrate Industry 4.0 principles in the manufacturing shopfloor of large and small-medium enterprises by designing a workstation framework that balances operator well-being and manufacturing productivity. First, this approach evaluates a set of general production tasks from the manufacturing industry, assesses the ergonomic risks during execution and identifies the technological enablers to balance human productivity and well-being. Second, this approach provides a set of guidelines for deploying a generic human centred workstation with ergonomic considerations. Finally, this paper describes a case study in which a human-centred workstation was constructed as a proof of concept of the proposed methodology. Experimental tests were applied to find significant statistical improvements between controlled and experimental scenario. The experimental results determined from the methodological constructed workstation with human-centred considerations contributes to reduce the ergonomic risk on industrial operators without affecting its productivity.

Parallel cognition: hybrid intelligence for human-machine interaction and management

As an interdisciplinary research approach, traditional cognitive science adopts mainly the experiment, induction, modeling, and validation paradigm. Such models are sometimes not applicable in cyber-physical-social-systems (CPSSs), where the large number of human users involves severe heterogeneity and dynamics. To reduce the decision-making conflicts between people and machines in human-centered systems, we propose a new research paradigm called parallel cognition that uses the system of intelligent techniques to investigate cognitive activities and functionals in three stages: descriptive cognition based on artificial cognitive systems (ACSs), predictive cognition with computational deliberation experiments, and prescriptive cognition via parallel behavioral prescription. To make iteration of these stages constantly on-line, a hybrid learning method based on both a psychological model and user behavioral data is further proposed to adaptively learn an individual’s cognitive knowledge. Preliminary experiments on two representative scenarios, urban travel behavioral prescription and cognitive visual reasoning, indicate that our parallel cognition learning is effective and feasible for human behavioral prescription, and can thus facilitate human-machine cooperation in both complex engineering and social systems.

Infodemic Management Using Digital Information and Knowledge Cocreation to Address COVID-19 Vaccine Hesitancy: Case Study From Ghana.

BackgroundInfodemic management is an integral part of pandemic management. Ghana Health Services (GHS) together with the UNICEF (United Nations International Children's Emergency Fund) Country Office have developed a systematic process that effectively identifies, analyzes, and responds to COVID-19 and vaccine-related misinformation in Ghana.ObjectiveThis paper describes an infodemic management system workflow based on digital data collection, qualitative methodology, and human-centered systems to support the COVID-19 vaccine rollout in Ghana with examples of system implementation.MethodsThe infodemic management system was developed by the Health Promotion Division of the GHS and the UNICEF Country Office. It uses Talkwalker, a social listening software platform, to collect misinformation on the web. The methodology relies on qualitative data analysis and interpretation as well as knowledge cocreation to verify the findings.ResultsA multi-sectoral National Misinformation Task Force was established to implement and oversee the misinformation management system. Two members of the task force were responsible for carrying out the analysis. They used Talkwalker to find posts that include the keywords related to COVID-19 vaccine–related discussions. They then assessed the significance of the posts on the basis of the engagement rate and potential reach of the posts, negative sentiments, and contextual factors. The process continues by identifying misinformation within the posts, rating the risk of identified misinformation posts, and developing proposed responses to address them. The results of the analysis are shared weekly with the Misinformation Task Force for their review and verification to ensure that the risk assessment and responses are feasible, practical, and acceptable in the context of Ghana.ConclusionsThe paper describes an infodemic management system workflow in Ghana based on qualitative data synthesis that can be used to manage real-time infodemic responses.

Systems safety in nonoperating room anesthesia locations.

Nonoperating room anesthesia (NORA) care is an area of rapid growth over the last decade. However, literature describing safety systems in NORA is limited. This review evaluates historical safety models described by Donabedian and Reason, assesses the NORA environment and safety concerns that may contribute to adverse events, and provides potential solutions via a human-centered systems safety design. Systems Engineering Initiative for Patient Safety (SEIPS) 3.0 provides a framework for quality and patient safety improvement. Although the previous SEIPS 2.0 model has been used to evaluate NORA environments with focus on the case volume, high productivity pressure, and significant physical constraints common to NORA sites, literature describing SEIPS 3.0 in relation to NORA care is sparse. Given the rate of malpractice claims for death in NORA settings, solutions that address the multifactorial nature of adverse events are needed. The SEIPS 3.0 model may be applied to NORA care. Changes should focus on staffing ratios, staff/patient education, checklist utilization, burnout prevention, scheduling efficiency, anesthesia workstation standardization, communication improvements, room layout, medication and supply availability and storage, and the global managerial approach. Team members must demonstrate flexibility and a willingness to adapt to successfully implement change.