Human-machine Collaboration Research Articles

Is Artificial Intelligence Better than Manpower? The Effects of Different Types of Online Customer Services on Customer Purchase Intentions

Artificial intelligence has been widely applied to e-commerce and the online business service field. However, few studies have focused on studying the differences in the effects of types of customer service on customer purchase intentions. Based on service encounter theory and superposition theory, we designed two shopping experiments to capture customers’ thoughts and feelings, in order to explore the differences in the effects of three different types of online customer service (AI customer service, manual customer service, and human–machine collaboration customer service) on customer purchase intention, and analyses the superposition effect of human–machine collaboration customer service. The results show that the consumer’s perceived service quality positively influences the customer’s purchase intention, and plays a mediating role in the effect of different types of online customer service on customer purchase intention; the product type plays a moderating role in the relationship between online customer service and customer purchase intention, and human–machine collaboration customer service has a superposition effect. This study helped to deepen the understanding of AI developers and e-commerce platforms regarding the application of AI in online business service, and provides reference suggestions for the formulation of more perfect business service strategies.

Security and safety assurance of collaborative manufacturing in industry 4.0

ABSTRACT Industry 4.0 provides an ideal platform to support a direct interaction of humans and machines inadapting changes and uncertainties in system operations. However, a physical human-machineinteraction must assure security and safety. The safety requirements of collaborativemanufacturing are explored and the techniques to assure safety in differentcollaboration modes are investigated to identify the challenges of safetyassurance of human–machine collaborations in shared workspaces. Inaddition, system-level safety requirements of collaborative manufacturing arediscussed to reveal the importance of sustaining similar safety levels for allsystem components and tools in developing an integrated collaborative system.

A Bioinformatics-Assisted Review on Iron Metabolism and Immune System to Identify Potential Biomarkers of Exercise Stress-Induced Immunosuppression.

The immune function is closely related to iron (Fe) homeostasis and allostasis. The aim of this bioinformatics-assisted review was twofold; (i) to update the current knowledge of Fe metabolism and its relationship to the immune system, and (ii) to perform a prediction analysis of regulatory network hubs that might serve as potential biomarkers during stress-induced immunosuppression. Several literature and bioinformatics databases/repositories were utilized to review Fe metabolism and complement the molecular description of prioritized proteins. The Search Tool for the Retrieval of Interacting Genes (STRING) was used to build a protein-protein interactions network for subsequent network topology analysis. Importantly, Fe is a sensitive double-edged sword where two extremes of its nutritional status may have harmful effects on innate and adaptive immunity. We identified clearly connected important hubs that belong to two clusters: (i) presentation of peptide antigens to the immune system with the involvement of redox reactions of Fe, heme, and Fe trafficking/transport; and (ii) ubiquitination, endocytosis, and degradation processes of proteins related to Fe metabolism in immune cells (e.g., macrophages). The identified potential biomarkers were in agreement with the current experimental evidence, are included in several immunological/biomarkers databases, and/or are emerging genetic markers for different stressful conditions. Although further validation is warranted, this hybrid method (human-machine collaboration) to extract meaningful biological applications using available data in literature and bioinformatics tools should be highlighted.

In Situ labeling and monitoring technology based on projector-camera synchronization for human–machine collaboration

In Situ labeling and monitoring technology based on projector-camera synchronization for human–machine collaboration

EEG-based work experience prediction using hazard recognition

Extraction of individual characteristics promotes intuitive human-machine collaboration (HMC) for hazard recognition. Despite the essential role of work experience in hazard recognition, HMC techniques require ways for efficient individual characteristic identification with physiological signals. We proposed a measure that extracts implicit electroencephalography (EEG) signals to predict workers' experience as a proxy for hazard recognition ability. First, we hypothesized that work experience is potentially related to EEG signals. Second, an experiment was conducted to collect brain activity signals during hazard recognition from construction workers. Third, the brain activity signals (event-related potentials) were extracted to train a sparse regression model for experience prediction with the nested leave-one-out cross-validation approach. EEG-based prediction results were significantly correlated with years of work experience (r = 0.6455), and the model achieved good external validity and out-of-sample reliability. The proposed model could serve as a viable basis to identify individual characteristics during HMC.

Human–machine collaboration based sound event detection

Human–machine collaboration based sound event detection

Fast-Decoding Algorithm for Electrode Processes at Electrified Interfaces by Mean-Field Kinetic Model and Bayesian Data Assimilation: An Active-Data-Mining Approach for the Efficient Search and Discovery of Electrocatalysts.

The microscopic origins of the activity and selectivity of electrocatalysts has been a long-lasting enigma since the 19th century. By applying an active-data-mining approach, employing a mean-field kinetic model and a statistical approach of Bayesian data assimilation, we demonstrate here a fast decoding to extract key properties in the kinetics of complicated electrode processes from current-potential profiles in experimental and literary data. As the proof-of-concept, kinetic parameters on the four-electron oxygen reduction reaction in the 0.1 M HClO4 solution (ORR: O2 + 4e- + 4H+ → 2H2O) of various platinum-based single-crystal electrocatalysts are extracted from our own experiments and third-party literature to investigate the microscopic electrode processes. Furthermore, data assimilation of the mean-field ORR model and experimental data is performed based on Bayesian inference for the inductive estimation of kinetic parameters, which sheds light on the dynamic behavior of kinetic parameters with respect to overpotential. This work shows that a fast-decoding algorithm based on a mean-field kinetic model and Bayesian data assimilation is a promising data-driven approach to extract key microscopic features of complicated electrode processes and therefore will be an important method toward building up advanced human-machine collaborations for the efficient search and discovery of high-performance electrochemical materials.

From Disrupted Classrooms to Human-Machine Collaboration? The Pocket Calculator, Google Translate, and the Future of Language Education

This article argues that consumer-oriented machine translation software applications are disrupting foreign language education. In order to mitigate this impact, the article provides guidance on how to transform teachers’ perceptions of online translators. This process is a critical precondition for the gradual and thoughtful implementation of online translators in the foreign language classroom. The first part of the articles will define the concept of disruption and use the pocket calculator as an historical example to illustrate challenges and solutions for an educational setting that was fundamentally impacted by a new technology. The second part will turn to the present and focus on the impact of online translators not only on ways humans communicate across languages in authentic real-world settings, but also on the foreign language classroom. In the third part, we will argue that a careful recalibration of educational objectives that will have to include the students’ ability to engage effectively in tasks that rely on human-machine collaboration will provide an opportunity to integrate online translators and related technologies into foreign language curricula. To this end, we propose that future generations of language learners need to develop specific competencies that will qualify them to effectively collaborate with online translators and related technologies. The conclusion will outline future leadership priorities for professional organizations and teacher training programs while acknowledging the limitations associated with the integration of the machine translation technologies into language learning environments.

A review of some techniques for inclusion of domain-knowledge into deep neural networks

We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines the inclusion of domain-knowledge by means of changes to: the input, the loss-function, and the architecture of deep networks. The categorisation is for ease of exposition: in practice we expect a combination of such changes will be employed. In each category, we describe techniques that have been shown to yield significant changes in the performance of deep neural networks.

Can industry 5.0 revolutionize the wave of resilience and social value creation? A multi-criteria framework to analyze enablers

The ever-changing times demand a resilient industry that quickly adapts to the oncoming wave of new technology; however, a strong social environment that comprises organic social values is needed for a thriving human society. Industry 4.0 has become the standard for applications in recent years, as its technologies are rapidly being implemented and positively impacting every sector. However, these developments are still unable to achieve the desired outcomes and have neglected the environment by prioritizing machines over humans. Therefore, the Industry 5.0 (I5.0) revolution is a call to bring forth the ideas of sustainability into practice, integrate human values with technology, and is considered a step forward for achieving sustainable development goals. Hence, the present study proposes a framework for analyzing I5.0 enablers for achieving sustainability by integrating human values with technology. To achieve the objectives, this study was conducted in three different phases: 1) through extensive review, the list of criteria and enablers was identified; 2) Pythagorean fuzzy Delphi was used to validate the enablers against criteria; 3) a hybrid approach of Pythagorean fuzzy analytical hierarchy process-combined compromise solution was employed to calculate the weights of selected criteria and determine the ranks of enablers. A sensitivity analysis was then performed to check the robustness of this framework. The findings show that the criterion of personal customization obtained the highest weight followed by human-machine collaboration, which will create a smart cognitive environment for humans. Human intelligence is used in more important places, which will help society focus on developing social values. The authors also put forward seven propositions about adopting I5.0 enablers for best results, taking examples from existing case studies and helping industrialists adopt I5.0 methods.

Effectiveness Analysis on Human-Machine Information Interaction of Intelligent Highway

Different human-machine collaboration modes and driving simulation tests with the orthogonal method considered are designed for a series of typical intelligent highway landscapes. The feedback of drivers under different interaction modes is evaluated through NASA-LTX questionnaire, driving simulator, eye tracker, and electroencephalograph (EEG). This optimal interaction mode (including voice form, broadcasting timing, and frequency) of each driving assistance scene in CVI (Cooperative Vehicle Infrastructure) environment under the conditions of high and low traffic is determined from subjective and objective perspectives. In accordance with feedback of these subjects on each set scene, the voice information structure of each assistance mode plays the most important role on drivers followed by the broadcasting timing and frequency. These broadcasts which provide good effects include scenarios such as various assistance scenes at curves and an early warning timing at a long-distance trip as well as a high early warning frequency; in addition, as for an exit-tip assistance scenario, a voice mode assistance is preferred; and for various speed assistance scenes, the beep mode is better. Furthermore, it is found that, at a higher traffic level but a short-distance trip, an early warning timing is favored generally for various scenes while under a low traffic level, a long-distance early warning timing is better.

Command-filter-adaptive-based lateral motion control for autonomous vehicle

Human–machine collaborative (HMC) torque control allows the drivers to participate in driving and cooperate to complete driving tasks. However, the driver’s torque input and unknown disturbances encountered by the vehicle will adversely affect the control of autonomous vehicles. The problems of “explosion of complexity” appear when the adaptive backstepping method is used to design the steering control strategy. To solve the above problems, a steering control strategy based on command filter adaptive torque control is proposed. Firstly, in order to describe the dynamic response of the vehicle and the maneuvering behavior of the driver, a human–vehicle–road model with steering torque as input is established. Then, command filtering adaptive control (CFAC) is used to design the steering control strategy of HMC, and Lyapunov theory is used to analyze the stability of the control system. To reduce the uncertainty range of the system and guarantee stability under disturbances, the unknown steering load boundary and driver’s torque input are estimated. Finally, simulation and hardware-in-the-loop experiments verify the effectiveness of the proposed steering control strategy based on torque control. The experimental results show that the path tracking error converges to zero rapidly even when the HMC driving encounters disturbances.

Flexibilization 4.0 for production manufacturing optimization

The continuous variations of requirements and the versatility of customers have a real impact on the company performance. Digital transformation corresponds to one lever for making the company more competitive. New technologies and tools are required as recommended in Industry 4.0 concepts for making this transformation a success. This paper focuses on production manufacturing problems such as human-machine collaboration, to achieve a high level of performance while maintaining a wide range of operational complexity, guaranteeing the flexibility of the workstations and thus the company’s ability to respond to varied demands. A sustainable digital transformation methodology has been elaborated for solving problems related to human-robot collaboration during the production process, to reduce lead time and decreasing series changing time. After a literature review on artificial intelligence (AI), collaborative robotics and production performance optimization methods, this article describes the developed sustainable digital transformation methodology and focuses on operational problems that could be solved in this frame. Then, the results obtained on an electronic card Industry 4.0 demonstration platform will be presented.

Ethically Responsible Machine Learning in Fintech

Rapid technological developments in the last decade have contributed to using machine learning (ML) in various economic sectors. Financial institutions have embraced technology and have applied ML algorithms in trading, portfolio management, and investment advising. Large-scale automation capabilities and cost savings make the ML algorithms attractive for personal and corporate finance applications. Using ML applications in finance raises ethical issues that need to be carefully examined. We engage a group of experts in finance and ethics to evaluate the relationship between ethical principles of finance and ML. The paper compares the experts’ findings with the results obtained using natural language processing (NLP) transformer models, given their ability to capture the semantic text similarity. The results reveal that the finance principles of integrity and fairness have the most significant relationships with ML ethics. The study includes a use case with SHapley Additive exPlanations (SHAP) and Microsoft Responsible AI Widgets explainability tools for error analysis and visualization of ML models. It analyzes credit card approval data and demonstrate that the explainability tools can address ethical issues in fintech, and improve transparency, thereby increasing the overall trustworthiness of ML models. The results show that both humans and machines could err in approving credit card requests despite using their best judgment based on the available information. Hence, human-machine collaboration could contribute to improved decision-making in finance. We propose a conceptual framework for addressing ethical challenges in fintech such as bias, discrimination, differential pricing, conflict of interest, and data protection.

Towards the assessment of performance-based interactions in collaborative CPPS

Cyber-Physical Production Systems (CPPS) are promised to be the systems that will drive the technical transformation in manufacturing. However, the role of human operators is still decisive due to the intrinsic human flexibility to analyze, learn and face unpredicted circumstances, forcing to an approach based on fully collaborative environments between humans and machines. Nevertheless, a validated and repeatable method to evaluate and contrast these interactions and the general performance metrics of the system is still missing. This paper introduces a new holistic method and model to set indices and metrics to assess the performance-based interactions while considering the collaborative nature of the actions under different dimensions: i) user experience aspects, ii) machine specific indicators, iii) human-machine collaboration, and iv) production indicators. Finally, a collaborative industrial case is exposed to exemplify the use of the proposed method.

Sustainable Work Environment and Human-Machine Collaboration: Employee Satisfaction and Diversity

Sustainable Work Environment and Human-Machine Collaboration: Employee Satisfaction and Diversity

Mobile collaborative welding system for complex welding seams

The growing variety of products brings various workpieces, which have complex welding seams that cannot be welded by current welding robots fixed in the welding stations or carried by the gantry. Therefore, this paper proposes a mobile collaborative welding system composed of an AGV (Automated Guided Vehicle) and a 6-DOF (Six-Degree-of-Freedom) collaborative robot. Considering the complex welding seams, a mobile collaborative welding method is proposed. The collaborative welding method includes three steps, i.e., welding seam acquisition, welding seam classification and segmentation, and welding task allocation. The authors present a new approach to acquire the spatial position characteristics of welding seams based on the human-machine collaboration. According to the spatial position characteristics of the welding seams, the welding type identification and classification segmentation can be obtained. Finally, the welding tasks of the robot and AGV can be allocated.

Modeling the Soft Bellows of the Bionic Soft Arm

Conventional robots are strong, fast and rigid. Although these properties make them useful for industrial applications, for human machine collaborations they pose a threat. An alternative is provided by soft robots. However, model-based control algorithms for soft robots are not yet at the same level as for conventional robots. Their performance is often limited by their soft materials, which are difficult to model. The goal of this paper is to extend and increase the quality of the existing model for the bionic soft arm while ensuring real-time feasibility. In particular, the focus is on the soft bellows of the manipulator that actuates the robot. In this work, the three-dimensional geometrical problem of the inflating bellows is reduced to a two-dimensional problem that can be efficiently solved in real-time. The solution approximates the nonlinear behavior of the hyperelastic material and is part of a regressor, which then models the driving torque. In comparison to the existing model, the new developed model is able to describe hysteresis effects caused by the material. This increases the overall accuracy of the model. The results are backed up by experimental data.

Digital Twin-driven Smart Human-machine Collaboration: Theory, Enabling Technologies and Applications

Digital Twin-driven Smart Human-machine Collaboration: Theory, Enabling Technologies and Applications

Lotse: A Practical Framework for Guidance in Visual Analytics.

Co-adaptive guidance aims to enable efficient human-machine collaboration in visual analytics, as proposed by multiple theoretical frameworks. This paper bridges the gap between such conceptual frameworks and practical implementation by introducing an accessible model of guidance and an accompanying guidance library, mapping theory into practice. We contribute a model of system-provided guidance based on design templates and derived strategies. We instantiate the model in a library called Lotse that allows specifying guidance strategies in definition files and generates running code from them. Lotse is the first guidance library using such an approach. It supports the creation of reusable guidance strategies to retrofit existing applications with guidance and fosters the creation of general guidance strategy patterns. We demonstrate its effectiveness through first-use case studies with VA researchers of varying guidance design expertise and find that they are able to effectively and quickly implement guidance with Lotse. Further, we analyze our framework's cognitive dimensions to evaluate its expressiveness and outline a summary of open research questions for aligning guidance practice with its intricate theory.