[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
From Human–Machine Interaction to Human–Machine Cooperation: Status and Progress
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

From Human–Machine Interaction to Human–Machine Cooperation: Status and Progress

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 10 June 2025 | Viewed by 7647

Special Issue Editors

Dr. Tomislav Stipančić

E-Mail Website
Guest Editor
Associate Professor, Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia
Interests: human-machine interaction, cognitive informatics, smart robotics, virtual agents, IoT, artificial intelligence
Prof. Dr. Duska Rosenberg

E-Mail Website
Guest Editor
iCOM Research, University of London, London WC1E 7HU, UK
Interests: artificial intelligence; computing in social science; arts and humanities; human-computer interaction; discourse analysis; cognitive science

Special Issue Information

Dear Colleagues,

Human–machine interaction is all about how people and automated systems interact and communicate with each other within virtual, augmented, or real environments. With the advance of AI and cyber–physical systems, the research fulcrum has gradually moved from interaction towards cooperation.

We are pleased to announce a Special Issue on challenging and innovative topics in the field of human–machine interaction and cooperation, including those related to theoretical aspects, methodology, and practice.

Developing systems such as collaborative, social, or industrial robots and computers; bioinspired systems; and digital systems and devices for the Internet of Things (IoT), Metaverse, and blockchain technology is highly interdisciplinary and often involves innovations and breakthroughs in many diverse technical areas, including but not limited to human behaviour modelling, task and motion planning, learning, activity recognition and intention prediction, novel interaction devices, user interface concepts and technologies, multimodal interaction and cooperation, evaluation methods and tools, emotions in HMI, environments and tools, etc.

Topics of interest include (but are not limited to):

  • H2M and M2M interaction and cooperation theory and applications;
  • Cyber–physical systems;
  • Social and biomedical signal processing;
  • Learning by example;
  • Multimodal perception;
  • Human behavior modeling;
  • Activity and intention recognition;
  • Intelligent manufacturing;
  • Human–machine dialogue systems;
  • Planning and decision making under uncertainty;
  • Context-aware and affective systems;
  • Safe navigation around humans;
  • Intelligent systems for training/teaching humans;
  • VR, AR, and XR collaboration environments.

Dr. Tomislav Stipančić
Prof. Dr. Duska Rosenberg
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

30 pages, 13318 KiB  
Article
Towards a System Dynamics Framework for Human–Machine Learning Decisions: A Case Study of New York Citi Bike
by Ganesh Sankaran, Marco A. Palomino, Martin Knahl and Guido Siestrup
Appl. Sci. 2024, 14(22), 10647; https://doi.org/10.3390/app142210647 - 18 Nov 2024
Cited by 1 | Viewed by 1013
Abstract
The growing number of algorithmic decision-making environments, which blend machine and bounded human rationality, strengthen the need for a holistic performance assessment of such systems. Indeed, this combination amplifies the risk of local rationality, necessitating a robust evaluation framework. We propose a novel [...] Read more.
The growing number of algorithmic decision-making environments, which blend machine and bounded human rationality, strengthen the need for a holistic performance assessment of such systems. Indeed, this combination amplifies the risk of local rationality, necessitating a robust evaluation framework. We propose a novel simulation-based model to quantify algorithmic interventions within organisational contexts, combining causal modelling and data science algorithms. To test our framework’s viability, we present a case study based on a bike-share system focusing on inventory balancing through crowdsourced user actions. Utilising New York’s Citi Bike service data, we highlight the frequent misalignment between incentives and their necessity. Our model examines the interaction dynamics between user and service provider rule-driven responses and algorithms predicting flow rates. This examination demonstrates why understanding these dynamics is essential for devising effective incentive policies. The study showcases how sophisticated machine learning models, with the ability to forecast underlying market demands unconstrained by historical supply issues, can cause imbalances that induce user behaviour, potentially spoiling plans without timely interventions. Our approach allows problems to surface during the design phase, potentially avoiding costly deployment errors in the joint performance of human and AI decision-makers. Full article
(This article belongs to the Special Issue From Human–Machine Interaction to Human–Machine Cooperation: Status and Progress)
►▼ Show Figures

Figure 1

Figure 1
<p>Double-loop learning applied to refine collaborative human–AI decision-making.</p> Full article ">Figure 2
<p>Overview of the modelling framework.</p> Full article ">Figure 3
<p>Analysis of suboptimal incentive timing at a Citi Bike station during August 2023, showcasing opportunities for improved inventory management through better-aligned incentives.</p> Full article ">Figure 4
<p>Causal Loop Diagram illustrating the feedback structures involved in bike-share inventory balancing and the hypothesised influences on system performance.</p> Full article ">Figure 5
<p>High-level overview of the bike-share inventory model, highlighting the main flows of rentals and returns and their interconnections within the system.</p> Full article ">Figure 6
<p>Data pipeline detailing the flow from raw demand and incentive data collection to the processing steps that generate critical input for forecasting models.</p> Full article ">Figure 7
<p>Causal impact analysis showing the effect of incentives on rental demand for one test day, illustrating key results.</p> Full article ">Figure 8
<p>Diagram of the stocks and flows structure, demonstrating how key system elements interact in the simulation model.</p> Full article ">Figure 9
<p>Focused view of a single station’s stocks and flows structure, illustrating how return dynamics are modelled.</p> Full article ">Figure 10
<p>Comparative analysis of availability factor curves under two levels of responsiveness.</p> Full article ">Figure 11
<p>Comparative analysis of risk perception curves under two levels of responsiveness.</p> Full article ">Figure 12
<p>Simplified representation of the partial testing model used for verifying local rationality before full-scale integration.</p> Full article ">Figure 13
<p>Bias correction analysis in the partial testing phase to enhance ML forecast accuracy and reduce systematic errors.</p> Full article ">Figure 14
<p>Generated demand variability scenarios for testing station response at “E 16 St and 5 Ave” on 24 August.</p> Full article ">Figure 15
<p>Performance results from simulation runs across 432 policy scenarios with decision parameters varied.</p> Full article ">Figure 16
<p>Analysis of key stock and flow variables influencing performance at two different risk perception delay values (orange for the yin cluster, grey for the yang cluster).</p> Full article ">Figure 17
<p>Analysis of key stock and flow variables influencing performance at two different availability perception delay values (orange for the yin cluster, grey for the yang cluster).</p> Full article ">Figure 18
<p>Impact of demand perturbation until 10 AM on station performance, with the figure illustrating results for the yin cluster.</p> Full article ">Figure A1
<p>CLD of the bike-share two-stock model.</p> Full article ">
23 pages, 2757 KiB  
Article
A Comprehensive Evaluation of Features and Simple Machine Learning Algorithms for Electroencephalographic-Based Emotion Recognition
by Mayra Álvarez-Jiménez, Tania Calle-Jimenez and Myriam Hernández-Álvarez
Appl. Sci. 2024, 14(6), 2228; https://doi.org/10.3390/app14062228 - 7 Mar 2024
Cited by 3 | Viewed by 1517
Abstract
The study of electroencephalographic (EEG) signals has gained popularity in recent years because they are unlikely to intentionally fake brain activity. However, the reliability of the results is still subject to various noise sources and potential inaccuracies inherent to the acquisition process. Analyzing [...] Read more.
The study of electroencephalographic (EEG) signals has gained popularity in recent years because they are unlikely to intentionally fake brain activity. However, the reliability of the results is still subject to various noise sources and potential inaccuracies inherent to the acquisition process. Analyzing these signals involves three main processes: feature extraction, feature selection, and classification. The present study extensively evaluates feature sets across domains and their impact on emotion recognition. Feature selection improves results across the different domains. Additionally, hybrid models combining features from various domains offer a superior performance when applying the public DEAP dataset for emotion classification using EEG signals. Time, frequency, time–frequency, and spatial domain attributes and their combinations were analyzed. The effectiveness of the input vectors for the classifiers was validated using SVM, KNN, and ANN, which are simple classification algorithms selected for their widespread use and better performance in the state of the art. The use of simple machine learning algorithms makes the findings particularly valuable for real-time emotion recognition applications where the computational resources and processing time are often limited. After the analysis stage, feature vector combinations were proposed to identify emotions in four quadrants of the valence–arousal representation space using the DEAP dataset. This research achieved a classification accuracy of 96% using hybrid features in the four domains and the ANN classifier. A lower computational cost was obtained in the frequency domain. Full article
(This article belongs to the Special Issue From Human–Machine Interaction to Human–Machine Cooperation: Status and Progress)
►▼ Show Figures

Figure 1

Figure 1
<p>Steps in the proposed emotion recognition process.</p> Full article ">Figure 2
<p>Bidimensional model representation.</p> Full article ">Figure 3
<p>Criteria for categorizing emotional quadrants. High arousal–high valence (HAHV), high arousal–low valence (HALV), low arousal–low valence (LALV), and low arousal–high valence (LAHV).</p> Full article ">Figure 4
<p>Feature extraction methods in the time domain. Energy (Eng), root mean square (RMS), line length (LinLen), average power (Avg), Shannon entropy (ShEn), approximate entropy (ApEn), sample entropy (SampEn), permutation entropy (PerEn), Higuchi fractal dimension (HFD), Petrosian fractal dimension (PFD), Hjorth parameters (HP), zero crossing (ZeCr), higher-order crossing (HOC), empirical mode decomposition (EMD), higher-order spectral (HOS), Katz’s fractal dimension (KFD), statistics (ST).</p> Full article ">Figure 5
<p>Statistical feature extraction methods in the time domain.</p> Full article ">Figure 6
<p>Feature extraction methods in the frequency domain.</p> Full article ">Figure 7
<p>Feature extraction methods in the time–frequency domain.</p> Full article ">Figure 8
<p>Classification algorithms.</p> Full article ">
25 pages, 4793 KiB  
Article
Integrated Multilevel Production Planning Solution According to Industry 5.0 Principles
by Maja Trstenjak, Petar Gregurić, Žarko Janić and Domagoj Salaj
Appl. Sci. 2024, 14(1), 160; https://doi.org/10.3390/app14010160 - 24 Dec 2023
Cited by 3 | Viewed by 2487
Abstract
This paper presents the development and implementation of Integrated Multilevel Planning Solution (IMPS) a solution adhering to Industry 4.0 and 5.0 standards. Today, companies face challenges in understanding how new orders would impact existing production plans when there is limited traceability and information [...] Read more.
This paper presents the development and implementation of Integrated Multilevel Planning Solution (IMPS) a solution adhering to Industry 4.0 and 5.0 standards. Today, companies face challenges in understanding how new orders would impact existing production plans when there is limited traceability and information flow in their manufacturing process. The digital transformation of the production planning system enables a company to overcome the current challenges; however, to overcome the usual barriers of digital transformation a specialized solution for each company should be developed. IMPS was developed by first understanding the problems in the existing production planning process through a gemba (jap. for “actual place”) walk and interviews with stakeholders. The solution was designed with a human-centric approach and consists of seven components (Design System App (DSA), SAP (Systems Applications and Products in Data Processing), Microsoft Project, Microsoft Project Server, The Project Group (TPG) PSLink software, TPG ProjectLink, Tableau, and Smart Digital Assistance), which are well connected and integrated into the existing design. The system is accessible to the end user to find information, as the principles of Industry 5.0 require. A multivariant and multiuser planning capability was achieved with an interconnected Gantt chart of the master project with the ability to drill down into individual projects and custom views for various types of internal users. Most of the production planning solutions found in the literature were optimization-oriented, related to the improvements of the calculation methods within the planning activities in order to achieve a better efficiency of the planning system. Here, the goal was to achieve a system architecture that enabled a unique solution for design-to-order manufacturing without complex interventions into the existing system, which overcomes the most common barriers in Industry 4.0 implementations which are the human resistance to change, high investments, a lack of needed skills and knowledge for its implementation and use, and challenges of the adaptability to the new system. IMPS (ver 1.0) is a hybrid solution for SMEs, which aims to advance their planning system from the most commonly used Excel sheets towards a more advanced system but has financial and knowledge limitations from its implementation of highly complex software (ver. 1.0). Full article
(This article belongs to the Special Issue From Human–Machine Interaction to Human–Machine Cooperation: Status and Progress)
►▼ Show Figures

Figure 1

Figure 1
<p>Communication scheme between the planning and technical departments.</p> Full article ">Figure 2
<p>Footage of the old planning system. The system is not connected.</p> Full article ">Figure 3
<p>A display which is not suitable for presentation to the end user. It is used exclusively for work in MS Project.</p> Full article ">Figure 4
<p>IMPS system architecture.</p> Full article ">Figure 5
<p>Factory load chart. The Tableau system was connected to the MS Project database and was used for reporting and production capacity planning.</p> Full article ">Figure 6
<p>Smart Digital Assistance (SDA).</p> Full article ">Figure 7
<p>TSS Web App—interactive web display of short-term plans.</p> Full article ">

Review

Jump to: Research

21 pages, 476 KiB  
Review
A Review of Artificial Intelligence Research in Peer-Reviewed Communication Journals
by Tugce Ertem-Eray and Yang Cheng
Appl. Sci. 2025, 15(3), 1058; https://doi.org/10.3390/app15031058 - 22 Jan 2025
Viewed by 1431
Abstract
This study analyzes artificial intelligence (AI) research in communication scholarship through a content analysis of published articles between 2006 and 2022. It aims to understand the status of AI research between 2006 and 2022 and identify directions for future inquiry. Findings indicate that [...] Read more.
This study analyzes artificial intelligence (AI) research in communication scholarship through a content analysis of published articles between 2006 and 2022. It aims to understand the status of AI research between 2006 and 2022 and identify directions for future inquiry. Findings indicate that the number of articles about AI has increased over the years and scholars should continue applying existing theoretical frameworks or proposing new ones to investigate diverse topics across cultural and sociopolitical contexts. Full article
(This article belongs to the Special Issue From Human–Machine Interaction to Human–Machine Cooperation: Status and Progress)
►▼ Show Figures

Figure 1

Figure 1
<p>The number of articles about AI in peer-reviewed journals in the communication field between 2006 and 2022.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop