Submit to Sensors Review for Sensors Propose a Special Issue

Journal Browser

► Journal Browser

Human Centered Artificial Intelligence: Putting the Human in the Loop for Implementing Sensors Based Intelligent Environments

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensors and Robotics".

Deadline for manuscript submissions: closed (31 December 2022) | Viewed by 11463

Share This Special Issue

Special Issue Editors

Prof. Dr. Constantine Stephanidis

E-Mail Website
Guest Editor

1. Foundation for Research and Technology—Hellas (FORTH), Institute of Computer Science, 70013 Heraklion, Greece
2. Department of Computer Science, University of Crete, 70013 Heraklion, Greece
Interests: human–computer interactions; universal access; design for all; ambient intelligence; interaction in smart environments
Special Issues, Collections and Topics in MDPI journals

Dr. George Margetis

E-Mail Website
Guest Editor

Institute of Computer Science, Foundation for Research and Technology—Hellas (FORTH), 70013 Heraklion, Greece
Interests: human-centered AI; ambient intelligence; X-reality; intelligent user interfaces; universal access; design for all; human–computer interactions
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The ushering of artificial intelligence (AI) in our everyday life has already stimulated rich discussions with, on the one hand, enthusiastic forecasts about how AI technologies will support human activities and improve quality of life, and, on the other hand, dark scenarios about the potential pitfalls and dangers entailed. In light of the above, there is an urgent need for a human-centered AI approach that will not just aim to consider human needs and requirements, but, more importantly, will actively aim to put humans in the loop. Recent research efforts towards better explainability, trustworthiness, and transparency pinpoint this need as a prerequisite for harmonious human and autonomous system symbiosis.

In parallel, the unprecedented growth of the data generated from a vast number of sensors, cyber–physical and embedded systems, and IoT, which are already interwoven in our everyday life, lays the foundation for the fast pace developments of AI in general and machine learning in particular. However, this rapid evolution in the field of AI, associated with a remarkable depth of novel research contributions focusing on AI functionality, has not been accompanied by similar emphasis and progress on equally important fundamental aspects and design considerations advocated by the human-centered design process.

Keeping bridging this gap in mind, this Special Issue aims to solicit original and high quality research articles that consider the current evolvement of AI approaches under a human-centric approach in the development of intelligent environments. Exceptional contributions that extend previously published work will also be considered, provided that they contribute at least 60% new results. Authors of such submissions will be required to provide a clear indication of the new contributions and explain how this work extends the previously published contributions.

Topics may include, but are not limited to, the following:

Active machine learning
Adaptive personal AI systems
Causal learning, causal discovery, causal reasoning, causal explanations, and causal inference
Cognitive computing
Decision making and decision support systems
Emotional intelligence
Explainable, accountable, transparent, and fair AI
Explanatory user interfaces and HCI for explainable AI
Ethical and trustworthy AI
Federated learning and cooperative intelligent information systems and tools
Gradient-based interpretability
Interaction modalities and devices: visual, 2D/3D, augmented reality, simulations, digital twin, conversational interfaces, and multimodal interfaces
Interactive machine learning
Interpretability in reinforcement learning
Human–AI interactions and intelligent user interfaces
Human–AI teaming
Natural language generation for explanatory models
Processes, tools, methods, user involvement, user research, evaluation, AI technology assessment and customization, and standards
Rendering of reasoning processes
Self-explanatory agents and decision support systems
Usability of human–AI interfaces

Dr. Constantine Stephanidis
Dr. George Margetis
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. Sensors 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 2600 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.

Keywords

Human-centered AI
Explainable AI
Human in the loop
Human–AI symbiosis
Ethical, trustworthy, transparent, and fair AI

Published Papers (3 papers)

Download All Papers

Research

Jump to: Review

38 pages, 5753 KiB

Open AccessArticle

A Bayesian Network Approach to Explainable Reinforcement Learning with Distal Information

by Rudy Milani, Maximilian Moll, Renato De Leone and Stefan Pickl

Sensors 2023, 23(4), 2013; https://0-doi-org.brum.beds.ac.uk/10.3390/s23042013 - 10 Feb 2023

Cited by 1 | Viewed by 2236

Abstract

Nowadays, Artificial Intelligence systems have expanded their competence field from research to industry and daily life, so understanding how they make decisions is becoming fundamental to reducing the lack of trust between users and machines and increasing the transparency of the model. This paper aims to automate the generation of explanations for model-free Reinforcement Learning algorithms by answering “why” and “why not” questions. To this end, we use Bayesian Networks in combination with the NOTEARS algorithm for automatic structure learning. This approach complements an existing framework very well and demonstrates thus a step towards generating explanations with as little user input as possible. This approach is computationally evaluated in three benchmarks using different Reinforcement Learning methods to highlight that it is independent of the type of model used and the explanations are then rated through a human study. The results obtained are compared to other baseline explanation models to underline the satisfying performance of the framework presented in terms of increasing the understanding, transparency and trust in the action chosen by the agent. Full article

(This article belongs to the Special Issue Human Centered Artificial Intelligence: Putting the Human in the Loop for Implementing Sensors Based Intelligent Environments)

► Show Figures

Figure 1

25 pages, 16586 KiB

Open AccessArticle

Design and Implementation of a New Training Flight Simulator System

by Ming-Yen Wei, Shen-An Fang and Ji-Wei Liu

Sensors 2022, 22(20), 7933; https://0-doi-org.brum.beds.ac.uk/10.3390/s22207933 - 18 Oct 2022

Cited by 3 | Viewed by 3778

Abstract

Aircraft flight simulators have good cost efficiency, high reusability, and high flight safety. All airlines and aircraft manufacturing companies choose it as sophisticated training equipment for ground simulation, effectively reducing pilot training costs, ensuring personnel safety and aircraft wear and tear. The new simulator proposed in this paper combines a digital motion-cueing algorithm, flight software and motion platform to make pilots feel as if they are in the real world. By using EtherCAT technology to drive the motion-cueing platform, it can improve the data transmission speed of the simulator as well as the strong anti-interference ability of communication and the control operation efficiency. Therefore, the simulated flight subjects can perform long-distance and large-angle training. Next, a set of measurement systems was established to provide monitoring items including attitude, velocity and acceleration, which can be displayed on the screen and recorded on the computer in real time and dynamically. Finally, seven training subjects were implemented to demonstrate the feasibility and correctness of the proposed method. Full article

(This article belongs to the Special Issue Human Centered Artificial Intelligence: Putting the Human in the Loop for Implementing Sensors Based Intelligent Environments)

► Show Figures

Figure 1

Review

Jump to: Research

20 pages, 1605 KiB

Open AccessReview

Deep Learning-Based Motion Style Transfer Tools, Techniques and Future Challenges

by Syed Muhammad Abrar Akber, Sadia Nishat Kazmi, Syed Muhammad Mohsin and Agnieszka Szczęsna

Sensors 2023, 23(5), 2597; https://0-doi-org.brum.beds.ac.uk/10.3390/s23052597 - 26 Feb 2023

Cited by 5 | Viewed by 3401

Abstract

In the fourth industrial revolution, the scale of execution for interactive applications increased substantially. These interactive and animated applications are human-centric, and the representation of human motion is unavoidable, making the representation of human motions ubiquitous. Animators strive to computationally process human motion in a way that the motions appear realistic in animated applications. Motion style transfer is an attractive technique that is widely used to create realistic motions in near real-time. motion style transfer approach employs existing captured motion data to generate realistic samples automatically and updates the motion data accordingly. This approach eliminates the need for handcrafted motions from scratch for every frame. The popularity of deep learning (DL) algorithms reshapes motion style transfer approaches, as such algorithms can predict subsequent motion styles. The majority of motion style transfer approaches use different variants of deep neural networks (DNNs) to accomplish motion style transfer approaches. This paper provides a comprehensive comparative analysis of existing state-of-the-art DL-based motion style transfer approaches. The enabling technologies that facilitate motion style transfer approaches are briefly presented in this paper. When employing DL-based methods for motion style transfer, the selection of the training dataset plays a key role in the performance. By anticipating this vital aspect, this paper provides a detailed summary of existing well-known motion datasets. As an outcome of the extensive overview of the domain, this paper highlights the contemporary challenges faced by motion style transfer approaches. Full article

(This article belongs to the Special Issue Human Centered Artificial Intelligence: Putting the Human in the Loop for Implementing Sensors Based Intelligent Environments)

► Show Figures