1,834 Hits in 5.2 sec

How Mock Model Training Enhances User Perceptions of AI Systems [article]

Amama Mahmood, Gopika Ajaykumar, Chien-Ming Huang
2021 arXiv   pre-print
We further contribute to work on improving user perceptions of AI by demonstrating that bringing the user in the loop through mock model training can improve their perceptions of an AI agent's capability  ...  Prior work has highlighted the potential of factors such as transparency and explainability in improving user perceptions of AI.  ...  Figure 1 : 1 Figure 1: We explore how mock model training involving various data labeling strategies may affect users' perceptions of AI agents posed as driving assistants.  ... 
arXiv:2111.08830v1 fatcat:ur3dpzndzrcibmml6qoylmusmi

Discovering social interaction strategies for robots from restricted-perception Wizard-of-Oz studies

Pedro Sequeira, Patricia Alves-Oliveira, Tiago Ribeiro, Eugenio Di Tullio, Sofia Petisca, Francisco S. Melo, Ginevra Castellano, Ana Paiva
2016 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI)  
In this paper we propose a methodology for the creation of social interaction strategies for human-robot interaction based on restricted-perception Wizard-of-Oz studies (WoZ).  ...  The results of the evaluation study show that, by performing restricted-perception WoZ studies, our robots are able to engage in very natural and socially-aware interactions.  ...  Building the Task AI from Mock-up Studies Generally speaking, mock-up models are used to conduct studies before hardware and software development with the aim of abstracting the environment and the end-users  ... 
doi:10.1109/hri.2016.7451752 dblp:conf/hri/SequeiraA0TPMCP16 fatcat:tivjyguqzbdehaligr74743n7m

User Experience of Augmented Reality System for Astronaut's Manual Work Support

Kaj Helin, Timo Kuula, Carlo Vizzi, Jaakko Karjalainen, Alla Vovk
2018 Frontiers in Robotics and AI  
on a physical mock-up of an ISS module.  ...  cost, and time efficiency of the training.  ...  AUTHOR CONTRIBUTIONS KH: AR system description, EdcAR case and evaluation, conclusion; TK: Evaluation methods and results, conclusion; CV: ALTEC case description; JK: AR system description; AV: Evaluation  ... 
doi:10.3389/frobt.2018.00106 pmid:33500985 pmcid:PMC7805856 fatcat:p6kutzzcurbsfk72qef63fby2a

Explainable recommendation: when design meets trust calibration

Mohammad Naiseh, Dena Al-Thani, Nan Jiang, Raian Ali
2021 World wide web (Bussum)  
As a conclusion of our research, we provide five design principles: Design for engagement, challenging habitual actions, attention guidance, friction and support training and learning.  ...  In this paper, we explore how to help trust calibration through explanation interaction design. Our research method included two main phases.  ...  The co-design phase goal was to investigate how users of XAI systems would like to integrate AI-based explanations in their everyday decisionmaking task.  ... 
doi:10.1007/s11280-021-00916-0 pmid:34366701 pmcid:PMC8327305 fatcat:7mipj7ejpfbkxoq53oubsxw7ea

A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems [article]

Sina Mohseni and Niloofar Zarei and Eric D. Ragan
2020 arXiv   pre-print
, we present a categorization of interpretable machine learning design goals and evaluation methods to show a mapping between design goals for different XAI user groups and their evaluation methods.  ...  interpretable systems.  ...  ACKNOWLEDGMENTS The authors would like to thank anonymous reviewers for their helpful comments on earlier versions of this manuscript.  ... 
arXiv:1811.11839v5 fatcat:pl4mmtd2zzhipilebnc2khagu4

Machine Learning Explanations to Prevent Overtrust in Fake News Detection [article]

Sina Mohseni, Fan Yang, Shiva Pentyala, Mengnan Du, Yi Liu, Nic Lupfer, Xia Hu, Shuiwang Ji, Eric Ragan
2020 arXiv   pre-print
For a deeper understanding of Explainable AI systems, we discuss interactions between user engagement, mental model, trust, and performance measures in the process of explaining.  ...  We design a news reviewing and sharing interface, create a dataset of news stories, and train four interpretable fake news detection algorithms to study the effects of algorithmic transparency on end-users  ...  • RQ2: How do AI explanations affect users' mental models of intelligent assistants? • RQ3: How do AI explanations affect end-user trust and reliance in intelligent assistants?  ... 
arXiv:2007.12358v2 fatcat:cm4c2jrbx5artnwibigh4mearm


2021 STRATEGIES XXI - Command and Staff College  
The system aims to improve the cognitive capabilities and the perception of border guards through intuitive user interfaces that will help them acquire an improved situation awareness by filtering the  ...  and Secure Telecommunications, Robots swarming technique and Planning of Context-Aware Autonomous Missions, and Artificial Intelligence (AI), in order to implement user-friendly tools for border and coast  ...  Such a decision increases the cognitive of the user and the effort that has to be spent in thinking how to interact with the system.  ... 
doi:10.53477/2668-2028-21-31 fatcat:bd5huwf3yje67de33kyc4hkq6a

A Report to ARPA on Twenty-First Century Intelligent Systems

Barbara J. Grosz, Randall Davis
1994 The AI Magazine  
mock-up version of system (IRSS) could meet a wide range of Perception, Planning, and Acting).  ...  systems, but should also Sharable resources: The advances in ciently no matter how much faster we increase our understanding of how AI technology necessary for large- make our computers  ... 
doi:10.1609/aimag.v15i3.1097 dblp:journals/aim/GroszD94 fatcat:sh5zcoriujbmtknhdruh5e6jpy


Andrei-Dragoş POPESCU
2019 Annals of the University of Craiova for Journalism, Communication and Management  
AlphaGo was trained using data from real human Go games.  ...  This article will analyses several studies and researches on Artificial Intelligence (AI) and its other subsets, from a perspective of Data Input, focusing on a synthesis of several framework attributes  ...  The design of any AI systems starts with the choice of training data, which is the first place where unfairness can arise.  ... 
doaj:e6a8335a7255492ab040e5bb62146c50 fatcat:otesn4e4hzdeli5xv6hbps7qdu

Co-Creation: Human & AI Collaboration in Creative Expression

Sara Feldman
2017 EVA London 2017  
It also focuses on co-creativity between human and AI and what this means for the role of designers/artist today. Creative Artificial Intelligence systems. User experience design. Creative process.  ...  This paper focuses on understanding how CAIS encourages new modes of creative practice with users through cognitive and emotional UX factors within the domains of creative expressions.  ...  This adoption requires for new models of creative practice to emerge, where the system acts in collaboration with the users.  ... 
doi:10.14236/ewic/eva2017.84 dblp:conf/eva/Feldman17 fatcat:iogbrgajpvak3hfotchiuqn324

Data Management Plan [article]

Silvia Esparza-Becerra, Juan Vicente Balbastre-Tejedor
2021 Zenodo  
Figure 5 5 BUBBLES collision risk model training. Figure 6 6 Generation of data for training the BUBBLES collision model.  ...  These data sets will be generated in WP6 and will be used to achieve objectives SO 4 and SO 5. • Separation Error Model (AI algorithm trained to calculate the effect of nominal and non-nominal U-space  ... 
doi:10.5281/zenodo.4704920 fatcat:xzd5sulrqnfhnhfqnw6xp2ntny

Supporting the Contact Tracing Process with WiFi Location Data: Opportunities and Challenges

Kaely Hall, Dong Whi Yoo, Wenrui Zhang, Mehrab Bin Morshed, Vedant Das Swain, Gregory D. Abowd, Munmun De Choudhury, Alex Endert, John Stasko, Jennifer G Kim
2022 CHI Conference on Human Factors in Computing Systems  
To investigate how technology can alleviate this challenge, we developed a visualization tool using de-identified location data sensed from campus WiFi and provided it to contact tracers during mock contact  ...  We suggest design implications for technologies that can better highlight and inform contact tracers of potential areas of inconsistencies, and further present discussion on using imperfect data in decision  ...  The early collaboration and user research with contact tracers was thanks to the efforts of Shubhangi Gupta, Soumya Pachigolla, Tanuja Sawant, and Taylor Stillman.  ... 
doi:10.1145/3491102.3517703 fatcat:pj3h6lumhvdltiwndgzzjlzb2y

Augmented, Virtual and Mixed Reality in Dentistry: A Narrative Review on the Existing Platforms and Future Challenges

Riccardo Monterubbianesi, Vincenzo Tosco, Flavia Vitiello, Giulia Orilisi, Franco Fraccastoro, Angelo Putignano, Giovanna Orsini
2022 Applied Sciences  
Augmented Reality, Virtual Reality and Mixed Reality represent effective tools in the educational technology, as they can enhance students' learning and clinical training.  ...  Clinicians can apply Virtual Reality for a digital wax-up that provides a pre-visualization of the final post treatment result.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app12020877 fatcat:nt2w7wrltbaehhex4bp5clwd7u

Investigation of a Web-based Explainable AI Screening for Prolonged Grief Disorder

Wan Jou She, Chee Siang Ang, Robert A Neimeyer, Laurie A Burke, Yihong Zhang, Adam Jatowt, Yukiko Kawai, Jun Hu, Matthias Rauterberg, Holly G Prigerson, Panote Siriaraya
2022 IEEE Access  
Afterwards, five grief experts were asked to provide feedback on a mock-up of the results generated by the GIFT model, and discuss the potential value of the explanatory AI model in real-world PGD care  ...  Our results also showed that, in addition to the explainability of the model, the grief experts also preferred a more "empathetic" and "actionable" AI system, especially, when designing for patient end-users  ...  ACKNOWLEDGMENT The authors would like to thank the Ministry of Education in Taiwan for sponsoring the scholarship of studying abroad for the Ph.D. study of Wan Jou She.  ... 
doi:10.1109/access.2022.3163311 fatcat:3xwvnufwf5httgmyv727euj3lq

Artificial Intelligence powered smart phone application to facilitate medication adherence: Protocol for Human Factors Based Design (Preprint)

Don Roosan, Jay Chok, Mazharul Karim, Anandi V Law, Andrius Baskys, Angela Hwang, Moom R Roosan
2020 JMIR Research Protocols  
The results from this study will also open up future research opportunities in understanding how patients manage complex medication information and will inform the format and design for innovative, AI-powered  ...  Aim 1 has three phases: (1) an observational study to understand patient perception of fear and biases regarding medication information, (2) an eye-tracking study to understand the attention locus for  ...  Also, we acknowledge internal funding that supports this research from the Western University of Health Sciences, College of Pharmacy. Conflicts of Interest None declared.  ... 
doi:10.2196/21659 pmid:33164898 fatcat:pspgj47tlfaydor3tenmvxw7aq
« Previous Showing results 1 — 15 out of 1,834 results