Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Dec 21;22(1):20.
doi: 10.3390/s22010020.

Sensors and Artificial Intelligence Methods and Algorithms for Human-Computer Intelligent Interaction: A Systematic Mapping Study

Boštjan Šumak  1 , Saša Brdnik  1 , Maja Pušnik  1
Affiliations

Sensors and Artificial Intelligence Methods and Algorithms for Human-Computer Intelligent Interaction: A Systematic Mapping Study

Boštjan Šumak et al. Sensors (Basel). .

Abstract

To equip computers with human communication skills and to enable natural interaction between the computer and a human, intelligent solutions are required based on artificial intelligence (AI) methods, algorithms, and sensor technology. This study aimed at identifying and analyzing the state-of-the-art AI methods and algorithms and sensors technology in existing human-computer intelligent interaction (HCII) research to explore trends in HCII research, categorize existing evidence, and identify potential directions for future research. We conduct a systematic mapping study of the HCII body of research. Four hundred fifty-four studies published in various journals and conferences between 2010 and 2021 were identified and analyzed. Studies in the HCII and IUI fields have primarily been focused on intelligent recognition of emotion, gestures, and facial expressions using sensors technology, such as the camera, EEG, Kinect, wearable sensors, eye tracker, gyroscope, and others. Researchers most often apply deep-learning and instance-based AI methods and algorithms. The support sector machine (SVM) is the most widely used algorithm for various kinds of recognition, primarily an emotion, facial expression, and gesture. The convolutional neural network (CNN) is the often-used deep-learning algorithm for emotion recognition, facial recognition, and gesture recognition solutions.

Keywords: IUI; artificial intelligence; human–computer intelligent interaction; intelligent user interfaces; sensors.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.

Figures

Figure 1
Figure 1
A general architecture of a multimodal HCII system (adapted from [6]).
Figure 2
Figure 2
Systematic mapping study process adapted from [127].
Figure 3
Figure 3
Research process map.
Figure 4
Figure 4
Flow diagram of the database searches and article screening process.
Figure 5
Figure 5
Number of studies published through years 2010–2021 (all = 454).
Figure 6
Figure 6
Percentage of papers based on publication type (all = 454).
Figure 7
Figure 7
Number of studies by year and research type.
Figure 8
Figure 8
Number of studies by year and research methodology.
Figure 9
Figure 9
Number of studies by year and research method type.
Figure 10
Figure 10
Number of studies by year and data collection method.
Figure 11
Figure 11
Number of studies by year and research standpoint.
Figure 12
Figure 12
Distribution of HCII solutions’ development phases according to the research standpoint.
Figure 13
Figure 13
Distribution of HCI recognition solutions according to the research standpoint.
Figure 14
Figure 14
Distribution of data sources in existing HCI recognition solutions.
Figure 15
Figure 15
Distribution of sensors in existing HCI recognition solutions.
Figure 16
Figure 16
Distribution of AI methods and algorithms according to the research standpoint.
Figure 17
Figure 17
Distribution of AI methods and algorithms for HCI recognition solutions.
Figure 18
Figure 18
Distribution of data sources used in AI methods and algorithms.
Figure 19
Figure 19
Distribution of sensors used in AI methods and algorithms.
Figure 20
Figure 20
Distribution of AI methods and algorithms HCI recognition used for HCI recognition solutions.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Cano S., Araujo N., Guzman C., Rusu C., Albiol-Perez S. Low-Cost Assessment of User eXperience Through EEG Signals. IEEE Access. 2020;8:158475–158487. doi: 10.1109/ACCESS.2020.3017685. - DOI
    1. Elboushaki A., Hannane R., Afdel K., Koutti L. MultiD-CNN: A multi-dimensional feature learning approach based on deep convolutional networks for gesture recognition in RGB-D image sequences. Expert Syst. Appl. 2020;139:112829. doi: 10.1016/j.eswa.2019.112829. - DOI
    1. Golestan S., Mahmoudi-Nejad A., Moradi H. A Framework for Easier Designs: Augmented Intelligence in Serious Games for Cognitive Development. IEEE Consum. Electron. Mag. 2019;8:19–24. doi: 10.1109/MCE.2018.2867970. - DOI
    1. Shaikh S., Ajmal M., Ahmed N., Badar F. Comprehensive Understanding of Intelligent User Interfaces. Int. J. Adv. Comput. Sci. Appl. 2017;8:395–401. doi: 10.14569/IJACSA.2017.080652. - DOI
    1. Pantic M., Nijholt A., Pentland A., Huanag T.S. Human-Centred Intelligent Human Computer Interaction (HCI2): How far are we from attaining it? Int. J. Auton. Adapt. Commun. Syst. 2008;1:168. doi: 10.1504/IJAACS.2008.019799. - DOI

LinkOut - more resources