IEEE Computational Intelligence Magazine - May 2021 - 13

and the comparison results of the proposed algorithm with the state-of-theart algorithms indicate the proposed
algorithm is more effective. "
IEEE Transactions on Games

Cor relating Psyc hophysiological
Responses of Exergaming Boxing for
Predictive Heart Rate Regression Models in Young Adults, by N. A. Mohd
Jai, M. Mat Rosly, and N. A. Abd
Razak, IEEE Transactions on Games,
Vol. 12, No. 4, December 2020, pp.
398-405.
Digital Object Identifier: 10.1109/
TG.2020.3039838
" The purpose of this article is to
validate the correlations between the
heart rate (HR) and rating of perceived
exertion (RPE) during exergaming
boxing in sitting and standing positions.
Thirty healthy adults, whose mean age
was 25.10 and standard deviation (SD)
2.95 years, were recruited to play 10 minutes of exergaming boxing in sitting
and standing positions. HR measurements were obtained at rest and during
gameplay. RPE was assessed using
Borg's modified (1-10) and original
(6-20) scales. A paired-sample t-test,
bivariate Pearson's, and Spearman's rho
correlations were used to analyze the
results. Mean HR was significantly
higher while exergaming in standing
position (130.79 SD23.18 bpm) as
compared to sitting position (116.46
SD19.08 bpm) (p $¥leq 0.05$). There
was a significant correlation between
HR and RPE values while playing
boxing exergaming in the standing
position. A regression model that can be
fitted into an equation to predict HR
from reported RPE was derived from
the significant values of Pearson's correlations. However, HR and RPE values
did not significantly correlate with
each other during exergaming boxing
in the sitting position. The formula
extracted from the linear regression
models provides reliable predictions in
estimating HR from the reported RPE
while exergaming boxing in the standing position. "

IEEE Transactions on Cognitive
and Developmental Systems

Toward Improving Engagement in Neural Rehabilitation: Attention Enhancement Based on Brain-Computer Interface
and Audiovisual Feedback, by J. Wang,
W. Wang, and Z.-G. Hou, IEEE
Transactions on Cognitive and Developmental Systems, Vol. 12, No. 4,
December 2020, pp. 787-796.
Digital Object Identifier: 10.1109/
TCDS.2019.2959055
" Both motor and cognitive function
rehabilitation benefits can be improved
significantly by patients' active parti-
cipation. To this goal, an attention
enhancement system based on the braincomputer interface (BCI) and audiovisual feedback is proposed. First, an
interactive position-tracking riding game
is designed to increase the training challenge and neural engagement. Subjects
were asked to drive one of the avatars to
keep up with another by adjusting their
riding speed and attention. Second, the
subject's electroencephalogram (EEG)based attention level is divided into three
regions (low, moderate, and high) by
using the theta-to-beta ratio (TBR).
According to the subject's attention
states, different speed adjustment strategies are adopted to adjust the tracking
challenge and improve the subject's
attention. Besides, if the subject's attention focused on the training is moderate
or low, an auditory feedback will be
given to remind the subject to pay more
attention to the training. The contrast
experimental results show that subjects'
performance indicated by overall attention level and average muscle activation
can be improved significantly by using
the attention enhancement system,
which validates the feasibility of the proposed system for improving the neural
and motor engagement. "
IEEE Transactions on Emerging
Topics in Computational
Intelligence

Multidomain Features Fusion for ZeroShot Learning, by Z. Liu, Z. Zeng, and

C. Lian, IEEE Transactions on Emerging Topics in Computational Intelligence,
Vol. 4, No. 6, December 2020, pp.
764-773.
Digital Object Identifier: 10.1109/
TETCI.2018.2868061
" Given a novel class instance, the purpose of zero-shot learning (ZSL) is to
learn a model to classify the instance by
seen samples and semantic information
transcending class boundaries. The difficulty lies in how to find a suitable space
for zero-shot recognition. The previous
approaches use semantic space or visual
space as classification space. These methods, which typically learn visual-semantic
or semantic-visual mapping and directly
exploit the output of the mapping function to measure similarity to classify new
categories, do not adequately consider
the complementarity and distribution
gap of multiple domain information. In
this paper, we propose to learn a multidomain information fusion space by a
joint learning framework. Specifically, we
consider the fusion space as a shared
space in which different domain features
can be recovered by simple linear transformation. By learning a n-way classifier
of fusion space from the seen class samples, we also obtain the discriminative
information of the similarity space to
make the fusion representation more separable. Extensive experiments on popular
benchmark datasets manifest that our
approach achieves state-of-the-art performances in both supervised and unsupervised ZSL tasks. "
IEEE Transactions on
Artificial Intelligence

A Recommender System for Metaheuristic Algorithms for Continuous Optimization Based on Deep Recurrent Neural
Networks, by Y. Tian, S. Peng, X.
Zhang, T. Rodemann, K. C. Tan, and
Y. Jin, IEEE Transactions on Artificial
Intelligence, Vol. 1, No. 1, September
2020, pp. 5-18.
Digital Object Identifier: 10.1109/
TAI.2020.3022339
(continued on page 76)

MAY 2021 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE

IEEE Computational Intelligence Magazine - May 2021

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - May 2021