=Paper=
{{Paper
|id=Vol-2559/invited1
|storemode=property
|title=Towards Affective Walkability for Healthy Ageing in the Future of the Cities
|pdfUrl=https://ceur-ws.org/Vol-2559/invited1.pdf
|volume=Vol-2559
|authors=Stefania Bandini,Francesca Gasparini
|dblpUrl=https://dblp.org/rec/conf/aiia/BandiniG19
}}
==Towards Affective Walkability for Healthy Ageing in the Future of the Cities==
https://ceur-ws.org/Vol-2559/invited1.pdf
Towards Affective Walkability for Healthy
Ageing in the Future of the Cities?
Stefania Bandini1,2[0000−0002−7056−0543] and
Francesca Gasparini1[0000−0002−6279−6660]
1
Department of Computer Science, Systems and Communications,
University of Milano - Bicocca, Italy
{stefania.bandini,francesca.gasparini}@unimib.it
2
RCAST - Research Center for Advanced Science & Technology
The University of Tokyo
bandini@jamology.rcast.u-tokyo.ac.jp
Abstract. Social inclusion of elderly pedestrians in urban contexts by
enhancing healthy mobility means increase the level of walkability, where
the perception of safe walking and road crossing is a crucial factor. The
measurement of stress during walking and dynamic collision avoidance
through the acquisition and the analysis of physiological signals during
experimental activity requires the design of proper experimental settings
and protocols, in order to assess innovative approaches towards an af-
fective walkability, and open novel investigation fields involving affective
computing, pedestrian dynamics and artificial intelligence. The main aim
of the paper is to illustrate some preliminary studies conducted within
an experimental activity to test the validity of the approach.
Keywords: ageing · walkability · collision avoidance · affective state·
physiological signals.
1 Introduction
The healthy ageing framework 2015-2030 of the World Health Organization
(WHO) emphasizes “the need for enabling older people to remain a resource to
their families, communities and economies”, extending the previous framework
from age-friendly cities to age-friendly environment, that comprises physical and
social environments in which long-live people live their lives [15].
This framework strongly suggests to create advanced solutions to sustain
the social inclusion of the elderly active pedestrians in urban contexts by “en-
hancing pedestrian mobility” and the level of walkability [13], and [6], namely,
“the measure of the overall walking and living conditions in an urban area”.
?
This research is partially supported by the FONDAZIONE CARIPLO
“LONGEVICITY-Social Inclusion for a Elderly through Walkability” (Ref. 2017-
0938), and by the Japan Society for the Promotion of Science (Ref. L19513).
Copyright c 2020 for this paper by its authors. Use permitted under Creative Com-
mons License Attribution 4.0 International (CC BY 4.0).
2 S. Bandini and F. Gasparini
Such approach suggests new perspectives in the design/planning of the future
of the cities: how accessible, comfortable, safe and secure the city is for walk-
ing/crossing, also in presence of perceptive and motor limitations [12]. Moreover,
a healthy and inclusive friendly city is also a city able to develop a “walkable
community” [8], namely, to design a human scale environment where safety is
promoted, and people can enjoy walking and gathering in comfort [14].
Amid the main factors characterizing walkability (accessibility, comfort, and
safety), the concept of safe walking is crucial: “walking is a basic and common
mode of transport with benefits to health and the environment. Measures must
be taken to improve the safety of walkers” [2].
The vehicle-pedestrian interaction while road crossing is a crucial point in the
perception of safe walking, and subjective perceptions must be considered, due
to the different degrees of vulnerability (age, gender, disabilities) of pedestrians.
In order to focus on the pedestrians’ perception of safe road crossing, new
approaches could be investigated, and new sets of technological devices adopted.
Wearable sensors and the affecting computing approach [10] nowadays offer new
research scenarios, allowing the design of new forms of data collection through
pedestrians’ physiological responses during walking and dynamic collision avoid-
ance, being road crossing one of the cases of collision avoidance in the research
field of pedestrian behavior modeling and simulation [5], [7]. Measuring and rec-
ognizing the affective state of people during walking activities contribute to a
better comprehension of their perception of the environment, and a better defi-
nition of walkable urban area. The affective recognition task represents a fruitful
research direction to the study of safe walking perception to assess and introduce
quantitative evaluation tools for the measurement of affective walkability.
Sensor technology has improved significantly and allows measuring physio-
logical signals as well as registering daily life activities (e.g. inertial sensors, video
and audio recordings). Several sensors can be easily integrated into smartphones
or wearable devices [17], making them more comfortable and usable. The inte-
gration of multi-modal signal sources provides new perspectives towards the cre-
ation of an affective walking assessment approach, considering both data coming
from physical activity and uncontrolled reactions related to affective responses
to stressful conditions. Moreover, the role of Artificial Intelligence when joint to
affective computing approaches is more and more contributing to the design of
new generations of computer-based system supporting the creation of services
for the future cities [16]. The measurement of the level of an affective walkability
passes through the measurement of the level of stress affecting pedestrians in
walking and road crossing, namely, during dynamic collision avoidance. There
exist several possible definitions of stress, typically with a negative meaning.
Lazarus and Folkman [9], deeply analyzed the concept of stress, especially in its
scientific use. They argued that stress, and thus its definition, derives from the
observed stimulus-response relationships and neither from the stimulus nor from
the response separately. According to them, stress can be considered as intrinsi-
cally related to the interaction of the subject with the environment. Within this
perspective, and in the context of the research here proposed, it can be seen as a
Towards Affective Walkability for Healthy Ageing in the Future of the Cities 3
defensive reaction used to protect oneself from dangerous events [11]. Measuring
physiological states during walking and collision avoidance through collecting
physiological states by means of wearable sensors is the research direction we
adopted to grasp more knowledge about, and contribute to design an experi-
mental affective walkability approach to address future application of AI-based
learning techniques.
Physiological signals are nowadays widely used to detect affective states [4].
In our investigation we consider Plethysmogram (PPG) and Galvanic Skin Re-
sponse (GSR) as they are well indicated to detect emotional arousal.
Arousal is a physiological and psychological state that can be related to
sensory alertness, mobility, and readiness to respond. It is thus activated in the
interaction between pedestrian and the environment as a defensive reaction to
preserve safety, which is the connotation of stress here adopted.
Moreover, motion data both physiological, measuring the muscle activity
with Electromyogram (EMG), and inertial (accelerometer and gyroscope data)
have been adopted, in order to design a novel integrated approach in the study
of pedestrian dynamics, within a multi-modal framework.
Relying on different signal sources that register both physiological and dy-
namic walking responses will provide accurate results for affective state recogni-
tion tasks. Within this preliminary research, the multi-modal approach has been
adopted, in order to synchronize and properly segment all the raw data streams
collected. Depending on the type of signal, a proper noise reduction filtering
has been performed. Characteristic patterns of these signals, related to induced
stressful states, can be identified and provide new insights for measuring the
perception of safe walking.
In this paper, preliminary studies conducted within an experimental activ-
ity are described to test the validity of the approach. Section 2 illustrates our
study of the perception of safe walking, explaining in details in-vitro (through
the design of the experimental setting in a protected space) and in-vivo (data
collections in the real world) experiments and observations. Section 2.1 reports
our experimental activity on human subjects during collision avoidance tasks,
in a strictly controlled indoor environment, while Section 2.2 is related to the
evaluation of the perception of safe side walking in a selected urban scenario
and experiments considering road crossing tasks (both outdoor). Preliminary
analyses of collected data are illustrated in Section 3. Finally, we draw some
conclusive remarks about the next steps of the research towards the adoption of
the best AI-based learning techniques to be selected to reach an affective walk-
ability approach through massive collection of data (from commercial sensors)
supporting the design of future urban inclusive environments.
2 The study of the perception of safe walking
Studying age-driven walking and road crossing behaviors by means of direct
observations, two types of experiments have been designed and developed in
different environment configurations, conducted respectively in Tokyo (Japan)
4 S. Bandini and F. Gasparini
and in Milan (Italy). These experiments involved two populations: a population
of young adults (18 - 35 years old) and a population of elderly people (over 60),
in order to compare different affective behaviors.
In Tokyo in-vitro data collection experiments (i.e. through the design of the
experimental setting in a protected space) have been conducted in a controlled
laboratory environment, with the aim of studying pedestrian behaviour avoiding
collisions. In Milano in-vivo data collection (i.e. data collections in the real world)
in an outdoor uncontrolled environment have been carried out, to evaluate the
safety perception in pedestrian environments considering in particular crossings,
and sidewalks [1].
Both physiological signals and inertial data have been collected using wear-
able sensors produced by Shimmer3 [3]. Galvanic Skin Response (GSR), Pho-
toplethysmography (PPG), and Electromiogram (EMG) have been acquired to-
gether with accelerometer and gyroscope data. EMG is a two channels signal
that measures the muscle activity of the medial gastrocnemius muscle and of
the anterior tibial muscle. The adopted sensors are shown in figure 1.
Fig. 1: Wearable devices adopted.
2.1 Dynamic collision avoidance
In order to investigate the walking behavior during a dynamic collision avoidance
task, an experiment in a controlled laboratory environment has been carried out.
Two different populations have been considered: a population of young adults,
composed of 14 Japanese master and PhD students, (22 - 34 years old, 4 women),
and Japanese elderly people (retired), 20 subjects, (60-70 years old, 10 women).
3
https://www.shimmersensing.com/
Towards Affective Walkability for Healthy Ageing in the Future of the Cities 5
The controlled experimental environment is depicted in Figure 2. The plan
of the indoor environment is reported in the top left image, showing the U path
where the subjects are moving. Two subjects (sbj1 and sbj2), start at the same
time. The collision avoidance zone is identified by a red rectangle and depicted
also in the image at the top right. The two obstacles are controlled by one of the
experimenter, and the two subjects have to avoid the collision (bottom right).
During the rest of the U path, subjects walk with their own natural pace (bottom
left).
Fig. 2: Setting of the in-vitro experiment. Top left: the plant of the indoor con-
trolled environment, where a U path has been defined. The collision avoidance
zone is identified by a red rectangle and depicted also in the image at the top
right. The two obstacles are controlled by one of the experimenter and the two
subjects have to avoid the collision (figure bottom right). During the rest of the
U path, subjects walk with their own natural pace.
The experimental procedure is described as follows:
1. Baseline acquisition: all data are acquired for one minute, the two subjects
standing still. These data serve as reference for each subject.
2. Collision avoidance: the two subjects walk with their own pace, till they
reach the collision avoidance zone, where they have to avoid the collisions
with both obstacles and the other subject. Then they complete the U path,
with their natural pace.
3. Normal walk: the two subjects walk on the second half of the U path, with
their natural pace.
The whole procedure is repeated form 1 to 3, three times.
6 S. Bandini and F. Gasparini
2.2 Perception of safe walking and road crossing
Fig. 3: The in-vivo data collection. The selected urban environment is depicted
in the image on the left, where zebra-crossing and sidewalk considered are high-
lighted with red rectangles. Images on the right report a subject performing the
normal walking and the crossing tasks respectively.
For the in-vivo data collection, an experiment in an uncontrolled urban envi-
ronment has been conducted. For this experiment 14 young adults, all computer
science students at the University of Milano-Bicocca, have been recruited, (20-26
years old, 7 women). The aim of this experiment is to evaluate the safe walking
perception in urban scenarios, in particular of pedestrians crossings a road, and
walking on the sidewalks. To this end, a two way road, in correspondence to a
crossroad, without traffic lights, has been considered. In Figure 3 on the left,
this experimental environment is depicted. The zebra crossing and the portion
of the sidewalks where the experiment was conducted, are highlighted with red
rectangles. Images on the right report a subject performing the normal walking
and the crossing tasks respectively.
The experimental procedure is described as follows:
1. Normal walk: the subject walks on the sidewalks, back and forth, with its
own pace.
2. Baseline acquisition: all data are acquired for one minute, the two subjects
standing still. These data serve as reference for each subject.
3. Crossing: the subject has to cross the road in correspondence to the zebra
crossing, back and forth.
4. Baseline acquisition: all data are acquired for one minute, the two subjects
standing still. These data serve as a further reference for each subject.
The whole procedure is repeated form 1 to 4, three times.
Towards Affective Walkability for Healthy Ageing in the Future of the Cities 7
3 Discussion
During both the in-vitro and in-vivo experiments, raw data streams from mul-
tiple sensors have been acquired. A multi-modal system has been employed to
manage all the sensors in order to synchronize and properly segment all the
raw data streams into different tasks. As a pre-processing step, preliminary to
the segmentation phase, each signal has been filtered to perform noise reduc-
tion (see the review paper [10] for details on processing for each type of sensor).
Once data has been segmented, due to the high subjectivity of the physiological
responses, z-score normalization has been applied. The intent of this work is
to reveal if characteristic patterns of these signals can be identified related to
induced stressful states, providing new insights for measuring the perception of
safe walking.
As an example of what physiological signals can reveal, the in-vivo experi-
ment is considered.
In Figure 4, GSR and EMG signals of one subject, collected during the ex-
periment are depicted. Event windows are also drown to highlight the three
different tasks of the experiment: B=Baseline acquisition, W=Walk on the side-
walks, C=crossing the street. The Q window (Q=Questionnaires) is the initial
part of the experiment when the subject received the informed consent, and all
the details about the experimental procedure, and he/she provides personal in-
formation (age, level of instructions, gender, etc). The bottom signal (red one)
corresponds to the EMG, i.e. muscle activity. As expected, muscles are activated
by walking. The stops during the back and forth crossing are also clearly visi-
ble. Top signal (blue) is the EDA response. During non-stressful tasks (B and
W) the physiological response denotes a low activation, (slowly varying signal),
while in correspondence to the crossing tasks (C windows), significant peaks are
detectable. Moreover, the two single crossings corresponding to the back and
forth paths can be identified by the two main peaks. This preliminary analy-
sis confirms that physiological signals can be adopted to detect an increase of
arousal related to induced stress or activated by an attentive state originated
by the interaction between subject and environment, especially during collision
avoidance tasks.
4 Final remarks
Within this work, the problem of evaluating the perception of safe walking and
road crossing (collision avoidance task) has been faced, introducing a novel in-
vestigation field, involving affective computing.
An affective walkability approach that relies on physiological signals acquired
by means of wearable sensors has been introduced.
The preliminary analyses on data collected in in-vivo and in-vitro experi-
ments show that there are promising correlations between signal patterns and
affective states, related to different walking conditions. These considerations jus-
tify a massive effort to collect more experimental data from multi-modal sensors
8 S. Bandini and F. Gasparini
Fig. 4: EMG (bottom, red signal) and GSR (top, blue signal) acquired from
one subject in the in-vivo experiment are reported. Event window are also
shown to distinguish the different tasks: B=Baseline, W=Walk, C=Crossing,
and Q=Questionnaire.
within the context of the interaction between pedestrians and environment, es-
pecially considering dynamic collision avoidance tasks.
Proper features from all multi-modal signals collected can be extracted. Be-
sides initial statistical inferences that could support our preliminary considera-
tions, to take advantage from multi-modal sources, information fusion is manda-
tory, either at the feature extraction or at the decision level. Increasing collected
data and introducing multi-modal fusion strategies open the direction towards
the involvement of AI-based learning perspectives to reach an affective walkabil-
ity approach in the design of future urban inclusive environments, through the
future massive collection of data using commercial sensors.
Acknowledgement
This preliminary research has been possible thanks to the kind support of Kat-
suhiro Nishinari, Daichi Yanagisawa, Kenichiro Shimura (Research Center for
Advanced Science and Technology, The University of Tokyo) who supported the
organization of the experiments in Tokyo, and Arch. Matteo Belfiore, supporting
the team during the design of the experimental set in Tokyo.
References
1. Bandini, S., Gorrini, A., Manenti, L., Vizzari, G.: Crowd and pedestrian dynamics:
Empirical investigation and simulation. In: Proceedings of Measuring Behavior.
vol. 2012, pp. 308–311. Citeseer (2012)
Towards Affective Walkability for Healthy Ageing in the Future of the Cities 9
2. Bartolomeos, K., Croft, P., Job, S., Khayesi, M., Kobusingye, O., Peden, M.,
Schwebel, D., Sleet, D., Tiwari, B., Turner, B., et al.: Pedestrian safety: A road
safety manual for decision-makers and practitioners. Geneva: World Health Orga-
nization (2013)
3. Burns, A., Doheny, E.P., Greene, B.R., Foran, T., Leahy, D., O’Donovan, K., Mc-
Grath, M.J.: ShimmerTM : an extensible platform for physiological signal capture.
In: 2010 Annual International Conference of the IEEE Engineering in Medicine
and Biology. pp. 3759–3762. IEEE (2010)
4. Can, Y.S., Arnrich, B., Ersoy, C.: Stress detection in daily life scenarios using
smart phones and wearable sensors: A survey. Journal of biomedical informatics p.
103139 (2019)
5. Collett, P., Marsh, P.: Patterns of public behaviour: collision avoidance on a pedes-
trian crossing. Semiotica 12(4), 281–300 (1974)
6. Ewing, R., Handy, S.: Measuring the unmeasurable: Urban design qualities related
to walkability. Journal of Urban design 14(1), 65–84 (2009)
7. Gorrini, A., Crociani, L., Vizzari, G., Bandini, S.: Observation results on
pedestrian-vehicle interactions at non-signalized intersections towards simulation.
Transportation research part F: traffic psychology and behaviour 59, 269–285
(2018)
8. Jacobs, J.: Creating a walkable shelbourne community. Shelbourne Valley Walka-
bility Report. Saanich, British Columbia, Canada (2011)
9. Lazarus, R.S., Folkman, S.: Stress, appraisal, and coping. Springer publishing com-
pany (1984)
10. Schmidt, P., Reiss, A., Dürichen, R., Laerhoven, K.V.: Wearable-based affect recog-
nition—a review. Sensors 19(19), 4079 (2019)
11. Sioni, R., Chittaro, L.: Stress detection using physiological sensors. Computer
48(10), 26–33 (2015)
12. Speck, J.: Walkable City: How Downtown Can Save America, One Step at a Time.
North Point Press, New York, USA (2012)
13. Stantec: Walkability: Proposed Walkability Strategy for Edmonton. Tech. rep.,
Stantec Consulting Ltd (2010)
14. Talen, E., Koschinsky, J.: The walkable neighborhood: A literature review. Inter-
national Journal of Sustainable Land Use and Urban Planning 1(1) (2013)
15. World health organization: Age-friendly environments. a handbook of domains for
policy action. WHO Regional Office for Europe, Copenhagen, Denmark (2017)
16. Xia, S., de Godoy Peixoto, D., Islam, B., Islam, M.T., Nirjon, S., Kinget, P.R.,
Jiang, X.: Improving pedestrian safety in cities using intelligent wearable systems.
IEEE Internet of Things Journal 6(5), 7497–7514 (2019)
17. Yetisen, A.K., Martinez-Hurtado, J.L., Ünal, B., Khademhosseini, A., Butt, H.:
Wearables in medicine. Advanced Materials 30(33), 1706910 (2018)