In recent years, the growing trend of personal well-being has led an increasing number of people to engage in walking related activities to improve their physical health. As such, it is becoming increasingly important to develop walking navigation systems which are able to effectively support such activities. The conventional walking navigation systems found in modern smart phone devices usually recommends the shortest route to a destination and are not aimed at facilitating health promoting walking activities. Therefore, in this paper, we propose a novel walking navigation system which takes into consideration the rate of perceived exertion (based on the walking distance, geographical elevation and heart rate data) and the avoidance of dangerous locations and the possibility of passing through highly rated scenic locations (based on social network data from twitter) when recommending a route. Finally, we describe the results of a feasibility experiment study carried out to test the routes in the system.
INTRODUCTION The recent growing trend of personal well-being has led an increasing number of people to engage in walking related activities for a variety of health related purposes, such as to reduce weight and maintain their physical fitness. Various ©2018. Copyright for the individual papers remains with the authors. Copying permitted for private and academic purposes.
WII’18, March 11, 2018, Tokyo, Japan
government policies and initiatives (such as [
Despite walking navigation systems becoming more commonplace in modern smart phone devices, the conventional navigation systems were not created with the goal of facilitating health related walking activities and generally recommends the shortest route to a selected destination. In this paper, we propose a smart walking navigation system which is aimed especially at supporting health related walking activities. To create a walking route which is effective, enjoyable and safe for users, we describe how an appropriate perceived exertion load could be determined based on information such as the walking duration, geographical inclination and heart rate and describe how the system could help users avoid accident prone locations and suggest pleasurable walking routes which passes through scenic locations by using social network data from twitter.
The appropriate perceived exertion load refers to an exertion load which is appropriate for a user based on their physical characteristics and their purpose of exercise. Overall, the walking load of each route is calculated by combining data from the measurement of the level of inclination and distance within the route with heart rate data. To help avoid dangerous routes, data from geo-tagged twitters are also obtained and analyzed. For instances, various phrases which denote a dangerous conditions, such as "it’s dangerous", "I’m afraid" or "It’s dark" are collected and used to estimate the level of danger on a route. In addition, to facilitate a more enjoyable walking experience, data which could indicate the presence of appropriate resting locations is also taken into consideration. This includes data which describes locations with good panoramic views or seasonal sightseeing locations (for cherry blossom and autumn leaf viewing etc.). Similar to how we obtained information about dangerous routes, the system collects data about appropriate resting locations from geo-tagged tweets. Highly evaluated scenic locations are identified and considered in the route recommendation.
Overall, this paper presents a smart walking navigation system which recommends a route based on the rate of perceived exertion and the possibility of passing through highly rated scenic locations and avoiding dangerous locations. In this paper, we discuss how such a navigation system could be implemented. Afterwards, we describe a feasibility experiment carried out to test the routes in the proposed system.
RELATED RESEARCH
Route recommendation systems have been developed and used
for a variety of purposes such as in tourism and health care
(see [
Examples of walking support and route recommendation
systems which focus on health and safety include one system
devised by Takaishi et al [
Various systems have also been developed to help provide
users with a more pleasurable walking experience. For
instance, one study proposed a route recommendation system
which is not based on the shortest distance, but on the potential
enjoyment quality within the route [
The data
heart rate data
To help determine the appropriate exertion load, the user’s
target heart rate is calculated [
Implementation of the walking route recommendation
system
Estimating the walking speed based on age and gender
When using the system, the users would input how long they
wish to walk (their desired walking duration). To be able to
accurately determine the length of the recommended route, it
is necessary to estimate the potential walking speed of each
user. Information about the age and gender of the users is used
to help determine the walking speed. The average walking
speed of people when they walk around indeterminately could
be found at [
Route recommendation through Dijkstra’s algorithm Traditional walking navigation systems calculate the shortest route between the starting point and target destination using Dijkstra’s algorithm. In this study, in addition to the walking distance, we would also take into account the perceived rate of exertion, the presence of potentially dangerous areas as well as the availability of scenic locations.
Initially, the proposed system randomly selects multiple candidate sites based on the target walking distance. The inclination data and information about possible dangerous and scenic locations are obtained for the points on the shortest route to the candidate sites (calculated using Dijkstra’s algorithm). Afterwards, the system recommends routes by considering the perceived exertion load and the possibility of passing through safe and scenic locations.
For example, if a walking distance of 800 meters is required, multiple points from within the edge of the approximately 800 meter circular radius range are selected and the shortest route from the starting spot to these points are calculated using the Dijkstra’s algorithm. When the desired walking distance is reached, the points are then made into candidate sites. See Figure 2 for an example of the routes proposed by the system. After the candidate sites have been obtained, data about the inclination would be acquired for the points on the routes to the candidate sites and used to investigate the physical exertion load based on the targeted heart rate of the user. In the future, the heart rate data would be used to help predict the level of perceived exertion on different routes. Geo-tagged tweets were also obtained for the points on the route. In regards to the tweets, in the current system, the number of tweets were used as an indicator of the popularity of the location, regardless of whether they were positive or negative in nature. In the future, we would look into using sentiment analysis to separate the negative locations from the positive ones. Overall, both data related to the inclination and the tweets would be displayed for the routes to the candidate sites.
To test the feasibility of the currently proposed system, an experiment study was carried out. The main aim was to determine whether the perceived exertion load of the user is influenced by the inclination within the route and whether geo-tagged tweets could be a good indicator of the enjoyment within the route.
FEASIBILITY STUDY OF THE ROUTE RECOMMENDATION SYSTEM An experiment study was carried out to test the feasibility of the proposed method. Figure 2, shows an example of 8 different waking navigation routes recommended by the method proposed in the paper. The targeted walking distance (from the start location "S" to the points G1 to G8) is around 800m.
To test the feasibility of the recommendation method, three participants were asked to walk through the routes recommended by the system. Overall, the routes to the destinations G2 and G4 were selected as they had a large difference in tweet numbers but were similar in terms of changes to the level of inclination. In addition,the routes to the destinations G1 and G3 were also selected as they were similar in terms of tweet numbers but had large difference in inclination change. Participants wore a smart watch which measured their heart rate as they walked through the route. In addition, participants were also asked to rate their experience while walking the route. They were asked to rate three factors 1) how easy they felt the route was 2) how enjoyable was the route and 3) whether they would like to walk on the route again on a 7 point Likert scale.
The results are shown in table 3. As expected, the average heart rate of participants increased substantially for routes with high upper elevation (G1). In addition, participants felt it was easier to walk on routes with a low combined upper elevation (G2 and G3) than those with a high combined upper elevation (G1 and G4). Thus, the results suggest that the level of inclination change within a route could be a good indicator of the perceived exertion of users on that route.
The influence of the number of tweets on user enjoyment and
motivation was less clear. There seems to be a trend in that
for routes with a high number of tweets, the reported level of
enjoyment and motivation seems to be higher than routes with
a lower number of tweets (i.e. G1 being higher than G2 and
G3 and G4 being higher than G3). Overall, the system could
be further refined by using methods such as sentiment analysis
to analyze the tweets in more detail, using a method similar to
[
Route
G1 G2 G3 G4 SUMMARY In this paper, we have proposed a smart walking navigation system which recommends a walking route that takes into account the perceived exertion load (based on the walking duration, heart rate and inclination etc.), the possibility of avoiding dangerous locations and the ability to pass through highly rated scenic and popular locations. The overall aim of the system is to provide a walking experience which is enjoyable, safe and beneficial to the physical health of the user. We have described how such a system could be implemented. In addition, we have provided the results of an experiment study carried out to test the feasibility of the proposed method, showing how the routes suggested by the system could influence the level of perceived exertion for users. In the future, we aim to refine the proposed method by using sentiment analysis to analyze the tweets and determine the scenic and dangerous locations within the route. In addition, we would also examine a more personalized approach towards recommending the appropriate walking distance for each user based on their physical abilities and health conditions (i.e. by using information from smart watches which can collect health related data to infer the physical ability of users etc.).