ISO/TR 19167:2019

TECHNICAL ISO/TR
REPORT 19167
First edition
2019-12
Application of ubiquitous public
access to-geographic information to
an air quality information service
Reference number
©
ISO 2019
© ISO 2019
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of this publication may
be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting
on the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address
below or ISO’s member body in the country of the requester.
ISO copyright office
CP 401 • Ch. de Blandonnet 8
CH-1214 Vernier, Geneva
Phone: +41 22 749 01 11
Fax: +41 22 749 09 47
Email: copyright@iso.org
Website: www.iso.org
Published in Switzerland
ii © ISO 2019 – All rights reserved

Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Abbreviated terms and symbols . 3
5 UPA-to-GI environment for air quality information . 3
5.1 Overview . 3
5.2 Main components . 4
5.2.1 Air quality observation system. 4
5.2.2 Air quality information system . 4
5.2.3 Users . 4
5.3 Air quality index . 5
5.4 Use case diagram . 6
6 UPA context information model in ISO 19154 . 7
6.1 Overview . 7
6.2 UPA location context package . 7
6.3 UPA geospatial context package . 8
6.4 UPA geosemantic context package . 8
7 Air quality context information model . 8
7.1 Overview . 8
7.2 Locational air quality context information model . 9
7.3 Geospatial air quality context information model.11
7.4 Geosemantic air quality context information model.13
8 Implementation of the air quality context information model .14
8.1 Overview .14
8.2 Air quality information system components .15
8.3 Air quality information service .16
9 Conclusions .18
Annex A (informative) Investigation of global air quality information .19
Annex B (informative) Relation between this document and ISO 19154 .22
Bibliography .27
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www .iso .org/ directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www .iso .org/ patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and
expressions related to conformity assessment, as well as information about ISO's adherence to the
World Trade Organization (WTO) principles in the Technical Barriers to Trade (TBT) see www .iso .org/
iso/ foreword .html.
This document was prepared by Technical Committee ISO/TC 211, Geographic information/Geomatics.
Any feedback or questions on this document should be directed to the user’s national standards body. A
complete listing of these bodies can be found at www .iso .org/ members .html.
iv © ISO 2019 – All rights reserved

Introduction
Rapid urbanization and industrialization have led to a severe deterioration in the atmospheric
[1][2]
environments of major cities . Air pollutants, which include both naturally occurring and
anthropogenic substances, are associated with illness and mortality in humans, and with damage to
[3]
natural and built environments . However, despite the dedicated actions over the past decades of
both international and national organizations to decrease major pollutant emissions, urban air quality
[4]
continues to worsen, affecting residential environments and harming the health of citizens .
Information communication technology (ICT) has contributed to addressing the challenges of
improving urban air quality. Sensor networks provide a powerful tool for monitoring air quality in real-
[5][6]
time through widely dispersed monitoring stations . Portable air pollution sensors, combined with
the Global Navigation Satellite System (GNSS) technology, supplement an existing sensor network with
[7][8]
enhanced availability and accessibility for monitoring air quality in near real-time . Also, spatial
data infrastructure (SDI) is established for integrated and interoperable management of air pollutant
measurements at national and international levels. For example, INSPIRE, which is the European SDI
based upon ISO 19156, defines a framework to access, share, and use air quality data from member
[9]
countries . The air quality information platform is a bridge between the sensor systems and the
citizens. Both web- and mobile-based applications, highly coupled to geographic information systems
(GIS), enable citizens to easily obtain air quality information services without spatial or temporal
limitations.
As public awareness of urban atmospheric problems has risen, air pollution now has become both an
environmental and social problem. Citizens are also encouraged to participate in air quality assessment
[10]
and environmental governance . These societal and technical changes require a new paradigm to
develop an air quality information system and their services. Different from conventional air quality
information systems, citizens are no longer only consumers of air quality information, but rather
producers of air quality information. For example, a social media service such as a blog, Twitter, and
Facebook are now major communication channels for expressing the concern of citizens about urban
air quality issues. Social media technology platforms are now regarded as "social sensors" collecting
[11][12]
citizens’ perceptions of air quality .
In this document, an air quality information system was developed, referencing ISO 19154. The
ubiquitous public access to geographic information (UPA-to-GI) is a geographic information service
for the general public to easily access and produce geographic data or information in a ubiquitous
computing environment. In this system, the UPA context information model defined in ISO 19154 is
employed to systematically associate air quality data from various information sources (e.g. physical
sensor measurements, subjective citizen's opinions, and semantic social media data). The UPA context
information model is also used to formulate air quality information services, conforming to the citizen's
contextual requests.
This document aims to assist the understating of the UPA context information model and to illustrate
its application for air quality information services. In this regard, a proof of concept (POC) study was
conducted in Seoul, South Korea. The GIS-based air quality information system was designed and
implemented to realize a UPA-based air quality information service. Globally, there are widely different
approaches to monitor and report air quality. The UPA-based air quality information service model,
described in this document, is a sample of all possible examples. However, the underlying idea and
concept for designing and implementing the UPA context information model is still helpful to develop
other UPA-based air quality information services, conforming to the unique atmospheric and social
environments in each nation.
TECHNICAL REPORT ISO/TR 19167:2019(E)
Application of ubiquitous public access to-geographic
information to an air quality information service
1 Scope
This document facilitates an understanding of the Ubiquitous Public Access (UPA) context information
model, as defined in ISO 19154, to establish a UPA-to-Geographic Information (GI) environment.
In addition, this document illustrates how the UPA context information model is designed and
implemented to provide an air quality information service from a geographic information system (GIS)-
based air quality information system. The UPA context information model for air quality information
is only a sample of all possible examples to realize the UPA-to-GI that could satisfy the requirements of
ISO 19154.
2 Normative references
There are no normative references in this document.
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
ISO and IEC maintain terminological databases for use in standardization at the following addresses:
— IEC Electropedia: available at http:// www .electropedia .org/
— ISO Online browsing platform: available at https:// www .iso .org/ obp
3.1
air pollutant
material emitted into the atmosphere either by human activity or natural processes and adversely
affecting humans or the environment
[SOURCE: ISO 18158:2016, 2.1.2.1]
3.2
application
manipulation and processing of data in support of user requirements
[SOURCE: ISO 19101-1, 4.1.1]
3.3
context
aspects or properties of an entity that affect the behaviour or expectations of that entity in any given
situation
[SOURCE: ISO 19154:2014, 4.4]
3.4
comprehensive air-quality index
CAI
description of the ambient air qualities based on the health risk of air pollution
EXAMPLE The higher CAI values, the greater the level of air pollution.
Note 1 to entry: The index aims to make the public easily understand how polluted overall air quality currently is
or how polluted it is forecast to become.
3.5
geographic context awareness
application (3.2) or service (3.12) behaviour based on the recognition of user’s geographic context (3.3)
[SOURCE: ISO 19154:2014, 4.7]
3.6
geographic information
information concerning phenomena implicitly or explicitly associated with a location relative to the Earth
[SOURCE: ISO 19101-1, 4.1.18]
3.7
geographic information service
service (3.12) that transforms, manages, or presents geographic information to users
[SOURCE: ISO 19101-1, 4.1.19]
3.8
geographic information system
GIS
information system dealing with information concerning phenomena associated with location relative
to the Earth
[SOURCE: ISO 19101-1, 4.1.20]
3.9
interface
named set of operations (3.10) that characterize the behaviour of an entity
[SOURCE: ISO 19119:2016, 4.1.8, modified — Note 1 to entry was deleted.]
3.10
operation
specification of a transformation or query that an object may be called to execute
[SOURCE: ISO 19119:2016, 4.1.10, modified — Notes 1 and 2 to entry were deleted.]
3.11
public access
open access to information sources and/or services (3.12) by general public users and professional
users alike
[SOURCE: ISO 19154:2014, 4.18]
3.12
service
distinct part of the functionality that is provided by an entity through interfaces (3.9)
[SOURCE: ISO 19119:2016, 4.1.12]
3.13
ubiquitous public access
UPA
service (3.12) that enables end-users to have easy and interoperable access to specific types of data,
irrespective of their location or access device, and that match their interest criteria
EXAMPLE Linked Geodata Service.
2 © ISO 2019 – All rights reserved

Note 1 to entry: In the example, the Linked GeoData Service is responsible for openly inter-connecting geographic
information to external repositories or web resources using a transform to either Resource Description
Framework (RDF) or Web Ontology Language (OWL) format.
[SOURCE: ISO 19154:2014, 4.25]
4 Abbreviated terms and symbols
AQI Air Quality Index
AQMA Air Quality Mobile Application
AQODP Air Quality Open Data Platform
AQSDP Air Quality Social Media Data Platform
CAI Comprehensive Air Quality Index
CO Carbon Monoxide
CO Carbon Dioxide
GIS Geographic Information System
GNSS Global Navigation Satellite System
ICT Information Communication Technology
NO Nitrogen Dioxide
0 Ozone
PM Particle Matter
SDI Spatial Data Infrastructure
SO Sulphur Dioxide
UPA Ubiquitous Public Access
UPA-to-GI Ubiquitous Public Access to Geographic Information
WFS Web Feature Service
WMS Web Map Service
5 UPA-to-GI environment for air quality information
5.1 Overview
ISO 19154 is a relatively new International Standard from ISO/TC 211, Geographic information/
Geomatics, that defines the reference architecture to realize UPA-to-GI environments. The UPA-to-GI
environment aims to enable the general user to have easy and seamless access to geographic data and
services regardless of their locations and computing devices. Also, the user is no longer just a recipient
of geographic information, but also a producer of geographic information. To realize the UPA-to-GI
environment, the UPA context information model, which is defined in ISO 19154, gathers and manages
geographic context information from varied data sources including the user. Within the interactions
between each user and an information system, the context information model is used to characterize a
user’s situation in relation with geographic information. Thus, the user can access information meeting
their needs in a convenient and interoperable manner. In this document, the high-level design of an air
quality information system for the user to easily access air quality in real-time, and to contribute to air
quality monitoring data for participating in societal environmental decision making is presented.
5.2 Main components
The air quality information system is built using UPA-to-GI concepts, as shown in Figure 1 and is
composed of three fundamental main components:
a) air quality observation system (5.2.1),
b) air quality information platform (5.2.2), and
c) users (5.2.3)
5.2.1 Air quality observation system
The application of ICT to a variety of air quality observation systems has contributed to resolving global
air quality challenges. Air quality monitoring stations, connected in sensor networks, directly monitor
air pollutants (PM, O , NO , CO and SO ) and obtain real-time data from widely dispersed locations. The
3 2 2
Air Quality Open Data Platform (AQODP) stores and checks the quality of the data from the monitoring
stations. The Air Quality Social Media Data Platform (AQSDP) is another channel to detect air quality
issues from events occurring in real-time and reported within social media. The social media data,
which social media users share with the public, describes any events or news that influence urban
air quality such as a building fire or factory explosion. Furthermore, as public awareness of urban
environmental problems has increased, Air Quality Mobile Application (AQMA) running on mobile
devices can provide a mechanism for citizens to express their concerns about local air quality issues.
The perceptions from the citizens, when combined with air quality data from air quality monitoring
stations, will better enable local authorities to shape policies for improving urban air quality.
5.2.2 Air quality information system
In the UPA-to-GI environment, the air quality information platform is a bridge between heterogeneous
air quality observation systems and end users. Air quality data from the observation systems are
transmitted to the data hub of the platform, where the context information model employs geographic
information to define how air quality data are structured and maintained. At the same time, the air
quality information is explicitly or implicitly associated with user's contexts. The air quality information
services, which consist of air quality information and action tips, are then created according to the
user's location, time, and health status. The air quality platform is a basis for developing both web and
mobile applications that enable users to easily access air quality information services irrespective of
their locations or devices. These applications also allow users to produce air quality data based on their
perceptions and opinions, which are submitted to the air quality information platform, as contributed
social data.
5.2.3 Users
The main users of the air quality information system are citizens or local authorities. Local authorities
will use the air quality information services for policy or operational decision making. For example,
the air quality information platform provides locational air quality statistics along with citizens’
perceptions of air quality. These data provide a reference by which to recognize knowledge and
communication gaps between the citizens and policy makers. The web and mobile applications also
convey air quality information services to citizens, allowing them to represent their opinions visually
through an easy to understand graphic interface with icons and colours. Citizens can use the services
when planning outdoor activities and decisions on where to live or relocate.
4 © ISO 2019 – All rights reserved

Figure 1 — Main components in UPA-GI based air quality information
5.3 Air quality index
In the UPA-to-GI environment for air quality information, the air quality information platform collects
air quality data from the air quality observation systems. The air quality contexts are than extracted
and associated with contexts from users to provide relevant air quality information services. The
air pollutant measures obtained from the air quality monitoring station are simply numerical data,
therefore they are converted into a region-appropriate Air Quality Index (AQI) scheme to help citizens
more easily understand air quality levels and to protect their health during episodes of severe air
pollution. AQI indicates an overall air quality derived from all air pollutant measurements, as shown in
Table 1. The health implications corresponding to index categories are shown in Table 2.
Different countries employ specific air quality indices, corresponding to their respective national air
quality standards. This document presents examples using the Comprehensive Air Quality Index (CAI)
[13]
and behavioural guidelines established for use in the Republic of Korea .
Table 1 — Comprehensive air-quality index (CAI)
Very Unhealthy
Pollutant Good Moderate Unhealthy
I II
CAI 0~50 51~100 101~250 251~350 351~500
PM (μg/m ) 0~15 16~50 51~100 101~250 251~500
2.5
PM (μg/m ) 0~30 31~80 81~150 151~300 301~600
O (ppm) 0~0,030 0,031~0,090 0,091~0,150 0,151~0,500 0,501~0,600
NO (ppm) 0~0,030 0,031~0,060 0,061~0,200 0,201~0,600 0,601~2,000
CO (ppm) 0~2,000 2,001~9,000 9,001~15,000 15,001~30,000 30,000~50,000
Table 1 (continued)
Very Unhealthy
Pollutant Good Moderate Unhealthy
I II
SO (ppm) 0~0,020 0,021~0,050 0,051~0,151 0,151~0,400 0,401~1,000
Table 2 — Health implications
Index Description
Good A level that will not impact patients suffering from diseases related to air pollution.
Moderate A level that may have a minor effect on patients in case of chronic exposure.
A level that may have harmful impacts on patients and members of sensitive groups
Unhealthy (children, elderly, or infirm people), and may cause unpleasant feelings among the
general population.
A level that may have serious impacts on patients and members of sensitive groups
Very Unhealthy I
in case of acute exposure.
A level that may require emergency measures for patients and members of sensitive
Very Unhealthy II
groups, and may have harmful impacts on the general population.
5.4 Use case diagram
The following use cases depicted in Figure 2 consist of a series of actions defining the interactions
between the main stakeholders, either citizens or local authorities. The citizens are further categorized
based on their potential health risk due to air quality, such as a sensitive or high-risk group such as
the young and elderly people, or citizens with respiratory or cardiovascular issues. The context
information, which is required for all users, consists of age, health status, geographical regions of
interest, and current location. This information is transmitted to the air quality information platform
through the “Register User Information” case. The user is then categorized as part of the “General
Group” or “Sensitive Group,” based on analysis of their context information.
The air quality observation system includes AQODP and AQSDP. Additionally, the “Input Citizen Opinion”
case in AQMA delivers a citizen's perceptions of air quality relevant to their current location, and can
present their concerns about the air quality using a categorized icon. The “Show Citizens Opinion”
case employs an urban map to spatially represent the perceptual concerns registered by the citizens,
regarding local air quality issues. Local authorities can use the knowledge and perceptive experience
submitted directly from the citizens when establishing new air quality policies.
In AQMA, the “Receive Location-based Real-Time Air Quality Information” case provides estimated air
quality information for a user’s current location when the GNSS on a mobile device is activated. The
“Receive Regional Air Quality Information of Interest” case retrieves regional air quality when users
register a geographical region of interest. The “Receive Forecast of Air Quality Information” retrieves
an air quality forecast for the following day. The use case of “Receive Warning Message and Action
Tip” issues warning messages and action tips, considering the user’s contexts from the “Register User
Information” case. The warning message is issued when AQI exceeds the level of health concern or when
a user’s location is near an air quality event. The action tip is a behavioural guideline to propose what
actions the citizens should take to protect their health against each air pollutant incident.
The “Receive Regional Air Quality Statistics” case involves current and past air quality data from
AQODP, and computes daily, monthly, and yearly averages for each region of a city. Citizens can refer to
these statistics when deciding on where to relocate or reside for long-term health recovery purposes,
whereas policy makers can use such data to judge the effectiveness of the existing air quality policies.
6 © ISO 2019 – All rights reserved

Figure 2 — Use case diagram for UPA service
6 UPA context information model in ISO 19154
6.1 Overview
In ISO 19154, the UPA context information model is conceptually specified for an information system
to support the UPA-to-GI. The UPA context information model is based upon seamless mobility and
geographic context. The geographic context, which is the entity’s contexts in relation to geographic
information, includes an entity’s location, speed, and orientation, and other relevant static location data
such as nearby restaurants and hospitals or dynamic data such as traffic and weather conditions. The
geographic context enables an information system to provide a set of tailored geographic information
artefacts, satisfying an entity’s contextual requirements. However, as geographic information can be
represented in various forms, the UPA context information model, as shown in Figure 3, defines three
different context levels of geographic information:
a) UPA locational (6.2),
b) UPA geospatial (6.3), and
c) UPA geosemantic contexts (6.4).
6.2 UPA location context package
The UPA locational context package identifies types of location that are representative of an entity (e.g.
vehicle’s geographic coordinate measure from GNSS) and defines rules for extracting relevant contexts
from the location information of the entity (e.g. vehicle’s speed and orientation).
6.3 UPA geospatial context package
In the UPA geospatial context package, the locational entity is allocated the geospatial representation
type inferred by its locational contexts (e.g. a vehicle represented as a point feature on a roadway map).
The geospatial rule is used to retrieve relevant contexts from the entity’s geospatial information (e.g.
shortest route and travel distance computed along with a roadway map).
6.4 UPA geosemantic context package
The geosemantic context package, which is inherited from the location context package, employs the
geospatial entity to explicitly represent the implicit expression of the locational context of the entity.
The geosemantic type and a set of rules are used for geographical extraction and inference of relevant
context from the locational contexts of the entity (e.g. a location of vehicle’s accident inferred from news).
Figure 3 — Geographic context information model in ISO 19154
7 Air quality context information model
7.1 Overview
In this document, the air quality context information model refers to the UPA context information model
from ISO 19154, as shown in Figure 4. The air quality context information model, as shown in Figure 5,
primarily involves air quality data from the air quality observation systems that consists of the AQODP,
AQSDP, and AQMA. In particular, AQMA running on a smart phone is utilized for users to access an air
quality information as well as to provide their perceptions of air quality as social data.
In the UPA-to-GI service module, the air quality context information model is used to structure and
maintain air quality information from the air quality observation systems. The air quality context
information model is further categorized into locational, geospatial, and geosemantic context
information models. In Figure 5, the geographic context awareness is a function of the recognition of
a user’s contexts in relation to the air quality information, from which spatially relevant air quality
information services can be formulated, depending on the user’s locations, time, and health conditions.
The air quality information service includes real-time air quality information, the air quality forecasts,
air quality statistics, warning messages, action tips, and citizens’ opinions on air quality.
8 © ISO 2019 – All rights reserved

Figure 4 — Dependency of air quality context information model on UPA geographic context
information model in ISO 19154
Figure 5 — Information flow for UPA-to-GI based air quality information services
7.2 Locational air quality context information model
The locational air quality context information model as shown in Figure 6 is a set of classes inferred
from the UPA_LocationContext class (Figure 3). The air quality context classes are designed for the
users who use AQMA, the air quality monitoring stations that provide air quality data to AQODP, and the
air quality event detected from AQSDP (Tables 3, 4, and 5). These classes are associated to retrieve and
infer locational contexts from users, air quality monitoring stations, and air quality events (Table 6).
Figure 6 — Locational air quality context information model
AQMA requires all users to register information such as their age and health status, along with specific
regions of interest. Based on the registered information, the users are categorized as belonging to the
general group or a sensitive group (e.g. the young, elderly, and those with respiratory/cardiovascular
issues), based on their age and health status. The GNSS on a mobile device provides a means to identify
users’ locations. The set of classes, which describes users’ locational air quality context, is shown in
Table 3 and within the solid line in Figure 6.
Table 3 — Locational air quality context classes for users
Class name General description
Defines user contexts according to age, health status (e.g. the young,
Locational_User_AirQualityContext elderly, and those with respiratory/cardiovascular issues), and
region of interest (e.g. home and company addresses).
Determines a user type (general or sensitive group) according to
Locational_User_AirQuality_ContextRule
the user’s information (e.g. age and health status).
Locational_User_ContextElement, Defines a way of retrieving a user’s location.
Contains the geographic coordinates of the user’s current location,
UserLocation_byGNSS
obtained via GNSS directly from a mobile device.
The relevant locational and air quality contexts of an air quality monitoring station can be retrieved
from AQODP. A unique identity (ID) assigned to each air quality monitoring station is fundamental
to collecting locational information (geographic coordinates and address), real-time air quality
data (PM, CO, O , NO , and SO ), and air quality forecasts. In addition, the air quality statistics allow
3 2 2
comprehensive analyses of air qualities at the air quality monitoring station. The set of classes, which
describes the locational air quality contexts of an air quality monitoring station, are shown in Table 4
and within the dotted line in Figure 6.
10 © ISO 2019 – All rights reserved

Table 4 — Locational air quality context classes for air quality monitoring station
Class name General description
Defines contexts of an air quality monitoring station with ID,
station name, past and real-time air quality data (PM, CO, O ,
Locational_Station_AirQualityContext
NO , and SO ), and air quality forecasts. This information is
2 2
retrieved from AQODP.
Locational_Station_AirQuality_ContextRule Computes the air quality statistics.
Locational_Station_ContextElement, Defines a way of retrieving a station’s location.
Contains the geographic coordinates of the air quality moni-
StationLocation_byID toring station. The station ID is used to retrieve its geographic
coordinates from AQODP.
Contains the address of the air quality monitoring station. The
StationAddress_byID
station ID is used to retrieve its address from AQODP.
Social media data, which are transmitted from AQSDP, is used to contain implicit information regarding
air quality events (e.g. a forest wildfire on South Mountain, Seoul). Thus, the air pollutants, which
vary in response to air quality events, are then inferred. For example, a forest wildfire can be a source
of increased PM and CO pollution around the event location. The set of classes, which describes the
locational contexts of air quality events, is shown in Table 5 and within the dashed line in Figure 6.
Table 5 — Locational air quality context classes for air quality events
Class name General description
Utilizes AQSDP to define the contexts of an air quality
Locational_Event_AirQualityContext event (ID, date and time, and the location and type of air
quality event).
Infers which air pollutants might be influenced, based on
Locational_Event_AirQuality_ContextRule
the type of air quality event.
Defines a way of retrieving the air quality event location
Locational_Event_ContextElement
from the social media data.
Contains an implicit expression of the air quality event
EventLocation_bySocialMediaData
location.
The locational air quality context is inferred by associating locational air quality contexts from users,
air quality monitoring stations, and air quality events. The inference rule identifies the air quality
monitoring station within the user’s region of interest, subsequently retrieving real-time (or forecasted)
air quality information for that region. The Locational_AirQuality_ContextRule class, described in
Table 6, is shown in Figure 6.
Table 6 — Locational air quality context classes for user, air quality monitoring station, and air
quality event
Class name General description
Associates contexts from user, air quality monitoring station, and air
Locational_AirQuality_ContextRule quality event, and infers comprehensive air quality contexts (e.g. air
quality information and statistics from the user’s region of interest).
7.3 Geospatial air quality context information model
The geospatial air quality context information model in Figure 7, which is a set of classes inferred from
the type UPA_GeospatialContext in Figure 3, refers to the geospatial context classes for a user and an
air quality monitoring station (Tables 7 and 8). These are associated to retrieve and infer geospatial
contexts from the user and the air quality monitoring station (Table 9).
Figure 7 — Geospatial air quality context information model
A user’s geospatial context is represented as a point feature in the air quality information system. The
user’s current address is determined using appropriate geocoding methods, enabling a user to rate the
air quality at their current locations. The rating submitted by the user is reformatted and added to the
air quality information system to subjectively represent how the user feels about the air qualities in
comparison with the air quality data from the monitoring station. The set of classes, which describes
the geospatial contexts of a user, is shown in Table 7 and within the dotted line in Figure 7.
Table 7 — Geospatial air quality context classes for users
Class name General description
Represents the user as a point feature, as inferred from the
locational air quality context information model. The user’s
Geospatial_UserPoint_AirQualityContext
opinion on air quality at their current location becomes the
user’s context.
Defines a rule for inferring geospatial air quality contexts.
The rule defines the geocoding method to obtain a user’s
Geospatial_UserPoint_AirQuality_ContextRule
address at the current location, and the buffering method to
retrieve the locations of nearby hospitals.
The geospatial contexts of the air quality monitoring station are represented as point and polygon
features in the air quality information system. In this document, an air quality monitoring station is
installed in each region of the city. As air quality data from each station are representative of each
region, the air quality data are coded to a polygon feature that depicts the administrative boundary
of the region. The set of classes, which describes the geospatial contexts of an air quality monitoring
station, is shown in Table 8 and within the dashed line in Figure 7.
Table 8 — Geospatial air quality context classes for air quality monitoring stations
Class name General description
Represents the air quality monitoring station as a point
Geospatial_StationPoint_AirQualityContext feature, as inferred from the locational air quality con-
texts for the air quality monitoring station.
Represents the air quality monitoring station as a pol-
Geospatial_StationPolygon_AirQualityContext ygon feature, as inferred from the locational air quality
contexts for the air quality monitoring station.
12 © ISO 2019 – All rights reserved

Table 8 (continued)
Class name General description
Defines a rule for inferring geospatial air quality contexts,
Geospatial_StationPolygon_AirQuality_ContextRule
which assigns air quality data to the polygon features.
The geospatial air quality contexts are inferred by retrieving and associating the geospatial contexts
from the user and the air quality monitoring station. The air quality conditions at the user’s current
location can be established via geospatial operations that interpolate air quality values using data from
nearby air quality monitoring stations. The Geospatial_AirQuality_ContextRule class is described in
Table 9 and shown in Figure 7.
Table 9 — Geospatial air quality context classes for user and air quality monitoring station
Class name General description
Defines a rule for inferring geospatial air quality contexts
from a user's location and nearby air quality monitor-
ing stations. The rule includes geospatial operations
to identify and obtain air quality data from nearby air
Geospatial_AirQuality_ContextRule
quality monitoring stations. Interpolation methods such
as Kriging and Inverse Distance Weighting (IDW) are
then applied to infer the air quality data at the user’s
current location.
7.4 Geosemantic air quality context information model
The geosemantic air quality context information model in Figure 8, which is a set of classes inferred
from the type UPA_GeosematicContext in Figure 3, describes the geosemantic context classes of an air
quality event detected from AQSDP (Table 10). The geosemantic air quality contexts are inferred by
retrieving and associating the geosemantic contexts of the air quality event with a user’s geospatial
context (Table 11).
Figure 8 — Geosemantic air quality context information model
Within the air quality information system, the location of the air quality event, which is implicitly
expressed in the social media data, is explicitly represented as a polygon feature. For example, if an
air quality event implicitly refers to a fire event in “Dongdaemun-Gu” (a regional district in Seoul), a
regional polygon of “Dongdaemun-Gu” would be used to indicate the possible location of the fire event.
The polygon feature represents the area of a source of air pollution (potentially generating PM and CO,
etc.). Meanwhile, the zone affected by the air pollution is determined via the types of air pollutants
inferred from the air quality event. The set of classes, which describes the geosemantic contexts of an
air quality event, is shown in Table 10 and within the dotted line in Figure 8.
Table 10 — Geosemantic air quality context classes for air quality events
Class name General description
Represents an air quality event as a polygon feature,
Geosemantic_EventPolygon_AirQualityContext as inferred from the locational context information
model for the social media data.
Defines a rule for inferring geosemantic air quality
Geosemantic_Event_AirQuality_ContextRule contexts. The rule includes methods to determine the
zone affected by air pollution from the air quality event.
The geosemantic air qualities are inferred by
...