Lost Silence: An emergency response early
detection service through continuous processing
of telecommunication data streams
Qianru Zhou1 , Stephen McLaughlin1 , Alasdair J. G. Gray2 , Shangbin Wu3 ,
and Chengxiang Wang1
1
School of Engineering & Physical Sciences, Heriot-Watt University, EH14 4AS, UK
2
Department of Computer Science, Heriot-Watt University, EH14 4AS, UK
3
Samsung R&D Institute UK, Staines-upon-Thames, TW18 4QE, UK
Abstract. Early detection of significant traumatic events, e.g. a ter-
rorist attack or a ship capsizing, is important to ensure that a prompt
emergency response can occur. In the modern world telecommunication
systems could play a key role in ensuring a successful emergency response
by detecting such incidents through significant changes in calls and ac-
cess to the networks. In this paper a methodology is illustrated to detect
such incidents immediately (with the delay in the order of milliseconds),
by processing semantically annotated streams of data in cellular telecom-
munication systems. In our methodology, live information about the po-
sition and status of phones are encoded as RDF streams. We propose an
algorithm that processes streams of RDF annotated telecommunication
data to detect abnormality. Our approach is exemplified in the context
of a passenger cruise ship capsizing. However, the approach is readily
translatable to other incidents. Our evaluation results show that with a
properly chosen window size, such incidents can be detected efficiently
and effectively.
Keywords: telecommunications, event detection, emergency response,
C-SPARQL
1 Introduction
At 21:30 on 1st June, 2015, the cruise ship “Eastern Star” traveling on the
Yangtze River began to list as a consequence of stormy weather. One minute
later, the ship capsized with 458 passengers and crew on board. No distress signal
was sent. It was several hours before the emergency services became aware of the
tragedy and 442 lives were lost [1]. Although considerable effort has been devoted
to the emergency response to natural and man-made disasters, the fatalities and
economic cost due to untimely rescue are still significant [2, 3]. In 2016 alone,
225,665 refugees arrived in Europe by sea, and approximately 2,933 lost their
lives due to ship capsizing accidents during illegal migration [2]. Most of the
capsizes were not noticed until the survivors swam to shore.
2 Zhou et al.
When a ship capsizes and is incapable of communication by radio, is there
any way to detect the ship capsizing as soon as it happens? In a telecommu-
nication system, the location and status information of a phone are stored in
the service providers’ databases (the specific name of the databases are visiting
location register, VLR, and home location register, HLR). When a cell phone
is switched off normally (e.g., by pressing power button, or batteries wearing
out), it will register its status as “detached” to the database. However, if a de-
vice is forcefully shut down (e.g., dropped into the water, physically damaged,
or the battery removed), or it enters a blind spot with no signal coverage, it
does not have time to register its status [4]. Within a location update period
(this varies from 30 minutes to 1 hour, depending on the service provider), the
phone is marked as “unReachable” in the database. After that period, its sta-
tus will be changed to “Detached”, which is the same as in the situation of a
normal shutdown. These status signals can be used to infer abnormal events.
For example, a large number of phones losing signal abnormally at the same
time and location can be used as an indication of a significant event, potentially
catastrophic. Taking advantage of this fact, we present lost silence, an early de-
tection algorithm that can detect abnormalities. The location update process in
the telecommunication system generates large quantities of data in real time.
However, in current heterogenous telecommunication system, data from differ-
ent service providers adopt different local schemas. By annotating the data with
RDF/OWL vocabularies, we can present real time phone information as streams
of uniformly RDF encoded linked-data. The pattern is processed with continu-
ous SPARQL (C-SPARQL) queries [5, 6]. This lost silence service is a use case
for a large project, which aims at building a semantic intelligent knowledge base
for the current heterogenous telecommunication system, develop an technology-
independent interface, and identify various types of events with semantic web
technologies such as SPARQL and rules.
This paper is structured as follows. Section 2 presents our illustrative sce-
nario based on the “Eastern Star” shipwreck accident. Section 3 introduces some
technical background knowledge of telecommunication networks that are used in
our proposal. Section 4 presents the ontology we have adopted in our proposed
methodology. Section 5 gives details of the algorithms. The evaluation require-
ments, results and discussions based on our scenario are highlighted in Section 6.
Related work is presented in Section 7 and our conclusions are given in Section
8.
2 Motivating Scenario
We outline a scenario based on the cruise ship “Eastern Star” capsizing on the
Yangtze River, in Jianli, Hubei, China [1]. In addition to the Yangtze River, the
city of Jianli consists of two main parts, a densely populated zone – Rongcheng
town and a surrounding rural area – Hongcheng village. The detail of population
and geographic information is shown in Table. 1.
Lost Silence 3
Table 1. Geographic data of the city Jianli.
Town Area (km2 ) Population
Rongcheng Town 85 152, 358
Hongcheng Village 254 133, 544
Water Area 14.520 0
In a city with a busy telecommunication datacenter with high volumes of
phones (approx. 286,000 phones in the city covering an area of 373.520 km2 ), we
have evaluated the algorithm proposed in this paper against the time taken to
detect abnormalities, the accuracy of the detection. In particular, we have inves-
tigated the tradeoffs between the time taken in generating linked-data streams
for the massive amount of data in telecommunication system, and the accuracy
of the abnormalities detected.
It is possible that some situations would reduce the accuracy of the approach
described in this paper. For example, although the telecommunication service
providers are trying very hard to achieve full signal coverage, there are some
regions, especially in rural areas, that have no or limited signal coverage. These
areas are known as blind zones. If a large number of phones enter a blind zone,
then a large number of phone signals are lost at the same spot. Each service
provider keeps a list of its blind zones. Such false alarms could be avoided by a
simple comparison to the list before an alert is sent.
3 Background Technology
3.1 Stream processing
In the last few years, stream processing has gained a prominent attention in the
Semantic Web community [5–9]. The data in real telecommunication system, e.g.,
system log, SNMP polling, tcpdump, and configuration data, etc., are extremely
dynamic. The granularity of SNMP, Syslog and tcpdump update period is in
terms of a few seconds, one second and microseconds, respectively [10]. Thus,
there will be significant advantages to being able to manage rapidly changing
systems at the semantic level. The proposed lost silence application is powered
by the Continuous SPARQL (C-SPARQL) engine [6], an extension of SPARQL
with the ability to query streaming RDF data in real time.
3.2 The location register process in mobile telecommunication
networks
To ground our discussion, it is necessary to consider how the telecommunication
system maintains records of the location of a phone. In telecommunication net-
works, phones measure the channel environment and reselect cells every 200ms,
and report its location to the cell tower periodically. This period varies from
every 30 minutes to every hour, depending on the service providers [11]. When a
4 Zhou et al.
phone is turned off normally, it will deregister itself to the network system and
its status will be marked as “detached”. However, if a phone loses its power ab-
normally, it has no time to deregister. Thus its status in the network system will
be “unReachable”. After the update period, if the network still does not receive
update information from this phone, it will register the phone as “Detached”,
in the same manner as if it had been shut down normally [4, 11]. Thus, when a
phone loses signal abnormally, there is a limited time period to identify whether
it has been normally shut down or not. Typically this period is of the order of
30 minutes to an hour. The location information of a phone is sent and stored in
the telecommunication network servers (namely home location register, HLR or
visitor location register, VLR) located in the datacenter of the telecommunica-
tion system. Normally, there is one datacenter for one service provider per city,
managing the data of all the phones in the city. There are usually more than
one service provider in a city, and these service providers usually adopt different
schemas to represent the same data. In cases when public security is concerned,
some information is shared and uploaded to an authorized third party. For ex-
ample, in America, as enforced by the government, the location information of
every 911 call is automatically obtained and shown to the police [12].
3.3 Geo-Pixel
Lost silence needs to identify the spatial location where an abnormally high
number of phones lose their signals almost simultaneously. Key to the lost silence
algorithm is a uniformed spatial segmentation among the data. The current
spatial position representation, Universal Transverse Mercator (UTM), identifies
a location by dividing the earth into six zones, and applying a secant transverse
Mercator projection in each zone [13]. However, as the position information in
current telecommunication system is represented by traditional longitude and
latitude, a considerable amount of computation will be required to convert the
traditional position information into UTM. Thus, we propose the concept of Geo-
Pixel here. It is defined based on the third decimal degree of the latitude and
longitude coordination, with the resolution of 0.001◦ × 0.001◦ , or 100m × 100m.
Thus, with geo-pixel, phones are aggregated into grid cells based on location. The
main task of lost silence algorithm is to detect the geo-pixels with abnormally
high number of lost signal.
We made a simplification with regards to geo-pixel. At the equator, one third
decimal degree of longitude and latitude both cover about 100 meters. How-
ever, when moving toward the pole, the distance represented by one degree of
longitude degeneralize to zero, while the latitude stays almost the same, for the
distance resolution of longitude (east-west distance) depends on the latitude. For
example, the distance between one degree of longitude worth up to 111.320 km
when latitude is 0◦ , and reduces to only 28.920 km when latitude is 75◦ . How-
ever, most countries with significant mobile phone using populations lie between
75◦ to −75◦ latitude. Thus, the spatial resolution of geo-pixel varies between
100 m × 100 m to 100 m × 30 m, which does not have any impact on the algo-
Lost Silence 5
rithm except that making the result more accurate for some countries at high
latitudes.
Fig. 1. Classes of the TOUCON Ontology used in the Lost Silence scenario.
The solid block denotes a class, while the hollow block denotes a data. The
solid lines denote object properties, and dash lines denote datatype properties.
The prefixes adopted in lost silence are: net: ; core: ; geo: .
4 Ontology adopted in Lost Silence
To be able to transform telecommunication system data into RDF, we adopted an
ontology that models the raw data of the system. The ontology which is named
TOUCAN Ontology (TOCO) is developed for TOUCAN project4 . TOCO is
proposed to represent the knowledge within a heterogeneous telecommunication
system, consisting various technology domains, e.g., mobile network, computer
network, optical network, light fidelity (LiFi), and wireless fidelity (WiFi), etc.
TOCO is composed of one core ontology and 5 sub-ontologies, namely, network
resource, service, user, time, location. A diagram of the portion of the TOCO
class hierarchy adopted in lost silence is shown in Fig. 1.
Some important concepts and relations are presented below.
4
EPSRC TOUCAN project, No. EP/L020009/1. Website: http://gow.epsrc.ac.uk/
NGBOViewGrant.aspx?GrantRef=EP/L020009/1
6 Zhou et al.
“UserEquipment” - user equipments in mobile communication system, such
as phones, tablets, wearable facilities, etc. It has an object property hasStatus
with the object of class Status. It is defined in the network resource sub-
ontology.
“Point” - describes the location of phone, extended from SpatialThing of
the W3C WGS-84 vocabulary5 . It is defined in the location sub-ontology. It
has three datatype properties, namely, long, lat, and alt, describing the
longitude, latitude, and altitude of the phone.
“Status” - the status of UE connectivity in communication system. There are
three instances of this class, namely, Attached, Detached, and unReachable,
which denotes the phone is connected, detached after deregister to the sys-
tem, and unreachable without deregister to the system, respectively. It is
defined in the network resource sub-ontology. It is the range of the property
hasStatus of UserEquipment.
For example, to describe the fact that “a phone lost signal at location (329.860,
246.792)”, the corresponding triples are:
net:Phone 1 a net:UserEquipment.
pos:Point 1 a pos:Point.
net:Phone 1 pos:location pos:Point 1.
pos:Point 1 pos:latitude “329.860”.
pos:Point 1 pos:longitude “246.792”.
net:unReachable a net:Status.
net:Phone 1 net:hasStatus net:unReachable.
5 Algorithm
As the data volume from telecommunication system is extremely large, the phi-
losophy of divide-and-conquer is adopted in the algorithm design. In the data-
center of the telecommunication system, for our scenario more than 400 phones
lost their signal at the same location within seconds6 . This abnormality could
have been detected if continuous queries were being executed on the streams in
real-time. An alert could have been raised much earlier and help sent to those on
the ship. In the datacenter of the telecommunication system, every time a phone
updates its status, a linked-data event is generated and published as a collection
of triples. As the phones in the city keep updating their location information and
signal status, a linked-data stream is generated. In order to estimate the volume
and velocity of data variation from telecommunication system during accidents,
we referred to the literatures. The mobile phones penetration rate is 96.7% in
China, [14]. With the geo-pixel simplification, the number of geo-pixels and the
population density of phones in each town are shown in Table. 2. As a result, in
the city of Jianli, there are 29,215 geo-pixels, in which 7,024 of them are in the
densely populated zone with on average 21 phones per pixel, 20,991 pixels are
5
See http://www.w3.org/2003/01/geo/ for more detail.
6
By personal correspondence.
Lost Silence 7
in rural areas with on avaerage 6 phones per pixel, and on the river there are
1,200 pixels where the phone density is on average 0 phones per pixel.
Table 2. Phone density to geo-pixel in the city Jianli
Town Number of Geo-pixels Phone Density
Rongcheng Town 7024 21
Hongcheng Village 209911 6
Water Area 1200 0
REGISTER QUERY StreamingAndExternalStaticRdfGraph AS
PREFIX xsd:
PREFIX pos:
PREFIX net:
PREFIX fn:
SELECT (COUNT(?UE) AS ?counter) ?lat ?long
FROM STREAM [RANGE 30m STEP 5s]
WHERE {
?UE net:hasStatus net:unReachable.
?UE pos:location ?point.
?point pos:lat ?lat;
pos:long ?long.
BIND (fn:round(?lat * 1000) as ?roundLat)
BIND (fn:round(?long * 1000) as ?roundLong)
}
GROUP BY ?roundLat ?roundLong HAVING (?counter >10)
Listing 1.1. C-SPARQL query string for detecting the lost phones. Each non-empty
result in the returned result sets denotes an alert.
The C-SPARQL query string to detect lost phones is shown in Listing 1.1.
One C-SPARQL instance is generated for each geo-pixel. Thus, there are 29,215
C-SPARQL instances running in the experiment. With the massive data vol-
ume in telecommunication system and the heterogenous population density, it
is unrealistic to execute the query based on the arrival of new triples. Thus we
choose C-SPARQL, which supports a time step execution model. The query is
evaluated every 5 seconds calculating for each geo-pixel the count of unreach-
able devices over the last 30 minutes. A result is only returned if the count
is above 10. Each stream is denoted as in the query.
To avoid the omissions of accidents, we choose the window size the same as
the phone’s position update period in communication system – 30 minutes. We
adopt thread-per-geo-pixel architecture to process telecommunication data and
generate a RDF stream in one geo-pixel with one thread. The threads are main-
8 Zhou et al.
Algorithm 1 Stream Generator: Generate RDF streams for each given geo-
pixels.
// Input are the longitude and latitude of the city, ratio of phone lost signal, thread
sleep time. Output is the RDF stream created
Require: lat, long, lostRatio, sleepTime
Ensure: Stream
keepRunning ⇐ 1
while keepRunning do
Insert triple (net:Phone, geo:locateIn, geo:Point ) to Stream
Insert triple (geo:Point, geo:latitude, “lat”ˆˆxsd:double ) to Stream
Insert triple (geo:Point, geo:longitude, “long ”ˆˆxsd:double ) to Stream
With a ratio of lostRatio:
Insert triple (net:Phone, net:hasStatus, net:unReunReachableachable) to
Stream
With a ratio of(1 − lostRatio):
Insert triple (net:Phone, net:hasStatus, net:Attached) to Stream
Thread sleep for sleepTime seconds
end while
Algorithm 2 Thread Pool Scheduler: Schedule the C-SPARQL engine threads.
// Input is the number of geo-pixels for city center, rural area, and water zone.
Output is the tragedy detection results of the city
Require: CityNum, RuralNum, WaterNum
Ensure: Gstream
Instantiate a blocking queue: q
Instantiate a thread pool: pool
for each of the CityNum / RuralNum / WaterNum geo-pixels in the City /
Rural area / Water zone do
Create an Stream Generator as a thread into pool
Apply C-SPARQL query on the stream
end for
Shut down pool
Lost Silence 9
tained by a thread pool. Each thread in the pool has the same execution priority
and receives an equal share of CPU time.
The details of the generated streams and thread scheduling process are illus-
trated in an self-explanatory way in Algorithm 1 and 2 for brevity. Algorithm 1
shows the stream generating process for different areas. The lostRatio is adopted
to control the ratio of phones that lost signal in the simulated streams. For ex-
ample, if the lostRatio = 0.1, it means 10% of the phones in this stream will lose
signal, and if the lostRatio = 1, it denotes all the phones in this stream will lose
signal. The density of phones is determined by the sleepTime. For example, in the
rural area Hongcheng Village where the phone density is 6 phones per pixel, as
the location update period is 5 seconds (= 5000 milliseconds), in order to simu-
late the scenario that there are 6 phones signal update per 5 seconds, we have to
generate the RDF triples for one phone every 5000 ÷ 6 ≈ 833.333 milliseconds.
Thus, the sleepTime for rural area is 833 milliseconds. Similarly, the sleepTime
for Rongcheng Town is 5000 ÷ 21 ≈ 238 milliseconds.
6 Evaluation
We run an extensive and exhaustive evaluation based on the tragedy detection
algorithm. The evaluation was carried out on a MacBook Air OS X 10.9.5 with
3MB cache running on Intel Core i5 at 1.5 GHz. The system has 128 GB SSD
and 4 GB RAM.
6.1 Prepare the Data
A small number of phones will randomly disappear from random pixels along the
river. At a randomly chosen time, 424 phones will lose their signal simultaneously
in the geo-pixel (329.863, 246.792). With a query window of 30 minutes, we
experimented with query steps of 5, 20, and 30 seconds respectively. For the three
step sizes, we ran in total 3 iterations of the algorithm. Our evaluation for the
shipwreck scenario focus on two criteria: the time taken to detect abnormalities
and the accuracy of the detection, in terms of the cases of fail-to-report.
6.2 Experiment Framework
Fig. 2 shows our workflow and execution environment of the lost silence exper-
iment. Data from the telecommunication system in each geo-pixel is converted
into RDF streams by the Stream generator. RDF streams are accessed and
queries by the C-SPARQL engine thread. All the 29,215 query threads process-
ing 285,902 phone data are scheduled and executed by thread pool.
6.3 Evaluation Results
We run the experiment for three times, with the query steps of 5 seconds, 20
seconds, and 30 seconds, respectively. The simulation results are shown in Fig. 3.
10 Zhou et al.
Fig. 2. The Process of disaster early detection in lost silence.
The Fig. 3(a) and 3(b) are the simulation result with the query step of 5 seconds,
the Fig. 3(c) and 3(d) are with the query step of 20 seconds, and the Fig. 3(e)
and 3(f) 30 seconds. In the Fig. 3(a) 3(c), and 3(e) on the left, the horizontal
and vertical coordinates indicate the latitude and longitude of the geographical
area respectively. The total number of lost phones detected at each geo-pixel are
shown as circles on the subfigures. The number of lost phones are denoted as the
radius and colour of the circles, e.g., the smallest circle in black denotes only one
lost phone at that location, the second smallest circle in orange denotes two lost
phones, and the largest circle in red is the total 442 lost phones detected where
the shipwreck took place. The Fig. 3(b), 3(d), and 3(f) on the right show the
number of lost phones detected in the geo-pixel (329.863, 246.792), where the
shipwreck took place, at each query step, from the beginning of the experiment.
To shade light on the detailed detection process, we show the number of lost
phones below 10 as well, although no alert will be send for that. As shown in the
Fig. 3(b), 3(d), and 3(f), there are sudden jumps of the number of lost phones
in each figures, at the time when the shipwreck happens. As the number of lost
phones raised to above 10, the lost silence will send alert of that abnormally rise
together with the information of the geo-pixel. As the query step grow from 5
seconds (as shown in Fig. 3(b)) to 30 seconds (as shown in Fig. 3(f)), the number
of lost phones increase faster, and the slopes of the dots become steeper.
A pressure test is also carried out to simulate an extreme scenario in which
10 ships capsize in different locations on the river simultaneously, as shown in
Fig. 4. Each ship carries more than 300 passengers. The duration of the capsizing
of one ship is about 3 minutes. Thus, in the 10 geo-pixels along the river, there
is a massive phone loss incident with the rate of about 300 ÷ 3 = 100 phones
per minute. As shown in the Fig. 4(a), the abnormality of a large number of lost
phones in all of the 10 geo-pixels are detected, and alerts are sent successfully.
Lost Silence 11
246.804
45
246.802 40.0 40.0
40 38.0 38.0 39.0
246.800 34.0 34.0 34.0 35.0
35 32.0
30.030.0
Num. of Lost Phones
246.798 30
Longitude
246.796 25
20
246.794
15
246.792 10 7.0
3.0
246.790 5 1.0 2.0
0.0
0
246.788
17
37
1003
1767
1973
3661
6847
1
115
193
11632
13675
15506
17714
20614
22494
25321
28476
30976
33113
36304
38810
41662
44775
48198
50147
53120
55761
58919
61447
329.860 329.865 329.870 329.875
Latitude Time (ms)
(a) (b)
250
246.797
246.796 200 199.0
246.795 180.0
Num. of Lost Phones
161.0
150
246.794 138.0
Longitude
118.0
246.793
100
246.792 78.0
59.0
246.791 50
28.0
246.790
0 5.0
0.0
246.789 0.0 2.0 4.0 6.0 8.0 10.0 12.0 14.0 16.0
329.860 329.862 329.864 329.866 329.868 x 10000
Latitude Time (ms)
(c) (d)
246.800
100 93
246.798 88
90 82
79
246.796 80 73
67 69
Num. of Lost Phones
70 62
58
Longitude
246.794 60 51
46
50 42
246.792 37
40 33
28
246.790 30 20
20 15
246.788
10 0 2 4
246.786 0
329.859 329.861 329.863 329.865 329.867 329.869 0 20000 40000 60000 80000 100000
Latitude Time (ms)
(e) (f)
Fig. 3. The total number of lost phones in the shipwreck area and the query results in
the geo-pixel (329.863, 246.792), where the shipwreck took place, at each query step for
the three experiments with the query steps of 5 seconds, 20 seconds, and 30 seconds,
respectively. Fig. a) and b) correspond to the experiment with the query step of 5
seconds, Fig. c) and d) correspond to 20 seconds, and Fig. e) and f) 30 seconds. Fig.
a), c), and e) illustrate the total number of phones lost signal at the water area of
city Jianli at each experiment. The number of phones lost signal scales with the colour
and radius of the circle, e.g., the brighter colour and larger radius of a circle denotes
a larger number of lost phones. Fig. b), d), and f) show the number of detected lost
phones in the geo-pixel (329.863, 246.792), at each query step from the beginning of
the query.
12 Zhou et al.
239.800
100
239.798
90
239.796 80
Longitude
Num. of Lost Phones
239.794 70
60
239.792
50
239.790 40
239.788 30
20
239.786
10
322.858
322.859
322.860
322.861
322.862
322.863
322.864
322.865
322.866
322.867
322.868
322.869
322.870
0
5000 15000 25000 35000 45000 55000 65000 75000 85000
Latitude Time (ms)
(a) (b)
Fig. 4. Query result in the pressure test scenario in which massive phones lost signal
in multiple geo-pixels along the river.
The results at each query step for an random geo-pixel is shown in the Fig. 4(b).
A sharp increase of the lost phones can be spotted, with the rate about 100
phones per minute. The result demonstrates the efficiency and practicality of
the lost silence.
7 Related Work
The utility of data from telecommunication system in geography and social sci-
ence to improve urban planning has been increasingly investigated [4, 15–18].
In [4], Willessan presented how evidence obtained from mobile system plays a
part in forensic investigation. [15–18] provided a extensive coverage of the smart
city applications adopting data from telecommunication system. However, these
applications mainly focus on mobile positioning only. [21] presented an interest-
ing application adopting satellite images and linked geographic data to detect
wildfire. Ontology and RDF stream processing had also been adopted to develop
autonomous vehicles in [22]. A novel approach for spatiotemporal query linked
data was reported in [23].
Scholte and Rozenkrane [19] have proposed a system to localize and track
each ship, and send personalized alert to those that are expected to be in danger.
However, this system might lose function when the communication device fails,
and cannot detect an accident when the communication device on the ship is
not functioning. [20] designed and developed an ontology for emergency notifi-
cation, such as “a typhoon approaching”, but not for detection tragedies already
happened.
8 Conclusions
In this paper we have shown that the system data inside cellular networks can
be used to detect accidents with large number of phones lost signal at the same
location simultaneously, in our scenario a ship capsizing incident.
Lost Silence 13
In lost silence, heterogenous user data from all the vendors are concentrated
and organized with Geo-Pixel, which is proposed as a geography unit. Contin-
uous RDF processing is adopted to query the data streams in real time. We
perform the simulation based on a real life shipwreck incident in China 2015,
and discussed the results in different scenarios.
This lost silence service adopts the ontology developed and built for the
TOUCAN project. Current ontologies of telecommunication networks generally
do not provide information and knowledge inside the system. In our future work,
we will intent to extend the lost silence with machine learning approaches and
real data from cellular networks.
Acknowledgements
This research was supported by the EPSRC TOUCAN project (Grant No.
EP/L020009/1).
Bibliography
[1] Peace time disasters. 2017. https://en.wikipedia.org/wiki/List_of_
maritime_disasters_in_the_21st_century#Peacetime_disasters
[2] Missing migrates. 2017. https://missingmigrants.iom.int
[3] Shipwreck since 1833. 2017. http://www.infoplease.com/ipa
[4] Willassen, S., 2003. Forensics and the gsm mobile telephone system. Inter-
national Journal of Digital Evidence 2 (1), 1–17.
[5] Valle, E. D., Ceri, S., Harmelen, F. V., Fensel, D., 2009. It’s a streaming
world! reasoning upon rapidly changing information. IEEE Intelligent Systems
24 (6), 83–89.
[6] Barbieri, D. F., Braga, D., Ceri, S., Valle, E. D., M.Grossniklaus, 2009. C-
sparql: Sparql for continuous querying. In: ACM the 18th international con-
ference on World wide web. pp. 1061–1062.
[7] Kolchin, M., Dmitry, M., Sergey, A., 2014. Demonstration: web-based visu-
alisation and monitoring of smart meters using cqels,.
[8] Calbimonte J P, Corcho O, Gray A J G., 2010. Enabling ontology-based
access to streaming data sources. In: International Semantic Web Conference.
Springer, Berlin, Heidelberg, 2010. pp. 96 –111.
[9] Margara, A., Urbani, J., van Harmelen, F., 2014. Streaming the web: Rea-
soning over dynamic data.
[10] Gowrishankar, N., Satyanarayana, P. S., 2008. Neural network based traffic
prediction for wireless data networks. International Journal of Computational
Intelligence Systems 1 (4), 379–389.
[11] 3GPP, 2017. LTE specifications. http://www.3gpp.org/specifications
[12] FCC, 2017. Enhanced 911 - wireless services. https://www.fcc.gov/
general/enhanced-9-1-1-wireless-services
[13] Grubb, Teryl G., and Wade L. Eakle. Recording wildlife locations with the
Universal Transverse Mercator (UTM) grid system. vol. 483. USDA Forest
Service, Rocky Mountain Forest and Range Experiment Station, 1988.
[14] 2017. Ministry of industry and information technology of the people’s re-
public of china. http://www.miit.gov.cn/
[15] Steenbruggen, J., Tranos, E., Nijkamp, P., 2015. Data from mobile phone
operators: A tool for smarter cities? Telecommunications Policy 39 (3), 335–
346.
[16] Antonelli, F., Azzi, M., Balduini, M., 2014. Citysensing:visualising mobile
and social data about a city scale event. In: ACM International Working
Conference on Advanced Visual Interfaces. pp. 337–338.
[17] Gonzlez, M., Lind, P. G., Herrmann, H. J., 2006. System of mobile agents
to model social networks. Physical review letters 96 (8), 088702.
[18] Song, C., Qu, Z., Blumm, N., Barabási, A.-L., 2010. Limits of predictability
in human mobility. Science 327 (5968), 1018–1021.
[19] Scholte, K., Rothkrantz, L., 2014. Personal warning system for vessels under
bad weather conditions. Pennsylvania State University.
Lost Silence 15
[20] Malizia, A., Astorga-Paliza, F., Onorati, T., Dı́az Pérez, P., Aedo, I., 2008.
Emergency alerts for all: an ontology based approach to improve accessibility
in emergency alerting systems. In: ISCRAM, Washington, DC, USA, May 4-7,
2008.
[21] K. Kyzirakos, M. Karpathiotakis, et al.: Wildfire monitoring using satel-
lite images, ontologies and linked geospatial data. Journal of Web Semantics,
Volume 24.
[22] T. Eiter, J. X. Parreira, P. Schneider: Spatial Ontology-Mediated Query
Answering over Mobility Streams. In Proc. of ESWC 2017.
[23] H.N.M. Quoc, D. LePhuoc: An elastic and scalable spatio temporal query
processing for linked sensor data. In Proc. SEMANTICS 2015.