DETECTION OF OUTLIERS
IN REAL TIME KINEMATIC (RTK) GLOBAL POSITIONING SYSTEM (GPS) OBSERVATION
DEPARTMENT: SURVEYING AND GEOINFORMATICS
CHAPTER ONE
1.0 INTRODUCTION
1.1 BACKGROUND OF STUDY
In carrying out
data analysis, it is of uttermost importance to identify outlying observations
that deviates so much from the overall datasets before data modelling;
otherwise aberrant data may result in model misspecification, biased parameter
estimation and incorrect results. That is to say it is futile to do data based
analysis when data are contaminated with outliers because outliers can lead to
incorrect analysis of results.
Outliers are
observations that do not follow the statistical distribution of the bulk of the
data, and consequently may lead to erroneous results with respect to
statistical analysis (Liu, et al. 2004). According to Hawkins (1980), an
outlier can be referred to as an observation that deviates so much from other
observations as to arouse suspicions that it was generated by a different
mechanism.
Outliers are
results of mechanical faults, changes in system behaviour, fraudulent
behaviour, human error, instrument error or simply through natural deviations
in populations (Hodge and Austin, 2004). Their detection can identify system
faults and fraud before they escalate with potentially catastrophic
consequences. It can also identify errors and remove their contaminating effects on the data
set and as such to purify the data for processing.
Outliers has the
ability to alter the results arrived at if they are not carefully handled. The
identification and handling of outliers leads to significantly greater
computational process. Because of this, removal of outlying observations can enhance
the quality of data used for statistical inferences. Eliminated outliers from
observations will have positive effects on the
results of data analysis and data
mining. Simple statistical estimates, like sample mean and standard deviation
can be significantly biased by individual outliers that are very far from the
middle of the distribution (Kaya, 2010).
The overall
objective of outlier identification and removal is to discern the odd data, whose
behaviour is very anomalous when put side-by-side with the rest of the data
set. Assessing the abnormal behaviour of outliers aid in the uncovering the
valuable knowledge hidden behind them and also assist in decision making for
the improvement of service quality. The main purpose outlier detection is to separate
those observations that are divergent from the rest of the dataset. Outlier
identification and removal is applied in several fields such as fraud
detection, intrusion detection, data cleaning, medical diagnosis, etc. Data
mining includes supervised and unsupervised approaches (Nithya and Caroline,
2014).
Surveying
networks are used in many geomatics engineering projects to provide positioning
information. In a surveying network, geodetic observations (height differences,
distances, angles, directions and GPS baseline components) are made and then
parameter estimation is realized using the method of least squares (Yetkin,
2013).
1.2
STATEMENT OF THE PROBLEM
The least
squares technique is the most commonly used parameter estimation tool in geomatics.
It is carried out by minimizing the sum of squares of weighted residuals. The advantage
of the least squares method is that it has the ability to give an unbiased and
minimum variance estimate. However, the least squares technique is limited it
must use observations free from gross error i.e. blunder and systematic bias to
provide optimal results. Unfortunately, these unwanted errors are often
encountered in practice. Therefore, outlier detection and elimination in
spatial data is very necessary in conducting spatial data analysis (Yetkin,
2013).
The classical
least squares adjustment method is vulnerable against blunders because the
basic assumption on which the theory of the least squares estimation is founded
is that all the gross and systematic errors have been eliminated before the
adjustment is performed, and only random errors affect the data, but there are
outliers that are very close to random errors in magnitude and are determined
strictly by applying outlier tests. The local and large disturbances are
considered as gross errors, blunders or outliers, whereas smaller and global
deviations are considered as systematic errors. Although these concepts look
quite familiar, there are cases where clear distinction between local
systematic errors and outliers of small magnitude cannot be made. Both kinds of
errors have the same effect on the observations and therefore must be detected
and distributed accordingly.
1.3 AIM
AND OBJECTIVES
1.3.1 AIM
The main aim of
this study is to detect and separate measurement noise (outliers) of GPS
coordinates time series in RTK GPS observations.
1.3.2 OBJECTIVES
The specific
objectives are
i) Carry out field observations using RTK GPS
to generate data sets for detection of outliers.
ii) Develop a
software program based on Matlab for detection of outliers in RTK GPS
observations.
1.4
SIGNIFICANCE OF STUDIES
The monitoring
of buildings, slide slopes and crustal movement is very essential in geodetic
engineering since the reference points stability is very important in the
geodetic methods of determining displacements. In practice, the determination
of the monitored points displacements is usually preceded by the study of the
reference point stability. The application of GPS to determine ground
deformation may influenced on high accuracy of the obtained co-ordinates. This
coordinates especially the vertical coordinates is characterized by the lowest
accuracy. Outliers in the collected measurements may falsify points
coordinates. Consequently they don’t show the actual movement of the points.
This may prevent a proper initiation of constructional or geotechnical safety
measures for this reasons the study of outlier detection and removal is
significant in large engineering structures like buildings, bridges, dams etc.
which are subjects to movements and may eventually lead to failure or collapse
of the structures (Neumann and Kutterer, 2006; Zienkiewicz and Baryla, 2015).
1.5 STUDY
AREA
The study area
of this project is GidanKwano Campus of Federal University of Technology, Minna
(see Figures1.0& 1.1). GidanKwano Campus of Federal University of
Technology, Minna is located approximately between latitude 9.45N and 9.60N (9°
32′ 17″ N and 9° 31′ 27″ N) and longitude 6.33 E and 6.54 E (6° 27′
21″ E and 6° 26′ 18″ E). The university is located in Northern
Nigeria was established by the Federal Government of Nigeria by February, 1983.
Figure 1.0: Map
of Study Area
Figure 1.1: Part of GidanKwano campus Minna,
Niger state
1.6 SCOPE OF THE STUDY:
The study was
limited to the generation of outliers from observation made using just one
model of differential global positioning system to generate outliers for the
project. The study was restricted to the local topographic features found in
the study area that would provide poor satellite geometry. The factors
contributing to these were expected to be generated from the localized features
found at this site. These localized features included: the school of
environmental complex of the federal university of technology Minna including
some of the trees around the complex building. The observation for the study
was also restricted to a small number of sample data points that could be readily
recollected and covered a small geographic area. Also of all the many methods
available for the detection of outliers, this study only focused on the use of
Kalman Filter techniques for the detection of outliers in the real time
kinematic observation of GPS.