1,720,966 research outputs found
Fountain codes and their typical application in wireless standards like edge
Get PDFDissertation (MEng)--University of Pretoria, 2008.One of the most important technologies used in modern communication systems is channel coding. Channel coding dates back to a paper published by Shannon in 1948 [1] entitled “A Mathematical Theory of Communication”. The basic idea behind channel coding is to send redundant information (parity) together with a message to make the transmission more error resistant. There are different types of codes that can be used to generate the parity required, including block, convolutional and concatenated codes. A special subclass of codes consisting of the codes mentioned in the previous paragraph, is sparse graph codes. The structure of sparse graph codes can be depicted via a graphical representation: the factor graph which has sparse connections between its elements. Codes belonging to this subclass include Low-Density-Parity-Check (LDPC) codes, Repeat Accumulate (RA), Turbo and fountain codes. These codes can be decoded by using the belief propagation algorithm, an iterative algorithm where probabilistic information is passed to the nodes of the graph. This dissertation focuses on noisy decoding of fountain codes using belief propagation decoding. Fountain codes were originally developed for erasure channels, but since any factor graph can be decoded using belief propagation, noisy decoding of fountain codes can easily be accomplished. Three fountain codes namely Tornado, Luby Transform (LT) and Raptor codes were investigated during this dissertation. The following results were obtained: The Tornado graph structure is unsuitable for noisy decoding since the code structure protects the first layer of parity instead of the original message bits (a Tornado graph consists of more than one layer). The successful decoding of systematic LT codes were verified. A systematic Raptor code was introduced and successfully decoded. The simulation results show that the Raptor graph structure can improve on its constituent codes (a Raptor code consists of more than one code). Lastly an LT code was used to replace the convolutional incremental redundancy scheme used by the 2G mobile standard Enhanced Data Rates for GSM Evolution (EDGE). The results show that a fountain incremental redundancy scheme outperforms a convolutional approach if the frame lengths are long enough. For the EDGE platform the results also showed that the fountain incremental redundancy scheme outperforms the convolutional approach after the second transmission is received. Although EDGE is an older technology, it still remains a good platform for testing different incremental redundancy schemes, since it was one of the first platforms to use incremental redundancy.Electrical, Electronic and Computer EngineeringMEngunrestricte
A deep framework for predictive maintenance
Get PDFComputer ScienceENGLISH ABSTRACT: Predictive maintenance (PdM) is a well-known maintenance approach that comprises of two
problems, machine prognostic modelling and maintenance scheduling. The objective of prognostic
modelling is to predict faults in machine components such as aircraft engines, lithium-ion
batteries or bearings. The objective of maintenance scheduling is to reduce the cost of performing
maintenance once the future degradation behaviour of a component has been established.
Sensors are used to monitor the degradation behaviour of components as they change over time.
Supervised learning is a suitable solution for prognostic modelling problems, especially with the
increase in sensor readings being collected with Internet of Things (IoT) devices. Prognostic
modelling can be formulated as remaining useful life (RUL)- or machine state estimation. The
former is a regression- and the later is a classification problem.
Long short-term memory (LSTM) recurrent neural networks (RNNs) are an extension of traditional
RNNs that are effective at interpreting trends in the sensor readings and making longer
term estimations. An LSTM uses a window of sequential sensor readings when making prognostic
estimates which causes it to be less sensitive to local sensor variations, which results in
improved prognostic model performance.
In this study we create a framework to implement PdM approaches. The work consists of a
codebase which can be used to create testable, comparable and repeatable prognostic modelling
results and maintenance scheduling simulations. The codebase is designed to be extensible, to
allow future researchers to standardise prognostic modelling results. The codebase is used to
compare the prognostic modelling performance of an LSTM with tradition supervised prognostic
modelling approaches such as Random Forests (RF)s, Gradient boosted (GB) trees and
Support Vector Machines (SVM)s. The prognostic models are tested on three well-known
prognostic datasets, the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS)
engine aircraft-, Center for Advanced Life Cycle Engineering (CALCE) battery- and Intelligent
Maintenance Systems (IMS) bearing datasets. During the study we highlight factors that influence prognostic model performance, such as the effect of de-noising sensor readings and the size
of the sample window used by the LSTM when making estimations. The results of the prognostic
models are compared with previous studies and the LSTM shows improved performance
on considered cases.
The developed prognostic models are used to perform preventative maintenance scheduling with
assumed costs in two simulations. The objective is first to compare the efficacy of traditional
maintenance approaches, such as a mean time between failure (MTBF) strategy, with a PdM
strategy, and second to investigate the effect of using a better performing prognostic model
(such as the LSTM) in a PdM strategy. The improvements are measured by the reduction in
costs.
Key words:
Predictive maintenance; remaining useful life; machine state estimation; preventative maintenance
scheduling.AFRIKAANSE OPSOMMING: Voorspellende instandhouding (PdM) is ’n bekende instandhoudingsbenadering wat bestaan uit
twee probleme, naamlik masjienprognostiese modellering en instandhoudingskedulering. Die
doel van prognostiese modellering is om foute in masjienkomponente soos vliegtuigenjins, litiumioonbatterye
of laers te voorspel. Die doel van instandhoudingskedulering is om die koste van
die uitvoering van instandhouding te verminder sodra die toekomstige degradasiegedrag van ’n
komponent vasgestel is.
Sensors word monitor die degradasiegedrag van komponente soos hulle verander oor tyd. Toesigleer
is ’n geskikte oplossing vir prognostiese modelleringsprobleme, veral met die toename
in sensorlesings wat met Internet of Things (IoT) toestelle ingesamel word. Prognostiese modellering
kan geformuleer word as oorblywende nuttige lewensduur (RUL)- of masjientoestandberaming.
Eersgenoemde is ’n regressie- en die latere is ’n klassifikasieprobleem.
Langtermyngeheue (LSTM) herhalende neurale netwerke (RNN) is ’n uitbreiding van ’n tradisionele
RNN wat effektief is om tendense in die sensorlesings te interpreteer en langertermynskattings
te maak. ’n LSTM gebruik ’n venster van opeenvolgende sensorlesings wanneer
prognostiese skattings gemaak word, wat veroorsaak dat dit minder sensitief is vir plaaslike
sensorvariasies, wat lei tot verbeterde prognostiese modelwerkverrigting.
In hierdie studie skep ons ’n raamwerk om PdM-benaderings te implementeer. Die werk bestaan
uit ’n kodebasis wat gebruik kan word om toetsbare, vergelykbare en herhaalbare prognostiese
modelleringsresultate en onderhoudskeduleringssimulasies te skep. Die kodebasis is ontwerp om
uitbreidbaar te wees, sodat toekomstige navorsers prognostiese modelleringsresultate kan standaardiseer.
Die kodebasis word gebruik om die prognostiese modelleringsprestasie van ’n LSTM
te vergelyk met tradisionele prognostiese modelleringsbenaderings soos Random Forests (RF)’e,
Gradient boosted (GB) trees en Support Vector Machines (SVM)’s. Die prognostiese modelle
word getoets op drie bekende prognostiese datastelle, die Commercial Modular Aero-Propulsion
System Simulation (C-MAPSS) enjinvliegtuie, Sentrum vir Gevorderde Lewensiklusingenieurswese (CALCE) battery en Intelligente Onderhoudstelsels (IMS) dradatastelle. Tydens die
studie beklemtoon ons faktore wat prognostiese modelprestasie beïnvloed, soos die effek van
die ruisonderdrukking van sensorlesings en die grootte van die monstervenster wat deur die
LSTM gebruik word wanneer ramings gemaak word. Die resultate van die prognostiese modelle
word vergelyk met vorige studies en die LSTM toon verbeterde prestasie op die oorwoë
gevalle.
Die ontwikkelde prognostiese modelle word gebruik om voorkomende instandhoudingskedulering
uit te voer met veronderstelde koste in twee simulasies. Die doelwit is eerstens om die
doeltreffendheid van tradisionele-instandhoudingsbenaderings, vb. ’n gemiddelde tyd tussen
mislukking (MTBF)-strategie, met ’n PdM-strategie te vergelyk en tweedens om die effek van
die gebruik van ’n beter presterende prognostiese model (soos die LSTM) in ’n PdM strategie
te ondersoek. PdM strategie. Die verbeterings word gemeet aan die vermindering in koste.
Sleutelwoorde:
Voorspellende instandhouding; oorblywende nuttige lewensduur; masjien toestand skatting;
voorkomende onderhoudskedulering
Ergo: a gesture-based computer interaction device
Get PDFThesis (MSc)--Stellenbosch University, 2024.ENGLISH ABSTRACT: This thesis presents Ergo, a bespoke glove‐based sensor suite designed to fully replace the regular
QWERTY keyboard in terms of both number of input keys and speed of input. Ergo collects
acceleration data from each of the user’s 10 fingertips at 40 times per second and is able to
predict which of 50 differ‐ ent hand gestures is being performed at 40 times per second. The user
does not need to explicitly mark the start or end of each gesture, as Ergo is able to automatically
distinguish between intentional gestures made by the user and other non‐gesture movements. When a
known gesture is detected, a corre‐ sponding keystroke is emitted, allowing the user to “type” on
their computer by performing gestures in sequence. Five different classification models are eval‐
uated (Hidden Markov Models, Support Vector Machines, Cumulative Sum, and two different Neural
Network architectures) and Neural Networks are found to be the most effective. The difference in
difficulty between classification tasks which either do or do not include observations without
intentional movement is also evaluated. The additional requirement to be able to distinguish inten‐
tional gestures from other hand movements is found to increase the difficulty of the task
significantly.AFRIKAANSE OPSOMMING: Hierdie tesis stel Ergo bekend ‐ ‘n pasgemaakte stel sensors wat ontwerp is om die algemene
QWERTY‐sleutelbord in terme van die aantal invoersleutels en die spoed van invoering heeltemal te
vervang. Ergo versamel versnellingsdata van elk van die gebruiker se 10 vingerpunte teen ‘n tempo
van 40 keer per se‐ konde en kan voorspel watter van die 50 verskillende bewegings teen dieselfde
tempo uitgevoer word. Die gebruiker hoef nie die begin of einde van elke bewe‐ ging noukeurig aan
te dui nie aangesien Ergo ‘n gebrek aan doelbewuste bewe‐ ging kan opspoor en dienooreenkomstig kan
reageer. Wanneer ‘n bekende be‐ weging waargeneem word, word ‘n ooreenstemmende toetsaanslag
uitgestuur, en kan die gebruiker op sy of haar rekenaar “tik” deur bewegings in volgorde uit te
voer. Vyf verskillende klassifikasiemodelle word geëvalueer (Versteekte Markov‐modelle,
Ondersteuningsvektormasjiene, Kumulatiewe som en twee verskillende Neurale Netwerk‐argitekture).
Daar is bevind dat die Neurale Net‐ werke die klassifikasiemodel met die beste resultate is. Die
verskil in moei‐ likheidsgraad tussen klassifikasietake wat waarnemings sonder doelbewuste beweging
insluit of nie insluit nie, word ook geëvalueer. Daar is gevind dat die bykomende vereiste om
doelbewuste bewegings van ander handbewegings te
kan onderskei, die moeilikheidsgraad van die taak aansienlik verhoog.Master
An extension of the linear regression model for improved vessel trajectory prediction utilising a priori AIS Information
Get PDFThesis (MSc)--Stellenbosch University, 2022.ENGLISH ABSTRACT: As maritime activities increase globally, there is a greater dependency on technology in monitoring,
control and surveillance of vessel activity. One of the most prominent systems for monitoring vessel
activity is the Automatic Identification System (AIS). An increase in both vessels fitted with AIS
transponders, and satellite- and terrestrial receivers has resulted in a significant increase in AIS
messages received globally. This resultant rich spatial and temporal data source related to vessel
activity provides analysts with the ability to perform enhanced vessel movement analytics, of which
a pertinent example is the improvement of vessel location predictions. In this thesis, we propose
a novel method for predicting future locations of vessels by making use of historic AIS data. The
proposed method extends a Linear Regression Model (LRM), utilising historic AIS movement data
in the form of a priori generated spatial maps of the course over ground (LRMAC). The LRMAC
has low complexity and is programmatically easy to implement, and attains accurate prediction
results. We first compare the LRM with a Discrete Kalman Filter (DKF) on linear trajectories.
We then extend the LRM to form the LRMAC. The LRMAC is compared to another method in
literature called the Single Point Neighbour Search (SPNS). For the use case of predicting Cargo
and Tanker vessel trajectories, with a prediction horizon of up to six hours, the LRMAC has an
improved execution time and performance compared to the SPNS.AFRIKAANSE OPSOMMING: As gevolg van die toename in maritieme aktiwiteite wˆereldwyd, het die afhanklikheid van tegnologie
in die monitering, beheer en toesig van vaartuigaktiwiteite ook toegeneem. Een van die mees
prominente stelsels vir die monitering van vaartuigaktiwiteit is die Outomatiese Identifikasiestelsel
(OIS). ’n Toename in vaartuie wat toegerus is met OIS-transponders, en die toename in satelliet- en
terrestri¨ele ontvangers, het gelei tot ’n aansienlike groei in OIS-boodskappe wat wˆereldwyd ontvang
is. Dit het weer gelei tot die toename in dataryke ruimte-temporele bronne, wat verband hou met
vaartuigaktiwiteite. Dit gee ontleders die vermo¨e om gevorderde vaartuig-bewegingsanalise uit te
voer, waarvan ’n toepaslike voorbeeld, die verbetering van vaartuig-liggingvoorspelling is. In hierdie
tesis stel ons ’n nuwe strategie voor om toekomstige liggings van vaartuie te voorspel, wat gebruik
maak van historiese OIS-data. Die voorgestelde metode brei ’n Lineˆere Regressie Model (LRM)
uit, deur gebruik te maak van historiese bewegingsdata en ruimte kaarte van a priori koers oor
grond inligting (LRMAK). Die LRMAK het ’n lae kompleksiteit en is programmaties eenvoudig om
te implementeer, met relatiewe akkurate voorspelling resultate. Ons vergelyk eers die LRM met
’n Diskrete Kalman Filter (DKF) op lineˆere trajekte. Dan brei ons die LRM uit om die LRMAK
te vorm. Die LRMAK word vergelyk met ’n ander metode in literatuur wat die Enkel-punt Buur soektog (EPBS) genoem word. In die geval van trajek-voorspelling vir vrag- en tenkwa-vaartuie, het
die LRMAK ’n verbeterde uitvoeringstyd en is vergelykbaar met ’n ander algoritme in literatuur,
die EPBS, tot en met ’n voorspellingstydperk van ses-ure.Master
Sequential and non-sequential hypertemporal classification and change detection of Modis time-series
Get PDFThesis (PhD(Eng))--University of Pretoria, 2012.Satellites provide humanity with data to infer properties of the earth that were impossible a century ago. Humanity can now easily monitor the amount of ice found on the polar caps, the size of forests and deserts, the earth’s atmosphere, the seasonal variation on land and in the oceans and the surface temperature of the earth. In this thesis, new hypertemporal techniques are proposed for the settlement detection problem in South Africa. The hypertemporal techniques are applied to study areas in the Gauteng and Limpopo provinces of South Africa. To be more specific, new sequential (windowless) and non-sequential hypertemporal techniques are implemented. The time-series employed by the new hypertemporal techniques are obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor, which is on board the earth observations satellites Aqua and Terra. One MODIS dataset is constructed for each province. A Support Vector Machine (SVM) [1] that uses a novel noise-harmonic feature set is implemented to detect existing human settlements. The noise-harmonic feature set is a non-sequential hypertemporal feature set and is constructed by using the Coloured Simple Harmonic Oscillator (CSHO) [2]. The CSHO consists of a Simple Harmonic Oscillator (SHO) [3], which is superimposed on the Ornstein-Uhlenbeck process [4]. The noise-harmonic feature set is an extension of the classic harmonic feature set [5]. The classic harmonic feature set consists of a mean and a seasonal component. For the case studies in this thesis, it is observed that the noise-harmonic feature set not only extends the harmonic feature set, but also improves on its classification capability. The Cumulative Sum (CUSUM) algorithm was developed by Page in 1954 [6]. In its original form it is a sequential (windowless) hypertemporal change detection technique. Windowed versions of the algorithm have been applied in a remote sensing context. In this thesis CUSUM is used in its original form to detect settlement expansion in South Africa and is benchmarked against the classic band differencing change detection approach of Lunetta et al., which was developed in 2006 [7]. In the case of the Gauteng study area, the CUSUM algorithm outperformed the band differencing technique. The exact opposite behaviour was seen in the case of the Limpopo dataset. Sequential hypertemporal techniques are data-intensive and an inductive MODIS simulator was therefore also developed (to augment datasets). The proposed simulator is also based on the CSHO. Two case studies showed that the proposed inductive simulator accurately replicates the temporal dynamics and spectral dependencies found in MODIS data.Electrical, Electronic and Computer Engineeringunrestricte
Machine learning for antenna array failure analysis
Get PDFThesis (MEng)--Stellenbosch University, 2020.ENGLISH ABSTRACT: This work investigated the use of machine learning to detect failed elements in an antenna array.
The aim was to identify a trustworthy means of early detection and isolation of faulty elements to
improve the reliability of measured data. Previous work has shown that it is theoretically possible to
identify failed elements from the far-field radiation pattern, using machine-learning algorithms such
as artificial neural networks and support vector models. However, literature seems void of studies that
test howthe input data affects the accuracy of the machine-learning algorithm. It is possible to measure
the far-field radiation pattern of earth-based antenna arrays, but very few researchers have validated
their proposed techniques on a manufactured array. We therefore investigated the effects of various
far-field sampling methods on the accuracy and training time of a feedforward neural network, and
on the accuracies of different out-of-the-box classification algorithms, and the effect of the antenna
array configuration on the accuracy of a support vector model. We simulated, manufactured and
measured a 16-element circular patch antenna array to determine the feasibility of using the simulated
far-field pattern as training data for a machine-learning algorithm designed to identify failures in a
measured far-field pattern. We found it would not currently be feasible to employ machine learning
to detect single element failures by measuring distortions in the far-field radiation patterns generated
by a very large array of antennas in an irregular sparse configuration, such as those planned for the
Square Kilometer Array (SKA) radio astronomy project.AFRIKAANSE OPSOMMING: Die gebruik van masjienleerword ondersoek vir tydige opsporing en uitsluiting van foutiewe elemente
antenna samestellings. Die doel is om ’n betroubare manier te vind om foutiewe elemente vroegtydig
op te spoor en uit te sluit, sodat die gemete data meer betroubaar sal kan wees, soos byvoorbeeld in
groot antenna samestellings, soos die SKA radio astronomie projek. Vorige studies het bevind dat dit
teoreties moontlik is om foutiewe elemente vanaf die ver-veld patroon te identifiseer deur die gebruik
van ’n masjienleer algoritme soos ’n neurale netwerk(NN)of ondersteunings-vektor masjien ("SVM").
Daar is ’n tekort aan studies in die literatuur wat die invloed van die leerdata op die akkuraatheid van
die masjienleer algoritme toets. Die ver-veld van ’n aardvaste antenna samestelling kan gemeet word,
maar min navorsers het al hul voorgestelde metodes op ’n vervaardigde antenna samestelling getoets.
In hierdie studie is daar ondersoek ingestel na die invloed van verskeie ver-veld steekproefmetodes
op die akkuraatheid en opleidingstyd van ‘n FNN; en op die akkuraathede van verskeie standaard
klassifiseringsalgoritmes; asook die invloed van die uitleg van die saamgestelde antenna op die akkuraatheid
van ‘n SVM. ‘n 16-element sirkelvormige plak antenna samestelling is gesimuleer, vervaardig
en gemeet, om vas te stel of die gesimuleerde ver-veldpatroon suksesvol gebruik kan word as leerdata
vir ‘n masjienleer-algoritme vir foutsporing op ‘n gemete ver-veldpatroon. Ons sou nie tans aanbeveel
om ’n enkele foutiewe element te probeer identifiseer deur versteurings te meet in die ver-veldpatroon
van ‘n baie groot saamgestelde antenna met ‘n yl verspreide, ongeordende uitleg, soos beplan vir die
SKA radio astronomie projek nie.Master
Extended linear regression model for vessel trajectory prediction with a-priori AIS information
Get PDFDATA AVAILABILITY STATEMENT : The data that support the findings of this study are available
at https://doi.org/10.5281/zenodo.1167595 (Ray et al. 2019).As maritime activities increase globally, there is a greater dependency on technology in monitoring, control, and surveillance of vessel activity. One of the most prominent systems for monitoring vessel activity is the Automatic Identification System (AIS). An increase in both vessels fitted with AIS transponders and satellite and terrestrial AIS receivers has resulted in a significant increase in AIS messages received globally. This resultant rich spatial and temporal data source related to vessel activity provides analysts with the ability to perform enhanced vessel movement analytics, of which a pertinent example is the improvement of vessel location predictions. In this paper, we propose a novel strategy for predicting future locations of vessels making use of historic AIS data. The proposed method uses a Linear Regression Model (LRM) and utilizes historic AIS movement data in the form of a-priori generated spatial maps of the course over ground (LRMAC). The LRMAC is an accurate low complexity first-order method that is easy to implement operationally and shows promising results in areas where there is a consistency in the directionality of historic vessel movement. In areas where the historic directionality of vessel movement is diverse, such as areas close to harbors and ports, the LRMAC defaults to the LRM. The proposed LRMAC method is compared to the Single-Point Neighbor Search (SPNS), which is also a first-order method and has a similar level of computational complexity, and for the use case of predicting tanker and cargo vessel trajectories up to 8 hours into the future, the LRMAC showed improved results both in terms of prediction accuracy and execution time.MUNUS International.https://www.tandfonline.com/loi/tgsi20hj2023Electrical, Electronic and Computer Engineerin
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Land cover separability analysis of MODIS time series data using a combined simple harmonic oscillator and a mean reverting stochastic process
Get PDFIt is proposed that the time series extracted from moderate
resolution imaging spectroradiometer satellite data be modeled
as a simple harmonic oscillator with additive colored noise.
The colored noise is modeled with an Ornstein–Uhlenbeck process.
The Fourier transform and maximum-likelihood parameter estimation
are used to estimate the harmonic and noise parameters of
the colored simple harmonic oscillator. Two case studies in South
Africa show that reliable class differentiation can be obtained between
natural vegetation and settlement land cover types, when
using the parameters of the colored simple harmonic oscillator as
input features to a classifier. The two case studies were conducted
in the Gauteng and Limpopo provinces of South Africa. In the case
of the Gauteng case study, we obtained an average for
single-band classification, while standard harmonic features only
achieved an average . In conclusion, the results obtained
from the colored simple harmonic oscillator approach outperformed
standard harmonic features and the minimum distance
classifier.http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?reload=true&punumber=4609443ai201
- …
