Dissertations / Theses on the topic 'Electrical engineering-time series analysis'
To see the other types of publications on this topic, follow the link: Electrical engineering-time series analysis.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Electrical engineering-time series analysis.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Rawizza, Mark Alan. "Time-series analysis of multivariate manufacturing data sets." Thesis, Massachusetts Institute of Technology, 1996. http://hdl.handle.net/1721.1/10895.
Full text
2
Singh, Pushpendra. "Some studies on a generalized fourier expansion for nonlinear and nonstationary time series analysis." Thesis, IIT Delhi, 2016. http://localhost:8080/xmlui/handle/12345678/7064.
Full text
3
Lee, Fung-Man. "Studies in time series analysis and forecasting of energy data." Thesis, Massachusetts Institute of Technology, 1995. http://hdl.handle.net/1721.1/36032.
Full text
4
Hutchinson, James M. "A radial basis function approach to financial time series analysis." Thesis, Massachusetts Institute of Technology, 1994. http://hdl.handle.net/1721.1/12216.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1994.Includes bibliographical references (p. 153-159).
by James M. Hutchinson.
Ph.D.
5
Modlin, Danny Robert. "Utilizing time series analysis to forecast long-term electrical consumption /." Electronic version (PDF), 2006. http://dl.uncw.edu/etd/2006/modlind/dannymodlin.pdf.
Full text
6
Dzunic, Zoran Ph D. Massachusetts Institute of Technology. "A Bayesian latent time-series model for switching temporal interaction analysis." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/103723.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 153-157).
We introduce a Bayesian discrete-time framework for switching-interaction analysis under uncertainty, in which latent interactions, switching pattern and signal states and dynamics are inferred from noisy and possibly missing observations of these signals. We propose reasoning over posterior distribution of these latent variables as a means of combating and characterizing uncertainty. This approach also allows for answering a variety of questions probabilistically, which is suitable for exploratory pattern discovery and post-analysis by human experts. This framework is based on a Bayesian learning of the structure of a switching dynamic Bayesian network (DBN) and utilizes a states-pace approach to allow for noisy observations and missing data. It generalizes the autoregressive switching interaction model of Siracusa et al. [50], which does not allow observation noise, and the switching linear dynamic system model of Fox et al. [16], which does not infer interactions among signals. We develop a Gibbs sampling inference procedure, which is particularly efficient in the case of linear Gaussian dynamics and observation models. We use a modular prior over structures and a bound on the number of parent sets per signal to reduce the number of structures to consider from super-exponential to polynomial. We provide a procedure for setting the parameters of the prior and initializing latent variables that leads to a successful application of the inference algorithm in practice, and leaves only few general parameters to be set by the user. A detailed analysis of the computational and memory complexity of each step of the algorithm is also provided. We demonstrate the utility of our framework on different types of data. Different benefits of the proposed approach are illustrated using synthetic data. Most real data do not contain annotation of interactions. To demonstrate the ability of the algorithm to infer interactions and the switching pattern from time-series data in a realistic setting, joystick data is created, which is a controlled, human-generated data that implies ground truth annotations by design. Climate data is a real data used to illustrate the variety of applications and types of analyses enabled by the developed methodology. Finally, we apply the developed model to the problem of structural health monitoring in civil engineering. Time-series data from accelerometers located at multiple positions on a building are obtained for two laboratory model structures and a real building. We analyze the results of interaction analysis and how the inferred dependencies among sensor signals relate to the physical structure and properties of the building, as well as the environment and excitation conditions. We develop time-series classification and single-class classification extensions of the model and apply them to the problem of damage detection. We show that the method distinguishes time-series obtained under different conditions with high accuracy, in both supervised and single-class classification setups.
by Zoran Dzunic.
Ph. D.
7
Lindberg, Johan. "A Time Series Forecast of the Electrical Spot Price : Time series analysis applied to the Nordic power market." Thesis, Umeå universitet, Institutionen för fysik, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-41898.
Full textAbstract:
In this report six different models for predicting the electrical spot price on the Nordic power exchange, Nord Pool, are developed and compared. They are evaluated against the already existing model as well as the naive test, which is a forecast where the last week’s observations are used as a prognosis for the coming week. The models developed are constructed so that the models for different time resolutions are combined to create a full model. Harmonic regression with a linear trend are used to identify a yearly trend while SARIMAX/SARIMA time series models are used on a daily and hourly basis to reveal dependencies in the data. The model with the best prediction performance is shown to be a SARIMAX model with temperature as exogenous variable on a daily resolution, together with a SARIMA model on an hourly resolution. With an average MAPE of 12.69% and a MAPE2 of 6.90% it has the smallest prediction error out of all of the competing models when doing one week forecasts on the whole year 2009.
8
Thungtong, Anurak. "Synchronization, Variability, and Nonlinearity Analysis: Applications to Physiological Time Series." Case Western Reserve University School of Graduate Studies / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=case1364316597.
Full text
9
Shashidhar, Akhil. "Generalized Volterra-Wiener and surrogate data methods for complex time series analysis." Thesis, Massachusetts Institute of Technology, 2006. http://hdl.handle.net/1721.1/41619.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2006.Includes bibliographical references (leaves 133-150).
This thesis describes the current state-of-the-art in nonlinear time series analysis, bringing together approaches from a broad range of disciplines including the non-linear dynamical systems, nonlinear modeling theory, time-series hypothesis testing, information theory, and self-similarity. We stress mathematical and qualitative relationships between key algorithms in the respective disciplines in addition to describing new robust approaches to solving classically intractable problems. Part I presents a comprehensive review of various classical approaches to time series analysis from both deterministic and stochastic points of view. We focus on using these classical methods for quantification of complexity in addition to proposing a unified approach to complexity quantification encapsulating several previous approaches. Part II presents robust modern tools for time series analysis including surrogate data and Volterra-Wiener modeling. We describe new algorithms converging the two approaches that provide both a sensitive test for nonlinear dynamics and a noise-robust metric for chaos intensity.
by Akhil Shashidhar.
M.Eng.
10
Siracusa, Michael Richard 1980. "Dynamic dependence analysis : modeling and inference of changing dependence among multiple time-series." Thesis, Massachusetts Institute of Technology, 2009. http://hdl.handle.net/1721.1/53303.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 183-190).
In this dissertation we investigate the problem of reasoning over evolving structures which describe the dependence among multiple, possibly vector-valued, time-series. Such problems arise naturally in variety of settings. Consider the problem of object interaction analysis. Given tracks of multiple moving objects one may wish to describe if and how these objects are interacting over time. Alternatively, consider a scenario in which one observes multiple video streams representing participants in a conversation. Given a single audio stream, one may wish to determine with which video stream the audio stream is associated as a means of indicating who is speaking at any point in time. Both of these problems can be cast as inference over dependence structures. In the absence of training data, such reasoning is challenging for several reasons. If one is solely interested in the structure of dependence as described by a graphical model, there is the question of how to account for unknown parameters. Additionally, the set of possible structures is generally super-exponential in the number of time series. Furthermore, if one wishes to reason about structure which varies over time, the number of structural sequences grows exponentially with the length of time being analyzed. We present tractable methods for reasoning in such scenarios. We consider two approaches for reasoning over structure while treating the unknown parameters as nuisance variables. First, we develop a generalized likelihood approach in which point estimates of parameters are used in place of the unknown quantities. We explore this approach in scenarios in which one considers a small enumerated set of specified structures.
(cont.) Second, we develop a Bayesian approach and present a conjugate prior on the parameters and structure of a model describing the dependence among time-series. This allows for Bayesian reasoning over structure while integrating over parameters. The modular nature of the prior we define allows one to reason over a super-exponential number of structures in exponential-time in general. Furthermore, by imposing simple local or global structural constraints we show that one can reduce the exponential-time complexity to polynomial-time complexity while still reasoning over a super-exponential number of candidate structures. We cast the problem of reasoning over temporally evolving structures as inference over a latent state sequence which indexes structure over time in a dynamic Bayesian network. This model allows one to utilize standard algorithms such as Expectation Maximization, Viterbi decoding, forward-backward messaging and Gibbs sampling in order to efficiently reasoning over an exponential number of structural sequences. We demonstrate the utility of our methodology on two tasks: audio-visual association and moving object interaction analysis. We achieve state-of-the-art performance on a standard audio-visual dataset and show how our model allows one to tractably make exact probabilistic statements about interactions among multiple moving objects.
by Michael Richard Siracusa.
Ph.D.
11
Li, Chang. "Complexity Analysis of Physiological Time Series with Applications to Neonatal Sleep Electroencephalogram Signals." Case Western Reserve University School of Graduate Studies / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=case1345657829.
Full text
12
Mohajer, Maryam. "Nonlinear time series analysis of electrical activity in a slice model of epilepsy." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ46205.pdf.
Full text
13
Fourie, Gert. "Power system stabilizer and controlled series capacitor small-signal stability performance analysis." Thesis, Stellenbosch : Stellenbosch University, 2002. http://hdl.handle.net/10019.1/53013.
Full textAbstract:
Thesis (MScEng)--University of Stellenbosch, 2002.ENGLISH ABSTRACT: This thesis presents results of a study on the small-signal stability of a single-machine infinite-bus power system. Conditions of generator loading and network impedance are identified that require additional stability support. Two methods of stability enhancement are investigated, namely the power system stabilizer and the controlled series capacitor. Both stabilizers employ the conventional (classic) control structure, and parameters are evaluated for optimum performance using an integral-of-the-squared-error-based method. Results for damping capability versus generator loading and system impedance were generated. The ability of the power system stabilizer and controlled series capacitor to provide stability support is compared. This comparison is based on (a) the ability to provide more damping torque when needed, and (b) the amount of damping torque contributed by the stabilizer.
AFRIKAANSE OPSOMMING: Hierin word die resultate van 'n studie op die klein-sein stabiliteit van 'n enkel-masjien oneindige-bus kragstelsel weergegee. Kondisies van generator belasting en netwerk impedansie waar dempings-ondersteuning benodig word, word geïdentifiseer. Twee metodes van stabiliteits-verbetering word ondersoek, naamlik die kragstelstel stabiliseerder en die beheerde serie kapasitor. Beide stabiliseerders maak gebruik van die konvensionele (klassieke) beheerstruktuur, waarvan parameters geëvalueer word deur gebruik te maak van 'n integraal-van-die-vierkant-fout-gebaseerde metode. Resultate vir dempingsvermoë teenoor generator belasting en stelsel impedansie word verkry. Die vermoë van die kragstelsel stabiliseerder en beheerde serie kapasitor om stabiliteits-ondersteuning te verskaf, word vergelyk. Hierdie vergelyking is gebasseer op (a) die vermoë om meer dempingswrinkrag te voorsien wanneer benodig, en (b) die hoeveelheid dempingswrinkrag deur die stabiliseerder bygedra.
14
Meliane, Walid. "Applied time series analysis for forecasting process cycle times and process yields in the semiconductor manufacturing industry." Thesis, University of Ottawa (Canada), 1995. http://hdl.handle.net/10393/10331.
Full textAbstract:
Complementary metal oxide semiconductor (CMOS) integrated circuits (ICs) are the dominant technology in the semiconductor industry. Meeting delivery date is important to ensure customer satisfaction and maintain momentum between manufacturing divisions. Two major concerns are to produce the right quantity of ICs in the expected period of time. Yield and cycle time are two critical parameters used to assess process performance. The main objectives of this work were to obtain reliable forecasts of yields and cycle times and to monitor the process for detection of upsets. We explored the use of time series models such as ARIMA, transfer function and intervention models. A simultaneous outlier treatment and forecasting strategy was developed which combined the joint estimation of model parameters and outlier effects procedure with some new control charts. This method is particularly suited for highly correlated processes that are frequently subjected to large outliers. Choice of time basis was an important issue in this work (i.e., week of emergence from or entrance to the process). For ARIMA modeling, cycle time series were found to follow a highly correlated AR(1) process whereas yield series were just white noise. Five-step ahead ARIMA forecasts were often inaccurate due to the presence of frequent and large outliers. One step-ahead ARIMA forecasts were quite satisfactory. Transfer function models relating yield data to the process capacity data were built. Transfer function models for overall process cycle times were constructed using as inputs cycle times for various stages in the process. Five step-ahead forecasts were highly improved using these transfer functions. (Abstract shortened by UMI.)
15
Glaser, John Stanley 1964. "Analysis and design of a constant frequency diode-clamped series resonant converter." Thesis, The University of Arizona, 1991. http://hdl.handle.net/10150/278060.
Full textAbstract:
A constant frequency diode-clamped series resonant power converter (CFCSRC) is proposed as a solution to problems associated with frequency-controlled resonant converters. This converter has two resonant frequencies, and control is achieved by varying the relative time per switching cycle spent at each resonant frequency. Two zero-current-switching (ZCS) modes are examined and plotted in the output plane. Operating and mode boundaries are found and also plotted in the output plane. The output equation for the main mode is shown to be hyperbolic. Peak voltages are shown to be less than or equal to the input voltage, and peak currents are shown to be less than those of the frequency-controlled diode-clamped series resonant converter over a large operating range. A design procedure is given in the form of a design example. Data from a prototype converter is plotted with theoretical data in the output plane and good agreement with the theoretical model is obtained.
16
Norouzi, Mehdi. "Tracking Long-Term Changes in Bridges using Multivariate Correlational Data Analysis." University of Cincinnati / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1416570591.
Full text
17
Olsson, Magnus. "Optimal regulating power market bidding strategies in hydropower systems." Licentiate thesis, Stockholm :, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-596.
Full text
18
Ahmad, Imad Saleh. "Analysis of Intermodulation Distortion for MESFET Small-signal Amplifiers." PDXScholar, 1995. https://pdxscholar.library.pdx.edu/open_access_etds/4989.
Full textAbstract:
Using the nonlinear Volterra series representation, analytical expressions for the third-order intermodulation distortion power and intercept point for a MESFET small-signal amplifier are derived when its equivalent circuit is bilateral and includes the gate-to-drain capacitance (CgJ explicitly as a nonlinear element. Previously developed analytical expressions treated Cgd as a linear element or incorporated it as part of gate-to-source and drainto- source capacitances (Cgs and Cds). These new analytical expressions are then compared with experimental data and good agreement is obtained. The analytical expressions are also used to study the variation of intermodulation distortion with input power, frequency, and source and load impedances. It is shown that the nonlinearity of Cgd contributes significantly to the intermodulation distortion power and the third-order intercept point and therefore should not be neglected in the analysis and design.
19
Ghanavati, Goodarz. "Statistical Analysis of High Sample Rate Time-series Data for Power System Stability Assessment." ScholarWorks @ UVM, 2015. http://scholarworks.uvm.edu/graddis/333.
Full textAbstract:
The motivation for this research is to leverage the increasing deployment of the phasor measurement unit (PMU) technology by electric utilities in order to improve situational awareness in power systems. PMUs provide unprecedentedly fast and synchronized voltage and current measurements across the system. Analyzing the big data provided by PMUs may prove helpful in reducing the risk of blackouts, such as the Northeast blackout in August 2003, which have resulted in huge costs in past decades.
In order to provide deeper insight into early warning signs (EWS) of catastrophic events in power systems, this dissertation studies changes in statistical properties of high-resolution measurements as a power system approaches a critical transition. The EWS under study are increases in variance and autocorrelation of state variables, which are generic signs of a phenomenon known as critical slowing down (CSD).
Critical slowing down is the result of slower recovery of a dynamical system from perturbations when the system approaches a critical transition. CSD has been observed in many stochastic nonlinear dynamical systems such as ecosystem, human body and power system. Although CSD signs can be useful as indicators of proximity to critical transitions, their characteristics vary for different systems and different variables within a system.
The dissertation provides evidence for the occurrence of CSD in power systems using a comprehensive analytical and numerical study of this phenomenon in several power system test cases. Together, the results show that it is possible extract information regarding not only the proximity of a power system to critical transitions but also the location of the stress in the system from autocorrelation and variance of measurements. Also, a semi-analytical method for fast computation of expected variance and autocorrelation of state variables in large power systems is presented, which allows one to quickly identify locations and variables that are reliable indicators of proximity to instability.
20
Winicki, Elliott. "ELECTRICITY PRICE FORECASTING USING A CONVOLUTIONAL NEURAL NETWORK." DigitalCommons@CalPoly, 2020. https://digitalcommons.calpoly.edu/theses/2126.
Full textAbstract:
Many methods have been used to forecast real-time electricity prices in various regions around the world. The problem is difficult because of market volatility affected by a wide range of exogenous variables from weather to natural gas prices, and accurate price forecasting could help both suppliers and consumers plan effective business strategies. Statistical analysis with autoregressive moving average methods and computational intelligence approaches using artificial neural networks dominate the landscape. With the rise in popularity of convolutional neural networks to handle problems with large numbers of inputs, and convolutional neural networks conspicuously lacking from current literature in this field, convolutional neural networks are used for this time series forecasting problem and show some promising results.
This document fulfills both MSEE Master's Thesis and BSCPE Senior Project requirements.
21
Khalilnejad, Arash. "Data-Driven Evaluation of HVAC Systems in Commercial Buildings and Identification of Savings Opportunities." Case Western Reserve University School of Graduate Studies / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=case1579662167776891.
Full text
22
Pang, Yu. "Optimization of fixed-point circuits represented by Taylor Series and real-valued polynomials including analysis of precision and range." Thesis, McGill University, 2010. http://digitool.Library.McGill.CA:8881/R/?func=dbin-jump-full&object_id=92401.
Full text
23
Kyriazis, Panagiotis A. "Analysis and processing of mechanically stimulated electrical signals for the identification of deformation in brittle materials." Thesis, Brunel University, 2010. http://bura.brunel.ac.uk/handle/2438/4604.
Full textAbstract:
The fracture of brittle materials is of utmost importance for civil engineering and seismology applications. A different approach towards the aim of early identification of fracture and the prediction of failure before it occurs is attempted in this work. Laboratory experiments were conducted in a variety of rock and cement based material specimens of various shapes and sizes. The applied loading schemes were cyclic or increasing and the specimens were tested to compression and bending type loading of various levels. The techniques of Pressure Stimulated Current and Bending Stimulated Current were used for the detection of electric signal emissions during the various deformation stages of the specimens. The detected signals were analysed macroscopically and microscopically so as to find suitable criteria for fracture prediction and correlation between the electrical and mechanical parameters. The macroscopic proportionality of the mechanically stimulated electric signal and the strain was experimentally verified, the macroscopic trends of the PSC and BSC electric signals were modelled and the effects of material memory to the electric signals were examined. The current of a time-varying RLC electric circuit was tested against experimental data with satisfactory results and it was proposed as an electrical equivalent model. Wavelet based analysis of the signal revealed the correlation between the frequency components of the electric signal and the deformation stages of the material samples. Especially the increase of the high frequency component of the electric signal seems to be a good precursor of macrocracking initiation point. The additional electric stimulus of a dc voltage application seems to boost the frequency content of the signal and reveals better the stages of cracking process. The microscopic analysis method is scale-free and thus it can confront with the problems of size effects and material properties effects. The AC conductivity time series of fractured and pristine specimens were also analysed by means of wavelet transform and the spectral analysis was used to differentiate between the specimens. A non-destructive technique may be based on these results. Analysis has shown that the electric signal perturbation is an indicator of the forthcoming fracture, as well as of the fracture that has already occurred in specimens.
24
Wong, Wai-ping. "Critical analysis and time series forecasting of electrical energy use in university buildings a case study of the University of Hong Kong /." Click to view the E-thesis via HKU Scholars Hub, 2004. http://lookup.lib.hku.hk/lookup/bib/B37933929.
Full text
25
Tang, Chen. "Forecasting Service Metrics for Network Services." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-284505.
Full textAbstract:
As the size and complexity of the internet increased dramatically in recent years,the burden of network service management also became heavier. The need foran intelligent way for data analysis and forecasting becomes urgent. The wideimplementation of machine learning and data analysis methods provides a newway to analyze large amounts of data.In this project, I study and evaluate data forecasting methods using machinelearning techniques and time series analysis methods on data collected fromthe KTH testbed. Comparing different methods with respect to accuracy andcomputing overhead I propose the best method for data forecasting for differentscenarios.The results show that machine learning techniques using regression can achievebetter performance with higher accuracy and smaller computing overhead. Timeseries data analysis methods have relatively lower accuracy, and the computingoverhead is much higher than machine learning techniques on the datasetsevaluated in this project.Eftersom storleken och komplexiteten på internet har ökat dramatiskt under de senaste åren så har belastningen av nätverkshantering också blivit tyngre. Behovet av ett intelligent sätt för dataanalys och prognos blir brådskande. Den breda implementeringen av maskininlärningsmetoder och dataanalysmetoder ger ett nytt sätt att analysera stora mängder data.I detta projekt studerar och utvärderar jag dataprognosmetoder med hjälp av maskininlärningstekniker och analyser av tidsserier som samlats in från KTHtestbädden. Baserat på jämförelse av olika metoder med avseende på noggrannhet och beräkningskostnader, så föreslår jag föreslår den bästa metoden för dataprognoser för olika scenarier.Resultaten visar att maskininlärningstekniker som använder regression kan uppnå bättre prestanda med högre noggrannhet och mindre datoromkostnader. Metoderför dataanalys av tidsserier har relativt lägre noggrannhet, och beräkningsomkostnaderna är mycket högre än maskininlärningstekniker på de datauppsättningar som utvärderatsi detta projekt.
26
Van, der Merwe Johannes Wilhelm (Wim). "Natural balancing mechanisms in converters." Thesis, Stellenbosch : University of Stellenbosch, 2011. http://hdl.handle.net/10019.1/6791.
Full textAbstract:
Thesis (PhD (Electrical and Electronic Engineering))--University of Stellenbosch, 2011.AFRIKAANSE OPSOMMING: Hierdie proefskrif handel oor die natuurlike balanserings meganismes van veelvlakkige en modulêre omsetters wat fase-skuif dragolf puls wydte modulasie gebruik. Die meganismes kan in twee hoof groepe verdeel word: ‘n swak balanserings meganisme wat afhanklik is van die oorvleuling van die skakelfunksies en ‘n sterk meganisme wat voorkom ongeag of die skakelfunksies oorvleul al dan nie. Die sterk meganisme verdeel verder in twee subgroepe, ‘n direkte oordrag van onbalans energie en ‘n meganisme wat afhang van die verliese in die stelsel. Elkeen van die meganismes word aan die hand van ‘n omsetter topologie waarin die spesifieke meganisme oorheers beskryf en ontleed. In die ondersoek word klem geplaas op die daarstelling van uitdrukkings om die tydskonstantes van herbalansering na ’n afwyking vir elk van die omsetter toplologieë te beskryf.
ENGLISH ABSTRACT: This thesis investigates the natural balancing mechanisms in multilevel and modular converters using phase shifted carrier pulse width modulation. Two groups of mechanisms are identified; a weak balancing mechanism that is only present when the switching functions are interleaved and a strong mechanism that occurs irrespective of the interleaving of the switching functions. It is further shown that the strong balancing mechanism can be divided into a balancing mechanism that depends on the direct exchange of unbalance energy and a loss based balancing mechanism. Each of the mechanisms is discussed and analysed using a converter where the specific mechanism dominates as example. Emphasis is placed on the calculation of the rebalancing time constant following a perturbation. Closed form expressions for the rebalancing time constants for each of the analysed converters are presented.
27
Fatah, Kiar, and Taariq Nazar. "Stock Market Prediction With Deep Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-293853.
Full textAbstract:
Due to the unpredictability of the stock market,forecasting stock prices is a challenging task. In this project,we will investigate the performance of the machine learningalgorithm LSTM for stock market prediction. The algorithmwill be based only on historical numerical data and technicalindicators for IBM and FORD. Furthermore, the denoising anddimension reduction algorithm, PCA, is applied to the stockdata, to examine if the performance of forecasting the stockprice is greater than the initial model. A second method, transferlearning, is applied by training the model on the IBM datasetand then applying it on the FORD dataset, and vice versa, toevaluate if the results will improve. The results show that whenthe PCA algorithm is applied to the dataset separately, and incombination with transfer learning, the performance is greater incomparison to the initial model. Moreover, the transfer learningmodel is inconsistent as the performance is worse for FORD inrespect to the initial model, but better for IBM. Thus, concerningthe results when forecasting stock prices using related tools, it issuggested to use trial and error to identify which of the modelsthat performs the optimally.Att förutse aktiekurser är en utmanande uppgift. Detta beror på aktiemarknadens oförutsägbarhet. Därför kommer vi i detta projekt att undersöka prestandan för maskininlärnings algoritmen LSTMs prognosförmåga för aktie priser. Algoritmen baseras endast på historisk numerisk data och tekniska indikatorer for företagen IBM och FORD. Vidare tillämpas brus minskande och dimension reducerande algorithmen, PCA, på aktiedata för att undersöka om prestandan för att förutse aktie priser är bättre än den ursprungliga modellen. En andra metod, transfer learning, tillämpas genom att träna modellen på IBM data och sedan använda den på FORD data, och vice versa, för att utvärdera om resultaten kommer att förbättras. Resultaten visar, när PCA-algoritmen tillämpas på aktiedata separat, och i kombination med transfer learning är prestandan bättre jämfört med bas modellen. Vidare kan vi inte dra slutsatser om transfer learning då prestandan är sämre för FORD med avseende på bas modellen, men bättre för IBM. I hänsyn till resultaten så föreslås det att man tillämpar modellerna för att identifiera vilken som är mest optimal när man arbetar i ett relaterat ämnesområde.
Kandidatexjobb i elektroteknik 2020, KTH, Stockholm
28
Wang, Hongjie. "Design and Control of Series Resonant Converters for DC Current Power Distribution Applications." DigitalCommons@USU, 2018. https://digitalcommons.usu.edu/etd/7160.
Full textAbstract:
With the growth of renewable energy usage and energy storage adoption in recent decades, people have started to reevaluate the possible roles of dc systems in current and future electrical systems. The dc voltage distribution has been applied in various applications, such as data centers and aircraft industry, for high efficiency and power density. However, for some applications such as subsea gas and oil fields, and ocean observatory systems, the dc current distribution is preferred over dc voltage distribution for its low cost and robustness against cable faults. Design and control of dc power distribution systems for different applications is an emerging research area with complex technical challenges. This dissertation solves the technical challenges in analysis, design, modeling, control and protection of series resonant converters (SRCs) for dc current distribution applications. An optimum design that has high efficiency, high reliability, and minimum required control efforts for the SRC with constant input current has been achieved and demonstrated by applying the analysis and design procedures developed in this dissertation. The modeling and analysis presented in this dissertation represents an operating condition that has not been studied in the literature and could be easily extended to other resonant converter topologies. Explicit analytical expressions have been provided for all key transfer functions, including input impedance and control-to-output, offering valuable resources to design feed-back regulation and to evaluate system stability. Based on the control strategies and control design presented in this dissertation, stable and reliable operation of dc current distribution systems with long distance cable has been achieved and demonstrated. The proposed analysis, design procedure, stability evaluation, control strategy and protection techniques in this dissertation can be applied to a wide range of similar scenarios as well, which greatly increases their value.
29
Hansson, Jörgen. "Analysis and control of a hybrid vehicle powered by free-piston energy converter." Licentiate thesis, KTH, School of Electrical Engineering (EES), 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-4189.
Full textAbstract:
The introduction of hybrid powertrains has made it possible to utilise unconventional engines as primary power units in vehicles. The free-piston energy converter (FPEC) is such an engine. It is a combination of a free-piston combustion engine and a linear electrical machine. The main features of this configuration are high efficiency and a rapid transient response.
In this thesis the free-piston energy converter as part of a hybrid powertrain is studied. One issue of the FPEC is the generation of pulsating power due to the reciprocating motion of the translator. These pulsations affect the components in the powertrain. However, it is shown that these pulsations can be handled by a normal sized DC-link capacitor bank. In addition, two approaches to reduce these pulsations are suggested: the first approach is using generator force control and the second approach is based on phase-shifted operation of two FPEC units. The latter approach results in higher frequency and lower amplitude of the pulsations, which reduce the capacitor losses.
The FPEC start-up requirements are analysed and by choosing the correct amplitude of the generator force during start-up the energy consumption can be minimised.
The performance gain of utilising the FPEC in a medium sized series hybrid electric vehicle (SHEV) is also studied. An FPEC model suitable for vehicle simulation is developed and a series hybrid powertrain, with the same performance as the Toyota Prius, is dimensioned and modelled.
Optimisation is utilised to find a lower limit on the SHEV's fuel consumption for a given drivecycle. In addition, three power management control strategies for the FPEC system are investigated: two load-following strategies using one and two FPEC units respectively and one strategy based on the ideas of an equivalent consumption minimisation (ECM) proposed earlier in the literature.
The results show a significant decrease in fuel consumption, compared to a diesel-generator powered SHEV, just by replacing the diesel-generator with an FPEC. This result is improved even more by using two FPEC units to generate the propulsion power, as this increases the efficiency at low loads. The ECM control strategy does not reduce the fuel consumption compared to the load-following strategies but gives a better utilisation of the available power sources.
30
Nigrini, Lucas Bernardo. "Developing a neural network model to predict the electrical load demand in the Mangaung municipal area." Thesis, [Bloemfontein?] : Central University of Technology, Free State, 2012. http://hdl.handle.net/11462/176.
Full textAbstract:
Thesis (D. Tech. (Engineering: Electric)) -- Central University of technology, 2012Because power generation relies heavily on electricity demand, consumers are required to wisely manage their loads to consolidate the power utility‟s optimal power generation efforts. Consequently, accurate and reliable electric load forecasting systems are required. Prior to the present situation, there were various forecasting models developed primarily for electric load forecasting. Modelling short term load forecasting using artificial neural networks has recently been proposed by researchers. This project developed a model for short term load forecasting using a neural network. The concept was tested by evaluating the forecasting potential of the basic feedforward and the cascade forward neural network models. The test results showed that the cascade forward model is more efficient for this forecasting investigation. The final model is intended to be a basis for a real forecasting application. The neural model was tested using actual load data of the Bloemfontein reticulation network to predict its load for half an hour in advance. The cascade forward network demonstrates a mean absolute percentage error of less than 5% when tested using four years of utility data. In addition to reporting the summary statistics of the mean absolute percentage error, an alternate method using correlation coefficients for presenting load forecasting performance results are shown. This research proposes that a 6:1:1 cascade forward neural network can be trained with data from a month of a year and forecast the load for the same month of the following year. This research presents a new time series modeling for short term load forecasting, which can model the forecast of the half-hourly loads of weekdays, as well as of weekends and public holidays. Obtained results from extensive testing on the Bloemfontein power system network confirm the validity of the developed forecasting approach. This model can be implemented for on-line testing application to adopt a final view of its usefulness.
31
Naeem, Muhammad Farhan. "Analysis of an Ill-posed Problem of Estimating the Trend Derivative Using Maximum Likelihood Estimation and the Cramér-Rao Lower Bound." Thesis, Linnéuniversitetet, Institutionen för fysik och elektroteknik (IFE), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-95163.
Full textAbstract:
The amount of carbon dioxide in the Earth’s atmosphere has significantly increased in the last few decades as compared to the last 80,000 years approximately. The increase in carbon dioxide levels are affecting the temperature and therefore need to be understood better. In order to study the effects of global events on the carbon dioxide levels, one need to properly estimate the trends in carbon dioxide in the previous years. In this project, we will perform the task of estimating the trend in carbon dioxide measurements taken in Mauna Loa for the last 46 years, also known as the Keeling Curve, using estimation techniques based on a Taylor and Fourier series model equation. To perform the estimation, we will employ Maximum Likelihood Estimation (MLE) and the Cramér-Rao Lower Bound (CRLB) and review our results by comparing it to other estimation techniques. The estimation of the trend in Keeling Curve is well-posed however, the estimation for the first derivative of the trend is an ill-posed problem. We will further calculate if the estimation error is under a suitable limit and conduct statistical analyses for our estimated results.
32
Foghammar, Nömtak Carl. "Automatic SLAMS detection and magnetospheric classification in MMS data." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285533.
Full textAbstract:
Short Large-Amplitude Magnetic Structures (SLAMS) have been observedby spacecraft near Earth’s quasi-parallel bow shock. They arecharacterized by a short and sudden increase of the magnetic field,usually by a factor of 2 or more. SLAMS studies have previously beenlimited to small sample sizes because SLAMS were identified throughmanual inspection of the spacecraft data. This makes it difficult to drawgeneral conclusions and the subjective element complicates collaborationbetween researchers. A solution is presented in this thesis; anautomatic SLAMS detection algorithm. We investigate several movingwindowmethods and measure their performance on a set of manuallyidentified SLAMS. The best algorithm is then used to identify 98406SLAMS in data from the Magnetospheric Multiscale (MMS) mission. Ofthose, 66210 SLAMS were detected when the Fast Plasma Investigation(FPI) instrument was active. Additionally, we are interested in knowingwhether a detected SLAMS is located in the foreshock or magnetosheath.Therefore, we implement a Gaussian mixture model classifier,based on hierarchical clustering of the FPI data, that can separatebetween the four distinct regions of the magnetosphere that MMSencounters; magnetosphere, magnetosheath, solar wind and (ion) foreshock.The identified SLAMS are compiled into a database which holdstheir start and stop dates, positional coordinates, B-field informationand information from the magnetospheric classifier to allow for easyfiltering to a specific SLAMS population. To showcase the potentialof the database we use it to perform preliminary statistical analysison how the properties of SLAMS are affected by its spatial and/ormagnetospheric location. The database and Matlab implementationare available on github: https://github.com/cfognom/MMS_SLAMS_detection_and_magnetospheric_classification.Korta magnetiska strukturer med hög amplitud (SLAMS) har observeratsav satelliter nära jordens kvasi-parallella bogchock. En kortoch plötslig höjning av magnetfältsstyrkan är ett typiskt drag förSLAMS, vanligtvis med en faktor 2 eller mer. Forskning om SLAMShar tidigare varit begränsad till mindre fallstudier eftersom SLAMSidentifierats genom manuell inspektion av satellitdata. Detta gör detsvårt att dra generella slutsatser och det subjektiva elementet försvårarsamarbetet mellan forskare. En lösning till detta problem presenteras idenna avhandling; en automatisk identifieringsalgoritm för SLAMS. Viundersöker flera metoder och mäter deras prestanda på en uppsättningmanuellt identifierade SLAMS. Den bästa algoritmen används sedan föratt identifiera 98406 SLAMS i data från MMS-uppdraget. Av dessa upptäcktes66210 SLAMS när FPI-instrumentet var aktivt. Vi är dessutomintresserade av att veta om en upptäckt SLAMS finns i förshocken ellermagnetoskiktet. Därför implementerar vi en Gaussisk klassificeraresom bygger på hierarkisk klustring av FPI-data. Den kan separerade fyra distinkta regionerna av magnetosfären som MMS observerar;magnetosfär, magnetoskikt, solvind och (jon) förchock. De identifieradeSLAMS:en sammanställs till en databas som innehåller deras start- ochstoppdatum, positionskoordinater, B-fältsinformation och informationfrån magnetosfärsklassificeraren för att möjliggöra enkel filtrering tillen specifik SLAMS-population. För att visa potentialen av databasenutför vi en preliminär statistisk undersökning av hur egenskapernaav SLAMS påverkas av deras rumsliga och/eller magnetosfäriska position.Databasen och Matlab-implementationen är tillgängliga på Github:https://github.com/cfognom/MMS_SLAMS_detection_and_magnetospheric_classification.
33
Lorgat, Mohamed Wasim. "Detecting network attacks using high-resolution time series." Master's thesis, University of Cape Town, 2018. http://hdl.handle.net/11427/29489.
Full textAbstract:
Research in the detection of cyber-attacks has sky-rocketed in the recent past. However, there remains a striking gap between usage of the proposed algorithms in academic research versus industrial applications. Leading researchers have argued that efforts toward the understanding of proposed detectors are lacking. By digging deeper into their inner workings and critically evaluating their underlying assumptions, better detectors may be built. The aim of this thesis is therefore to provide an underlying theory for understanding a single class of detection algorithms, in particular, anomaly-based network intrusion detection algorithms that utilise high-resolution time series data. A framework is proposed to deconstruct the algorithms into their constituent components (windows, representations, and deviations). The framework is applied to a class of algorithms, allowing to construct a “space” of algorithms spanned by five variables: windowing procedure, information availability, single- or multi-aggregated representation, marginal distribution model, and deviation. The detection of a simple class of Denial-of-Service (DoS) attacks is modelled as a detection theoretic problem. It is shown that the effect of incomplete information is greatest when detecting low-intensity attacks (less than 5%), however, the effect slowly decays as the attack intensity increases. Next, the representation and deviation components are jointly analysed via a proposed experimental procedure using network traffic from two publicly available datasets: the Measurement and Analysis on the WIDE Internet (MAWI) archive, and the Booters dataset. The experimental analysis shows that varying the representation (single- versus multi-aggregated) has little effect on detection accuracy, and that the likelihood deviation is superior to the L2 distance deviation, although the difference is negligible for large-intensity attacks (approximately 80%).
34
Ayyaz, Usman. "Time series formalism : a systems approach." Thesis, Massachusetts Institute of Technology, 2017. http://hdl.handle.net/1721.1/112896.
Full textAbstract:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 51-52).
Time series data has become a modern day phenomena: from stock market data to social media information, modern day data exists as a continuous flow of information indexed by timestamps. Using this data to gather contextual inference and make future predictions is vital to gaining an analytical edge. While there are specialized time series databases and libraries available that optimize for performance and scale, there is an absence of a unifying framework that standardizes interaction with time series data sets. We introduce a python-based time series formalism which provides a SQL style querying interface alongside a rich selection of time series prediction algorithms. Users can forecast data or impute missing entries using a specialized prediction query which employs learning models under the hood. The decoupled architecture of our framework allows it to be easily substituted with any SQL database. We show the functionality of our abstraction with a single machine implementation which will be a building block towards a scalable distributed platform for time series analysis.
by Usman Ayyaz.
M. Eng.
35
Gartheeban, Ganeshapillai. "Learning connections in financial time series." Thesis, Massachusetts Institute of Technology, 2014. http://hdl.handle.net/1721.1/93061.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 125-132).
Much of modern financial theory is based upon the assumption that a portfolio containing a diversified set of equities can be used to control risk while achieving a good rate of return. The basic idea is to choose equities that have high expected returns, but are unlikely to move together. Identifying a portfolio of equities that remain well diversified over a future investment period is difficult. In our work, we investigate how to use machine learning techniques and data mining to learn cross-sectional patterns that can be used to design diversified portfolios. Specifically, we model the connections among equities from different perspectives, and propose three different methods that capture the connections in different time scales. Using the "correlation" structure learned using our models, we show how to build selective but well-diversified portfolios. We show that these portfolios perform well on out of sample data in terms of minimizing risk and achieving high returns. We provide a method to address the shortcomings of correlation in capturing events such as large losses (tail risk). Portfolios constructed using our method significantly reduce tail risk without sacrificing overall returns. We show that our method reduces the worst day performance from -15% to -9% and increases the Sharpe ratio from 0.63 to 0.71. We also provide a method to model the relationship between the equity return that is unexplained by the market return (excess return) and the amount of sentiment in news releases that hasn't been already reflected in the price of equities (excess sentiment). We show that a portfolio built using this method generates an annualized return of 34% over a 10-year time period. In comparison, the S&P 500 index generated 5% return in the same time period.
by Gartheeban Ganeshapillai.
Ph. D.
36
Liao, Ruizhi. "Temporal registration for MRI time series." Thesis, Massachusetts Institute of Technology, 2017. http://hdl.handle.net/1721.1/111921.
Full textAbstract:
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 29-32).
Time-course analysis in medical image series often suffers from serious motion. Registration provides voxel correspondences among images, and is commonly employed for correcting motion in medical images. Yet, the registration procedure fails when aligning volumes that are substantially different from template. We present a robust method to correct for motion and deformations in MRI time series. We make a Markov assumption on the nature of deformations to take advantage of the temporal smoothness in the image data. Forward message passing in the corresponding hidden Markov model (HMM) yields an estimation algorithm that only has to account for relatively small motion between consecutive frames. We demonstrate the utility of the temporal model by showing that its use for in-utero MRI time series alignment improves the accuracy of the segmentation propagation through temporal registration. Our results suggest that the proposed model captures accurately the temporal dynamics of deformations present in in-utero MRI time series. We also demonstrate that our method can be used for cardiac cine MRI. By propagating segmentation labels of one volume to the other frames in the cine MRI through deformation estimated by our method, 4D (3D+time) cardiac MRI series can be segmented.
by Ruizhi Liao.
S.M.
37
Hung, Elmer S. "Parameter estimation in chaotic time series." Thesis, Massachusetts Institute of Technology, 1994. http://hdl.handle.net/1721.1/32609.
Full text
38
Mashikian, Paul Stephan. "Multiresolution models of financial time series." Thesis, Massachusetts Institute of Technology, 1997. http://hdl.handle.net/1721.1/43483.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1997.Includes bibliographical references (leaves 89-92).
by Paul Stephan Mashikian.
M.Eng.
39
Thornlow, Robert Timothy. "Spectrum estimation using extrapolated time series." Thesis, Monterey, California : Naval Postgraduate School, 1990. http://handle.dtic.mil/100.2/ADA246554.
Full textAbstract:
Thesis (M.S. in Electrical Engineering)--Naval Postgraduate School, December 1990.Thesis Advisor(s): Hippenstiel, Ralph. Second Reader: Tummala, Murali. "December 1990." Description based on title screen as viewed on March 30, 2010. DTIC Descriptor(s): Frequency, Density, Data Management, Models, Signal To Noise Ratio, Theses, Power Spectra, Sequences, Estimates, Short Range(Time), Spectra, Sampling, Fast Fourier Transforms, Extrapolation, Data Processing. DTIC Identifier(s): Power Spectra, Estimates, Time Series Analysis, Extrapolation, Density, Theses, Fast Fourier Transforms, Eigenvectors, Mathematical Prediction. Author(s) subject terms: Data Extrapolation, Periodogram, AR spectral estimates. Includes bibliographical references (p. 94). Also available in print.
40
Johnson, Matthew James Ph D. Massachusetts Institute of Technology. "Bayesian time series models and scalable inference." Thesis, Massachusetts Institute of Technology, 2014. http://hdl.handle.net/1721.1/89993.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 197-206).
With large and growing datasets and complex models, there is an increasing need for scalable Bayesian inference. We describe two lines of work to address this need. In the first part, we develop new algorithms for inference in hierarchical Bayesian time series models based on the hidden Markov model (HMM), hidden semi-Markov model (HSMM), and their Bayesian nonparametric extensions. The HMM is ubiquitous in Bayesian time series models, and it and its Bayesian nonparametric extension, the hierarchical Dirichlet process hidden Markov model (HDP-HMM), have been applied in many settings. HSMMs and HDP-HSMMs extend these dynamical models to provide state-specific duration modeling, but at the cost of increased computational complexity for inference, limiting their general applicability. A challenge with all such models is scaling inference to large datasets. We address these challenges in several ways. First, we develop classes of duration models for which HSMM message passing complexity scales only linearly in the observation sequence length. Second, we apply the stochastic variational inference (SVI) framework to develop scalable inference for the HMM, HSMM, and their nonparametric extensions. Third, we build on these ideas to define a new Bayesian nonparametric model that can capture dynamics at multiple timescales while still allowing efficient and scalable inference. In the second part of this thesis, we develop a theoretical framework to analyze a special case of a highly parallelizable sampling strategy we refer to as Hogwild Gibbs sampling. Thorough empirical work has shown that Hogwild Gibbs sampling works very well for inference in large latent Dirichlet allocation models (LDA), but there is little theory to understand when it may be effective in general. By studying Hogwild Gibbs applied to sampling from Gaussian distributions we develop analytical results as well as a deeper understanding of its behavior, including its convergence and correctness in some regimes.
by Matthew James Johnson.
Ph. D.
41
Tinawi, Ihssan. "Machine learning for time series anomaly detection." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/123129.
Full textAbstract:
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (page 55).
In this thesis, I explored machine learning and other statistical techniques for anomaly detection on time series data obtained from Internet-of-Things sensors. The data, obtained from satellite telemetry signals, were used to train models to forecast a signal based on its historic patterns. When the prediction passed a dynamic error threshold, then that point was flagged as anomalous. I used multiple models such as Long Short-Term Memory (LSTM), autoregression, Multi-Layer Perceptron, and Encoder-Decoder LSTM. I used the "Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding" paper as a basis for my analysis, and was able to beat their performance on anomaly detection by obtaining an F0.5 score of 76%, an improvement over their 69% score.
by Ihssan Tinawi.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
42
Gerber, Georg Kurt 1970. "Do the time-wrap: continuous alignment of gene expression time-series data." Thesis, Massachusetts Institute of Technology, 2003. http://hdl.handle.net/1721.1/87336.
Full text
43
Grullon, Dylan Emanuel Centeno. "Disentangling time constant and time dependent hidden state in time series with variational Bayesian inference." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/124572.
Full textAbstract:
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 85-86).
In this thesis, we design and explore a new model architecture called a Variational Bayes Recurrent Neural Network (VBRNN) for modelling time series. The VBRNN contains explicit structure to disentangle time constant and time dependent dynamics for use with compatible time series, such as those that can be modelled by differential equations with time constant parameters and time dependent state. The model consists of a Variational Bayes (VB) layer to infer time constant state, as well as a conditioned-RNN to model time dependent dynamics. The VBRNN is explored through various synthetic datasets and problems, and compared to conventional methods on these datasets. This approach demonstrates effective disentanglement, motivating future work to explore the efficacy of this mo del in real word datasets.
by Dylan Emanuel Centeno Grullon.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
44
Gerstein, Beth Tamara. "Analyzing biololgical time series with higher order cumulants." Thesis, Massachusetts Institute of Technology, 1997. http://hdl.handle.net/1721.1/43403.
Full textAbstract:
Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1997.Includes bibliographical references (p. 103-105).
by Beth Tamara Gerstein.
M.S.
45
Pienaar, Marc. "On the classification of time series and cross wavelet phase variance." Doctoral thesis, University of Cape Town, 2016. http://hdl.handle.net/11427/22869.
Full textAbstract:
The continuous wavelet transform (CWT) is arguably one of the best tools to explore underlying characteristic features of time series data. Its application in large time series classification experiments, however, has been severely limited due to the large amount of redundant associated information. By extending the capabilities of the CWT to perform cross wavelet analysis (CWA), common frequency behaviour between two time series is highlighted, and the potential to extract amplitude modulated (AM) and frequency modulation (FM) characteristics in an automated way is possible. Characterisation of AM is relatively straightforward and can be resolved by any number of Euclidean based techniques in both the time and frequency domains. FM on the other hand, is somewhat more difficult as it transcends multiple wavelet scales. In this study, linear combinations of scales are used to extract both AM similarity (derived from global wavelet power spectra) and FM coherency, using a new method developed called cross wavelet phase variance (CWPV). The methodology is applied to large scale classification problems (using benchmark time series), in which the method clearly outperforms other common distance-based measures. Lastly, the approach provides a powerful framework in which AM and FM characteristics common between time series can be explicitly mapped to their corresponding scales, and with some initial optimisation, can be applied to any classification problem.
46
Jain, Bonny. "Modelling signal interactions with application to financial time series." Thesis, Massachusetts Institute of Technology, 2014. http://hdl.handle.net/1721.1/91832.
Full textAbstract:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.Thesis: S.B., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 99-100).
In this thesis, we concern ourselves with the problem of reasoning over a set of objects evolving over time that are coupled through interaction structures that are themselves changing over time. We focus on inferring time-varying interaction structures among a set of objects from sequences of noisy time series observations with the caveat that the number of interaction structures is not known a priori. Furthermore, we aim to develop an inference procedure that operates online, meaning that it is capable of incorporating observations as they arrive. We develop an online nonparametric inference algorithm called Online Nonparametric Switching Temporal Interaction Model inference (ONSTIM). ONSTIM is an extension of the work of Dzunic and Fisher [1], who employ a linear Gaussian model with time-varying transition dynamics as the generative graphical model for observed time series. Like Dzunic and Fisher, we employ sampling approaches to perform inference. Instead of presupposing a fixed number of interaction structures, however, we allow for proposal of new interaction structures sampled from a prior distribution as new observations are incorporated into our inference. We then demonstrate the viability of ONSTIM on synthetic and financial datasets. Synthetic datasets are sampled from a generative model, and financial datasets are constructed from the price data of various US stocks and ETFs.
by Bonny Jain.
M. Eng.
S.B.
47
Rahimi, Ali 1976. "Learning to transform time series with a few examples." Thesis, Massachusetts Institute of Technology, 2005. http://hdl.handle.net/1721.1/35528.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, February 2006.Also issued as printed in pages.
MIT Barker Engineering Library copy: printed in pages.
Includes bibliographical references (leaves 113-119).
I describe a semi-supervised regression algorithm that learns to transform one time series into another time series given examples of the transformation. I apply this algorithm to tracking, where one transforms a time series of observations from sensors to a time series describing the pose of a target. Instead of defining and implementing such transformations for each tracking task separately, I suggest learning a memoryless transformations of time series from a few example input-output mappings. The algorithm searches for a smooth function that fits the training examples and, when applied to the input time series, produces a time series that evolves according to assumed dynamics. The learning procedure is fast and lends itself to a closed-form solution. I relate this algorithm and its unsupervised extension to nonlinear system identification and manifold learning techniques. I demonstrate it on the tasks of tracking RFID tags from signal strength measurements, recovering the pose of rigid objects, deformable bodies, and articulated bodies from video sequences, and tracking a target in a completely uncalibrated network of sensors. For these tasks, this algorithm requires significantly fewer examples compared to fully-supervised regression algorithms or semi-supervised learning algorithms that do not take the dynamics of the output time series into account.
by Ali Rahimi
Ph.D.
48
Eriksson, Henrik, and Victor Löfgren. "Evaluating Different Algorithms for Detecting Change-points in Time Series." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-239360.
Full textAbstract:
Change-point detection is useful in many areas and there are several algorithms developed to cater specific needs such as fast calculations and statistical accuracy. In this report we outline five different algorithms, namely Fused Lasso, Filtered Fused Lasso, Normalized Fused Lasso, Dynamic Programming Approach and our own creation using convolution filtering, the Convolution Method. We evaluate them in the mentioned areas. Convolution Method is the fastest, Dynamic Programming Approach is the most accurate but suffers greatly in speed compared the other algorithms. Normalized and Filtered Fused Lasso performs similar in both speed and statistical accuracy. Although Fused Lasso is as fast as Normalized and Filtered Fused Lasso, it can not detect true change-points to any reliable extent.
49
Åkerlund, Agnes. "Time-Series Analysis of Pulp Prices." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-39726.
Full textAbstract:
The pulp and paper industry has a significant role in Europe’s economy and society, and its significance is still growing. The pulp market and the customers’ requirements are highly affected by the pulp market prices and the requested kind of pulp, i.e., Elementary Chlorine Free (ECF) or Total Chlorine Free (TCF). There is a need to predict different market aspects, where the market price is one, to gain a better understanding of a business situation. Understanding market dynamics can support organizations to optimize their processes and production. Forecasting future pulp prices has not recently been done, but it would help businesses to make decisions that are more informed about where to sell their product. The studies existing about the pulp industry and forecast of market prices were completed over 20 years ago, and the market has changed since then in terms of, e.g., demand and production volume. There is a research gap within the pulp industry from a market price perspective. The pulp market is similar to, e.g., the energy industry in some aspects, and time-series analysis has been used to forecast electricity prices to support decision making by electricity producers and retailers. Autoregressive Integrated Moving Average (ARIMA) is one time-series analysis method that is used when data are collected with a constant frequency and when the average is not constant. Holt-Winters model is a well-known and simple time-series analysis. In this thesis, time-series analysis is used to predict the weekly market price for pulp the three upcoming months, with the research question “With what accuracy can time-series analysis be used to forecast the European PIX price on pulp on a week-ahead basis?”. The research method in this thesis is a case study where data are collected through the data collection method documents. First, articles are studied to gain understanding within the problem area leading to the use of the artefact time-series analyses and a case study. Then, historical data are collected from the organization FOEX Fastmarkets, where a new market price of pulp has been released every Tuesday since September 1996. The dataset has a total of 1200 data points. After data cleaning, it is merged to 1196 data points that are used for the analysis. To evaluate the results from the time-series analysis models ARIMA and Holt-Winter, Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used. The software RStudio is used for programming. The results shows that the ARIMA model provides the most accurate results. The mean value for MAE is 16,59 for ARIMA and 44,61 for Holt-Winters. The mean value for MAPE is 1,99% for ARIMA and 5,37% for Holt-Winters.
50
Kim, Yongwook Bryce. "Physiological time series retrieval and prediction with locality-sensitive hashing." Thesis, Massachusetts Institute of Technology, 2017. http://hdl.handle.net/1721.1/111903.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 131-143).
The amount of time series data collected in the medical community has recently been exploding due to widespread affordable sensors and storage devices. However, while the massive repositories of such physiological time series data provide enormous opportunities for machine learning to make significant impacts, they are largely under-utilized due to their granular detail, overwhelming size, and lack of proper tools. Besides scale, fast yet accurate processing of physiological waveform data is desired in medical practice, especially in time-critical settings such as the intensive care unit (ICU). Efficiently leveraging these massive datasets is a key challenge that, when resolved, will support a new paradigm of scientific discovery and operational innovation in medicine. In this thesis, we develop highly efficient similarity-based methods that make it practical to search massive physiological time series repositories to rapidly identify waveforms similar to those from a given individual. We call this concept "patients with trajectories like mine." Our goal is to exploit rapid similar waveform retrieval to enable critical event prediction in the ICU setting. In order to achieve this goal, we propose to apply locality-sensitive hashing (LSH), which supports a very fast approximate nearest neighbor search in high dimensions. We empirically demonstrate that LSH based retrieval and prediction methods vastly speed up querying time while sacrificing only a trivial amount of accuracy as a cost. Despite being fast and accurate, the generic LSH has two shortcomings. First, it is capable of utilizing only one similarity measure at a time. To overcome this limit, we introduce Stratified LSH (SLSH) which finds similarity among the data from a more integrated perspective by employing multiple distance metrics in one framework. SLSH is essentially a dual-level hierarchical LSH where each LSH layer is associated with a distinct distance metric capturing a unique facet of similarity. The second shortcoming and the main bottleneck of the generic LSH is that it involves exhaustive distance calculations as a subroutine when short-listing the candidate set to find the final nearest neighbors. To surmount this, we propose Collision Frequency LSH (CFLSH) which short-lists the candidate set by simply counting the frequency of collision based on the key idea that the more frequently an element and a query collide across multiple LSH hash tables, the more similar they are. We show that with SLSH and CFLSH, we improve the efficiency of LSH in terms of both prediction accuracy and querying speed. We demonstrate our proposed methods on a mean arterial blood pressure dataset extracted from the MIMIC II database in the context of predicting acute hypotensive episodes in ICU. To examine the generality of our methods with respect to scaling, we validate our methods on datasets with various dimensions and item counts.
by Yongwook Bryce Kim.
Ph. D.