Search for: time-series
0.008 seconds
Total 159 records

    Determining the Optimal Level of Reserve in Power Systems with High Penetration of Wind Energy

    , M.Sc. Thesis Sharif University of Technology Riahinia, Shahin (Author) ; Abbaspour Tehrani Fard, Ali (Supervisor) ; Fotuhi-Firuzabad, Mahmud (Co-Advisor)
    Shortage in fossil fuels resources together with the pollution concerns have caused a systematic change in power system planners and decision makers policies to renewable energies as an alternative to produce electrical energy. However, some intrinsic features of the wind energy overshadow its profitability. Inability to predict the wind speed changes and consequently the output level of wind turbines, being an uncontrollable generation unit, and also being an intermittent unit can be accounted as the main attributes of renewable-based units. Taking into account these features, one can conclude that new challenges can be brought into existence in planning and operation issues of... 

    Exploiting Transfer Learning in Deep Neural Networks for Time Series

    , M.Sc. Thesis Sharif University of Technology Salami, Mohammad Sadegh (Author) ; Manzuri Shalmani, Mohammad Taghi (Supervisor)
    The importance of transfer learning in image-related problems comes from its many advantages that are sometimes undeniable. Previous researches have well shown the success of transfer learning in this area using deep neural networks. However, transfer learning for time series data has not yet been done in a conventional and automated manner. The main reason for avoiding transfer learning in this domain relates to the dynamic and stochastic nature of the time series, where they show a time-varying behavior. Previous experiments have shown that transfer learning between two heterogeneous time series could harm the forecasting accuracy of a model. Therefore, in this thesis, we aim to explore... 

    State Space Reconstruction with Application in Revealing the Nonlinear Dynamics of Brain

    , M.Sc. Thesis Sharif University of Technology Heydari, Mohammad Reza (Author) ; Tavazoei, Mohammad Saleh (Supervisor) ; Ghazazideh, Ali (Co-Supervisor)
    Learning is an essential mechanism for the survival of living things. There are different types of learning, and value learning is among the most important types. A child learns that water resolves the thirst need by repeatedly experiencing this situation. Eventually, the value of water, which has been valueless before that, increases gradually in his mind. How this concept is encoded in the brain? previous works reveal the role of different neurons and regions that are relevant to value learning. However, population analysis and dynamic modeling are less considered. Moreover, the links between different brain regions are unknown.Finding the relationship between two relevant regions of the... 

    Time Series Analysis Using Deep Neural Networks Based on DTW Kernels and its Application in Blood Pressure Estimation Using PPG Signals

    , M.Sc. Thesis Sharif University of Technology Ahmadi Mobarakeh, Mohammad (Author) ; Mohammadzadeh, Narjesolhoda (Supervisor)
    This work presents a modification of deep neural networks for time series analysis. We used kernel layer(s), as a novel approach, at the beginning of the common deep neural networks. These kernels learn based on dynamic time warping (DTW). In each kernel, DTW is calculated between the kernel value and a part of input time series or a part of last layer output (if the kernel is not in the first layer). DTW also gives an alignment path for the input series. This alignment path is used to defining a loss function with the goal of getting better alignment (lower DTW distance) between the kernel and the other input. Besides getting better accuracy on the examined datasets, the other achievement... 

    Forecasting Airline Demand by Using Hybric Bayesian Method and Time Series

    , M.Sc. Thesis Sharif University of Technology Shokouhi Seta, Hamid Reza (Author) ; Refie, Majid (Supervisor)
    Using revenue management in any industry can increase the profit. In aviation industries, due to the huge number of requests and travels for each airline, a revenue management system can lead to a good profit for the airlines. The first step in revenue management system is predicting the demand.In this article two models are developed using time series techniques, based on the information taken from one of the Iranian airlines in Tehran-Mashhad fly route.The first model is developed using ARIMA and seasonal-ARIMA models and the second one is based on the demand and price history, price in the day of prediction and the ARIMA model. The second model which is a combination of price, prior price... 

    Complex Dynamics of Epileptic Brain and Turbulence :From Time Series to Information Flow

    , Ph.D. Dissertation Sharif University of Technology Anvari, Mehrnaz (Author) ; Rahimi Tabar, Mohammad Reza (Supervisor) ; Karimipour, Vahid (Supervisor)
    Complex systems are composed of a large number of subsystems behaving in a collective manner. In such systems, which are usually far from equilibrium, collective behavior arises due to self-organization and results in the formation of temporal, spatial, spatio-temporal and functional structures. The dynamics of order parameters in complex systems are generally non-stationary and can interact with each other in nonlinear manner. As a result, the analysis of the behavior of complex systems must be based on the assessment of the nonlinear interactions, as well as the determination of the characteristics and the strength of the fluctuating forces. This leads to the problem of retrieving a... 

    Portfolio Formation Using Deep Learning

    , M.Sc. Thesis Sharif University of Technology Rabiee, Ali (Author) ; Manzuri, Mohammad Taghi (Supervisor)
    Throughout history, forming an optimal asset portfolio has been the primary goal of capital owners and managers of investment funds in any economic activity. Achieving this goal is equivalent to trying to minimize the risk caused by the inevitable fluctuations in the capital market and maximizing the overall investment return during the expected period. Investors can operate in various financial markets where there are different stocks and asset classes in each of these markets. The main goal of investors is to identify profitable stocks and form an optimal asset portfolio based on them.Based on this, during the past decades, many studies have been conducted to form and optimize the stock... 

    Feature Extraction for Financial Markets’ Transactions

    , M.Sc. Thesis Sharif University of Technology Karimi, Afshin (Author) ; Manzuri Shalmani, Mohammad Taghi (Supervisor)
    The use of machine learning and deep learning tools to predict the future behavior of trends in massive data requires the extraction and creation of the eigenvector for the chosen model in the problem. It should be noted that simply by increasing the number of features, it cannot be expected that the learning model will have a higher efficiency. Rather, the quality and importance of the features in the field under study should be carefully considered. Topics such as data redundancy, data correlation, the amount of information in the data, distorted data, outliers, etc. are important steps in improving the dataset and creating a feature vector for training the learning model. In the realm of... 

    OmpF, a nucleotide-sensing nanoprobe, computational evaluation of single channel activities

    , Article Physica A: Statistical Mechanics and its Applications ; Volume 457 , 2016 , Pages 215-224 ; 03784371 (ISSN) Haji Abdolvahab, R ; Mobasheri, H ; Nikouee, A ; Ejtehadi, M. R ; Sharif University of Technology
    Elsevier B.V  2016
    The results of highthroughput practical single channel experiments should be formulated and validated by signal analysis approaches to increase the recognition precision of translocating molecules. For this purpose, the activities of the single nano-pore forming protein, OmpF, in the presence of nucleotides were recorded in real time by the voltage clamp technique and used as a means for nucleotide recognition. The results were analyzed based on the permutation entropy of current Time Series (TS), fractality, autocorrelation, structure function, spectral density, and peak fraction to recognize each nucleotide, based on its signature effect on the conductance, gating frequency and voltage... 

    Chaos in the APFM nonlinear adaptive filter

    , Article Signal Processing ; Volume 89, Issue 5 , 2009 , Pages 697-702 ; 01651684 (ISSN) Tavazoei, M. S ; Haeri, M ; Sharif University of Technology
    In this paper, we show that an amplitude phase frequency model (APFM) which is used as a nonlinear adaptive filter in signal processing can exhibit chaotic behavior. It is illustrated that both frequency and amplitude of the input components have effect on the filter characteristics which can lead the filter to behave chaotically for some values of these parameters. We have exploited different measures such as the Lyapunov exponents, bifurcation diagram, sensitivity to initial condition, and 0-1 test on time series to confirm our claim. Existence of the chaotic behavior in APFM does not conform to the prior conjectures about this filter. © 2008 Elsevier B.V. All rights reserved  

    Analysis and data-driven reconstruction of bivariate jump-diffusion processes

    , Article Physical Review E ; Volume 100, Issue 6 , 2019 ; 24700045 (ISSN) Rydin Gorjao, L ; Heysel, J ; Lehnertz, K ; Rahimi Tabar, M. R ; Sharif University of Technology
    American Physical Society  2019
    We introduce the bivariate jump-diffusion process, consisting of two-dimensional diffusion and two-dimensional jumps, that can be coupled to one another. We present a data-driven, nonparametric estimation procedure of higher-order (up to 8) Kramers-Moyal coefficients that allows one to reconstruct relevant aspects of the underlying jump-diffusion processes and to recover the underlying parameters. The procedure is validated with numerically integrated data using synthetic bivariate time series from continuous and discontinuous processes. We further evaluate the possibility of estimating the parameters of the jump-diffusion model via data-driven analyses of the higher-order Kramers-Moyal... 

    Estimating structural damage of steel moment frames by Endurance Time method

    , Article Journal of Constructional Steel Research ; Volume 64, Issue 2 , 2008 , Pages 145-155 ; 0143974X (ISSN) Estekanchi, H. E ; Arjomandi, K ; Vafai, A ; Sharif University of Technology
    In Endurance Time (ET) method, structures are subjected to gradually intensifying accelerograms and their performance is judged based on the maximum time duration in which they can satisfy the predefined endurance criteria. Damage indexes are used in ET method as the endurance criteria. In this paper, correlation between the values of various damage indexes as obtained from nonlinear time-history analysis of steel moment frames subjected to scaled earthquakes are compared with those from ET method at the same level of spectral acceleration. It is shown that the average value of various damage indexes can be estimated from ET analysis results. Advantages, accuracy and limitations of this... 

    On the resolution of existing discontinuities in the dynamic responses of an Euler-Bernoulli beam subjected to the moving mass

    , Article 8th Biennial ASME Conference on Engineering Systems Design and Analysis, ESDA2006, Torino, 4 July 2006 through 7 July 2006 ; Volume 2006 , 2006 ; 0791837793 (ISBN); 9780791837795 (ISBN) Kargarnovin, M. H ; Saeedi, K ; Sharif University of Technology
    American Society of Mechanical Engineers  2006
    The dynamic response of a one-dimensional distributed parameter system subjected to a moving mass with constant speed is investigated. An Euler-Bernoulli beam with the uniform cross-section and finite length with specified boundary support conditions is assumed. In this paper, rather a new method based on the time dependent series expansion for calculating the bending moment and the shear force due to motion of the mass is suggested. Governing differential equations of the motion are derived and solved. The accuracy of the numerical results primarily is verified and further the rapid convergence of this new technique was illustrated over other existing methods. Finally, it is shown that a... 

    Developing a conjunctive nonlinear model for inflow prediction using wavelet transforms and artificial neural networks: A case study of Dez reservoir dam, Iran

    , Article Operations Management 2006, Sacramento, CA, 14 August 2006 through 16 August 2006 ; Volume 2006 , 2006 , Pages 69-78 ; 0784408750 (ISBN); 9780784408759 (ISBN) Mehdikhani, H ; Abrishamchi, A ; Khodaei, H ; Sharif University of Technology
    Dez reservoir dam is one of the famous dams in Khuzestan province in southwestern part of Iran. Operation of Dez reservoir dam and it's strategic position has an important role regard to providing country's net power, it's long precedence in operation, Dam dimension, multidisciplinary uses and existence of essential land use in downstream. Thus inflow forecasting could have a great role in effective operation of dam, flood non-structural and risk management by applying an effective flood warning. The more accurate the forecasting of inflow to reservoir will be results the less peak outflow and less risk to downstream. This paper presents a new Conjunctive nonlinear model using Wavelet... 

    Seizure detection in EEG signals: a comparison of different approaches

    , Article 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06, New York, NY, 30 August 2006 through 3 September 2006 ; 2006 , Pages 6724-6727 ; 05891019 (ISSN); 1424400325 (ISBN); 9781424400324 (ISBN) Mohseni, H. R ; Maghsoudi, A ; Shamsollahi, M. B ; Sharif University of Technology
    In this paper, the performance of traditional variance-based method for detection of epileptic seizures in EEG signals are compared with various methods based on nonlinear time series analysis, entropies, logistic regression, discrete wavelet transform and time frequency distributions. We noted that variance-based method in compare to the mentioned methods had the best result (100%) applied on the same database. © 2006 IEEE  

    Dimensional characterization of anesthesia dynamic in reconstructed embedding space

    , Article 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07, Lyon, 23 August 2007 through 26 August 2007 ; 2007 , Pages 6483-6486 ; 05891019 (ISSN) ; 1424407885 (ISBN); 9781424407880 (ISBN) Gifani, P ; Rabiee, H. R ; Hashemi, M. R ; Ghanbari, M ; Sharif University of Technology
    The depth of anesthesia quantification has been one of the most research interests in the field of EEG signal processing and nonlinear dynamical analysis has emerged as a novel method for the study of complex systems in the past few decades. In this investigation we use the concept of nonlinear time series analysis techniques to reconstruct the attractor of anesthesia from EEG signal which have been obtained from different hypnotic states during surgery to give a characterization of the dimensional complexity of EEG by Correlation Dimension estimation. The dimension of the anesthesia strange attractor can be thought of as a measure of the degrees of freedom or the 'complexity' of the... 

    Bootstrap-based Ensemble Clustering of Resting-state fMRI Time Series

    , M.Sc. Thesis Sharif University of Technology Ashtari, Pooya (Author) ; Vosoughi Vahdat, Bijan (Supervisor)
    Studies in recent years have shown formation of strongly functionally linked sub-networks during rest, networks that are often referred to as resting-state networks. RSNs not only have basic information about the brain but also play a key role in detecting brain disorders, such as Alzheimer and Autism; Consequently, they have been remarkably noticed by neuroscientists. Numerous methods have been used in order to extract RSNs using resting-states fMRI time series. Independent component analysis (ICA) is the most common method, whi have been reported to show a high level of consistency neurophysiology; however, its results is unstable in subject-level. is weakness restricted the ICA... 

    Comparison of artificial intelligence based techniques for short term load forecasting

    , Article Proceedings - 3rd International Conference on Business Intelligence and Financial Engineering, BIFE 2010, 13 August 2010 through 15 August 2010 ; 2010 , Pages 6-10 ; 9780769541167 (ISBN) Ghanbari, A ; Hadavandi, E ; Abbasian Naghneh, S ; Sharif University of Technology
    The past few years have witnessed a growing rate of attraction in adoption of Artificial Intelligence (AI) techniques to solve different engineering problems. Besides, Short Term Electrical Load Forecasting (STLF) is one of the important concerns of power systems and accurate load forecasting is vital for managing supply and demand of electricity. This study estimates short term electricity loads of Iran by means of Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Networks (ANN) and Genetic Algorithm (GA) which are the most successful AI techniques in this field. In order to improve forecasting accuracy, all AI techniques are equipped with preprocessing concept, and effects... 

    Forecasting models for flow and total dissolved solids in Karoun river-Iran

    , Article Journal of Hydrology ; Volume 535 , 2016 , Pages 148-159 ; 00221694 (ISSN) Salmani, M. H ; Salmani Jajaei, E ; Sharif University of Technology
    Water quality is one of the most important factors contributing to a healthy life. From the water quality management point of view, TDS (total dissolved solids) is the most important factor and many water developing plans have been implemented in recognition of this factor. However, these plans have not been perfect and very successful in overcoming the poor water quality problem, so there are a good volume of related studies in the literature. We study TDS and the water flow of the Karoun river in southwest Iran. We collected the necessary time series data from the Harmaleh station located in the river. We present two Univariate Seasonal Autoregressive Integrated Movement Average (ARIMA)... 

    On the existence of proper stochastic Markov models for statistical reconstruction and prediction of chaotic time series

    , Article Chaos, Solitons and Fractals ; Volume 123 , 2019 , Pages 373-382 ; 09600779 (ISSN) Jokar, M ; Salarieh, H ; Alasty, A ; Sharif University of Technology
    Elsevier Ltd  2019
    In this paper, the problem of statistical reconstruction and prediction of chaotic systems with unknown governing equations using stochastic Markov models is investigated. Using the time series of only one measurable state, an algorithm is proposed to design any orders of Markov models and the approach is state transition matrix extraction. Using this modeling, two goals are followed: first, using the time series, statistical reconstruction is performed through which the probability density and conditional probability density functions are reconstructed; and second, prediction is performed. For this problem, some estimators are required and here the maximum likelihood and the conditional...