In spite of increasingly sophisticated workforce management tools, a significant gap remains between the goal of effective staffing and the present difficulty predicting the stochastic demand of inbound calls. We have investigated the hypothesized nonhomogeneous Poisson process model of modem pool callers of the University community. In our case, we tested if the arrivals could be approximated by a piecewise constant rate over short intervals. For each of 1 and 10-minute intervals, based on the close relationship between the Poisson process and the exponential distribution, the test results did not show any sign of homogeneous Poisson process. We have examined the hypothesis of a nonhomogeneous Poisson process by a transformed statistic. Quantitative and graphical goodness-of-fit tests have confirmed nonhomogeneous Poisson process. <p>Further analysis on the intensity function revealed that linear rate intensity was woefully inadequate in predicting time varying arrivals. For sinusoidal rate model, difficulty arose in setting the period parameter. Spline models, as an alternative to parametric modelling, had more control of balance between data fitting and smoothness, which was appealing to our analysis on call arrival process.

<p>This dissertation is a collection of essays with the main objective of estimate and understand macroeconomic behavior of emerging countries by the lenses of modern tools in general equilibrium modeling.</p><p>In the first chapter, I study whether structural parameters of Small Open Economy Real Business Cycle models are constant when applied to Emerging Markets data. Using data from Argentina, I estimate a small open economy model with trend shocks and working capital constraints, augmented with time varying parameters. I find that so called ``structural" parameters suffer substantial changes in the period 1983-2008. Structural instabilities arise from both technological and financial sources. Given these findings, I inquire which are the features of the data that parameter drifts capture. I review emerging markets facts and find parameter instabilities play a key role in addressing for the variability observed in the data.</p><p>In the second chapter, I study policy changes in emerging countries. Motivated by the repeated stabilization programs implemented by emerging economies during the last 30 years, I develop a dynamic stochastic general equilibrium model with Markov-Switching to study fiscal and monetary policies in emerging economies. I estimate the model for Mexico and find strong evidence of policy changes. Two Regimes are identified. The Active Monetary Policy Regime (AMP), in which monetary and fiscal policies respond to inflation and government debt, respectively; and the Active Fiscal Policy Regime (AFP), in which fiscal policy does not respond to government debt and monetary policy does not respond to inflation. AMP holds during short periods of time after macroeconomic crises during the 80s and 90s, and for a long period after 2002. The rest of the periods, AFP is in effect. I find that switches from AFP to AMP have strong stabilization effects at the cost of high output losses. Moreover, credibility in the persistence of the regime change is key to assess the effectiveness of the stabilization program.</p> / Dissertation

"none"

This thesis concerns stability analysis and robust H¡Û performance analysis for discrete-time systems with interval time-varying delay; moreover, the results are extended to the systems with norm-bounded uncertainties. By defining a novel Lyapunov functional and combining delay partition methods to improve the results in existing literature, we obtain a less conservative linear matrix inequality condition to guarantee the asymptotic stability for the discrete-time systems. There are examples to illustrate the advantage of our method in every chapter.

The Great Moderation means the reduction in the volatility of aggregate economic activity and here we use GDP growth rate to stand for economic activity. In this paper, we apply a Markov switching model to estimate the timing of the Great Moderation in France. Subsequently, by using a Time-varying structural vector autoregression model to determine which are the main variables that cause the reduction of French GDP growth rate and to see the relationship of these variables we choose.

Novel methods of system identification are developed in this dissertation. First set of methods are designed to realize time varying linear dynamical system models from input-output experimental data. The preliminary results obtained in a recent paper by the author are extended to establish a new algorithm called the Time Varying Eigensystem Realization Algorithm (TVERA). The central aim of this algorithm is to obtain a linear, time varying, discrete time model sequence of the dynamic system directly from the input-output data. Important results relating to concepts concerning coordinate systems for linear time varying systems are developed (discrete time theory) and an intuitive understanding of equivalent realizations is provided. A procedure to develop first few time step models is detailed, providing a unified solution to the time varying identification problem. The practical problem of identifying the time varying generalized Markov parameters required for TVERA is presented as the next result. In the process, we generalize the classical time invariant input output AutoRegressive model with an eXogenous input (ARX) models to the time varying case and realize an asymptotically stable observer as a byproduct of the calculations. It is further found that the choice of the generalized time varying ARX model (GTV-ARX) can be set to realize a time varying dead beat observer. Methods to use the developed algorithm(s) in this research are then considered for application to the identification of system models that are bilinear in nature. The fact that bilinear plant models become linear for constant inputs is used in the development of an algorithm that generalizes the classical developments of Juang. An intercept problem is considered as a candidate for application of the time varying identification scheme, where departure motion dynamics model sequence is calculated about a nominal trajectory with suboptimal performance owing to the presence of unstructured perturbations. Control application is subsequently demonstrated. The dynamics of a particle in a rotating tube is considered next for identification using the time varying eigensystem realization algorithm. Continuous time bilinear system identification method is demonstrated using the particle example and the identification of an automobile brake model.

Abstract¡G This thesis mainly implemented an RF transmitter with high efficiency and high linearity. A Cartesian to Polar transformation was implemented by CORDIC algorithm using FPGA. By replacing the envelope detector and limiter in traditional envelope elimination and restoration transmitter, this technique not only achieves more accurate modulation quality, but also becomes more suitable for single chip system. Applying the first order delta-sigma modulation and highly efficient switching-mode DC converter, the envelope signal was amplified highly efficiently. Due to the class-E power amplifier having good linear relation between output voltage and supply voltage, the polar modulation transmitter can achieve high efficiency and high linearity simultaneously. Furthermore, this thesis purposed a new transmitter with two-terminal time-varying modulation. The IQ modulated signal was fed to the input terminal of class-E amplifier, while the envelope signal was used to amplitude modulate the voltage supply terminal. With dynamic input power control, the conversion efficiency and linearity are independent of output power in the purposed architecture. From the experimental results, while transmitting a QPSK-modulated CDMA2000 1x signal with 1.2288 Msps data rate, the transmitter achieve 48 % in drain efficiency, 47 dB in ACPR, and 6 % in EVM at the output power ranging from 10 to 22 dBm.

The direct sequence (DS) code division multiple access (CDMA) is one of the most promising multiplexing technologies for wireless communications. It is also a core technology used in the wideband CDMA (WCDMA) system for the third generation (3G) wireless communication systems. In practice, in the CDMA systems the incomplete orthogonal of the spreading codes between users may introduce the so-called multiple access interference (MAI). Usually, the near-far problem exists when the interfering users are assigned powers much higher than the desired user. Such that the system performance might degrade, dramatically, and thus limits the system capacity. To circumvent the above-mentioned problems many effective adaptive multiuser detectors, based on the minimum mean square error (MMSE) and the minimum output energy (MOE) criteria subject to certain constraints have been proposed. In addition, to mitigate multipath fading effect, RAKE receiver was adopted due to the advantages of path diversity, thus, enhances the system performance. To implement the blind adaptive multiuser detector the linearly constrained minimum variance (LCMV), which is the constrained version of MOE, has been suggested. Further, the LCMV-based receivers exhibit high sensitivity to the channel mismatch caused by the unreliable estimation. To deal with this problem the constant modulus (CM) criterion was considered. In this dissertation, to deal with diverse phenomena encountered in practical channels, we first propose new blind adaptive multi-user detectors, based on the Min/Max criterion associated with the LCCM approach. For implementation the LC exponential window (EW) recursive least-square (RLS) algorithm is derived, and is referred to as the EW LCCM-RLS receiver. It can be used to effectively suppress the MAI and ISI, simultaneously, over multipath fading channels and are robust to mismatch problem caused by inaccuracies in the acquisition of timing and spreading code of the desired user. To reduce the complexity of the above-mentioned blind adaptive multi-user receiver with the LCCM-RLS algorithm, the so-called generalized sidelobe-canceller (GSC) structure is adopted, results in obtaining new CM-GSC-RLS algorithm. Moreover, to further improve the system performance for multipath fading and time-varying channel, the sliding window (SW) LCCM-RLS and SW CM-GSC-RLS algorithms are developed. It can be employed for multipath fading channel with the rapidly changing strong narrowband interference (NBI), which is joined suddenly to the CDMA systems. To look more inside the effect of selecting the initial value of the input signals autocorrelation matrix, some theoretical analyses for the SW LC-RLS as well as EW LC-RLS are provided. Since, unfortunately, the LCCM criterion is known to highly depend on the exact knowledge of the desired user amplitude that is not known exactly at receiver. In the final of this dissertation, a novel linearly constrained adaptive constant modulus RLS (LC-ACM-RLS) algorithm for blind DS-CDMA receiver is proposed. With this new proposed LC-ACM-RLS algorithm, the amplitude variation of the desired user, due to changing characteristics of the channel, can be tracked adaptively. Thus, better performance achievement, in terms of output signal-to-interference-plus-noise ratio (SINR) and bit error rate (BER), over the conventional LCCM-LMS and LCCM-RLS algorithms can be expected.

Intelligent Transport Systems (ITS) are becoming a part of our daily lives in various forms of application. Their success depends highly on the accuracy of the digital data they use. In networks where characteristics change by time, time-based network analysis algorithms provide results that are more accurate. However, these analyses require time-based travel speed data to provide accurate results. Conventionally, traffic data are usually obtained using the data provided from loop-detectors. These detectors usually exist on main arteries, freeways and highways / they rarely exist on back roads, secondary roads and streets due to their deployment costs. Today, telematics systems offer fleet operators to track their fleet remotely from a central system. Those systems provide data about the behaviors of vehicles with time information. Therefore, a tracking system can be used as an alternative to detector-based systems on estimating travel speeds on networks. This study aims to provide methods to estimate network characteristics using the data collected directly from fleets consisting of global positioning system (GPS) receiver equipped vehicles. GIS technology is used to process the collected GPS data spatially to match digital road maps. After matching, time-dependent characteristics of roads on which tracked vehicles traveled are estimated. This estimation provides data to perform a time-dependent network analysis. The methods proposed in this study are tested on traffic network of Middle East Technical University campus. The results showed that the proposed methods are capable of measuring time-dependent link-travel times on the network. Peak hours through the network are clearly detected.

The purpose of this thesis is to derive and analyze the theoretical limits for estimatingthe symboltiming delayof Multiple-Input Multiple-Output (MIMO)systems. Two main N X M system models are considered, where N represents the number of transmit antennas and M denotes the number of receive antennas, the 2 X 2 system used by S.-A. Yangand J. Wu and the 4 X 4system used by Y.-C. Wu and E. Serpedin. The second model has been extended to take into account the symbol time-varying fading. The theoretical estimation limits are shown by several bounds: modified Cramer-Rao bound (MCRB), Cramer-Rao bound (CRB) and Barankin bound (BB). BB will be exploited to obtain accurate information regarding the necessary length of data to obtain good estimation. Two scenarios for synchronization are presented: data-aided (DA) and non-data-aided (NDA). Two models for the fading process are considered: block fading and symbol time-varying fading, respectively, the second case being assumed to be Rayleigh distributed. The asymptotic Cramer-Rao bounds for low signal-to-noise ratio (low-SNR) and for high-SNR are derived and the performance of several estimators is presented. The performance variation of bounds and estimators is studied byvarying different parameters, such as the number of antennas, the length of data taken into consideration during the estimation process, the SNR, the oversampling factor, the power and the Doppler frequency shift of the fading.