Gas-liquid mass transfer in bubbly flow: Estimation of mass transfer, bubble size and reactor performance in various applications

Gas-liquid mass transfer is an important issue in the design and operation of many chemical unit operations. Despite its importance, the evaluation of gas-liquid mass transfer is not straightforward due to the complex nature of the phenomena involved. In this thesis gas-liquid mass transfer was evaluated in three different gas-liquid reactors in a traditional way by measuring the volumetric mass transfer coefficient (kLa). The studied reactors were a bubble column with a T-junction two-phase nozzle for gas dispersion, an industrial scale bubble column reactor for the oxidation of tetrahydroanthrahydroquinone and a concurrent downflow structured bed.The main drawback of this approach is that the obtained correlations give only the average volumetric mass transfer coefficient, which is dependent on average conditions. Moreover, the obtained correlations are valid only for the studied geometry and for the chemical system used in the measurements. In principle, a more fundamental approach is to estimate the interfacial area available for mass transfer from bubble size distributions obtained by solution of population balance equations. This approach has been used in this thesis by developing a population balance model for a bubble column together with phenomenological models for bubble breakage and coalescence. The parameters of the bubble breakage rate and coalescence rate models were estimated by comparing the measured and calculated bubble sizes. The coalescence models always have at least one experimental parameter. This is because the bubble coalescence depends on liquid composition in a way which is difficult to evaluate using known physical properties. The coalescence properties of some model solutions were evaluated by measuring the time that a bubble rests at the free liquid-gas interface before coalescing (the so-calledpersistence time or rest time). The measured persistence times range from 10 msup to 15 s depending on the solution. The coalescence was never found to be instantaneous. The bubble oscillates up and down at the interface at least a coupleof times before coalescence takes place. The measured persistence times were compared to coalescence times obtained by parameter fitting using measured bubble size distributions in a bubble column and a bubble column population balance model. For short persistence times, the persistence and coalescence times are in good agreement. For longer persistence times, however, the persistence times are at least an order of magnitude longer than the corresponding coalescence times from parameter fitting. This discrepancy may be attributed to the uncertainties concerning the estimation of energy dissipation rates, collision rates and mechanisms and contact times of the bubbles.

Performance analysis of near-far resistant CDMA detectors-influence of system parameter estimation errors

Little has been reported on the performance of near-far resistant CDMA detectors in the presence of system parameter estimation errors (SPEEs). Starting with the general mathematical model of matched filters, the paper examines the effects of three classes of SPEEs, i.e., time-delay, carrier phase, and carrier frequency errors, on the performance (BER) of an emerging type of near-far resistant coherent DS/SSMA detector, i.e., the linear decorrelating detector. For comparison, the corresponding results for the conventional detector are also presented. It is shown that the linear decorrelating detector can still maintain a considerable performance advantage over the conventional detector even when some SPEEs exist.

Bayesian Estimation for Performance Measures of Two Diagnostic Tests in the Presence of Verification Bias

Sensitivity and specificity are measures that allow us to evaluate the performance of a diagnostic test. In practice, it is common to have situations where a proportion of selected individuals cannot have the real state of the disease verified, since the verification could be an invasive procedure, as occurs with biopsy. This happens, as a special case, in the diagnosis of prostate cancer, or in any other situation related to risks, that is, not practicable, nor ethical, or in situations with high cost. For this case, it is common to use diagnostic tests based only on the information of verified individuals. This procedure can lead to biased results or workup bias. In this paper, we introduce a Bayesian approach to estimate the sensitivity and the specificity for two diagnostic tests considering verified and unverified individuals, a result that generalizes the usual situation based on only one diagnostic test.

HIGH PERFORMANCE, LOW COST SUBSPACE DECOMPOSITION AND POLYNOMIAL ROOTING FOR REAL TIME DIRECTION OF ARRIVAL ESTIMATION: ANALYSIS AND IMPLEMENTATION

This thesis develops high performance real-time signal processing modules for direction of arrival (DOA) estimation for localization systems. It proposes highly parallel algorithms for performing subspace decomposition and polynomial rooting, which are otherwise traditionally implemented using sequential algorithms. The proposed algorithms address the emerging need for real-time localization for a wide range of applications. As the antenna array size increases, the complexity of signal processing algorithms increases, making it increasingly difficult to satisfy the real-time constraints. This thesis addresses real-time implementation by proposing parallel algorithms, that maintain considerable improvement over traditional algorithms, especially for systems with larger number of antenna array elements. Singular value decomposition (SVD) and polynomial rooting are two computationally complex steps and act as the bottleneck to achieving real-time performance. The proposed algorithms are suitable for implementation on field programmable gated arrays (FPGAs), single instruction multiple data (SIMD) hardware or application specific integrated chips (ASICs), which offer large number of processing elements that can be exploited for parallel processing. The designs proposed in this thesis are modular, easily expandable and easy to implement. Firstly, this thesis proposes a fast converging SVD algorithm. The proposed method reduces the number of iterations it takes to converge to correct singular values, thus achieving closer to real-time performance. A general algorithm and a modular system design are provided making it easy for designers to replicate and extend the design to larger matrix sizes. Moreover, the method is highly parallel, which can be exploited in various hardware platforms mentioned earlier. A fixed point implementation of proposed SVD algorithm is presented. The FPGA design is pipelined to the maximum extent to increase the maximum achievable frequency of operation. The system was developed with the objective of achieving high throughput. Various modern cores available in FPGAs were used to maximize the performance and details of these modules are presented in detail. Finally, a parallel polynomial rooting technique based on Newton’s method applicable exclusively to root-MUSIC polynomials is proposed. Unique characteristics of root-MUSIC polynomial’s complex dynamics were exploited to derive this polynomial rooting method. The technique exhibits parallelism and converges to the desired root within fixed number of iterations, making this suitable for polynomial rooting of large degree polynomials. We believe this is the first time that complex dynamics of root-MUSIC polynomial were analyzed to propose an algorithm. In all, the thesis addresses two major bottlenecks in a direction of arrival estimation system, by providing simple, high throughput, parallel algorithms.

Perceived Video Quality Estimation from Spatial and Temporal Information Contents and Network Performance Parameters in IPTV

The paper proposes a model for estimation of perceived video quality in IPTV, taking as input both video coding and network Quality of Service parameters. It includes some fitting parameters that depend mainly on the information contents of the video sequences. A method to derive them from the Spatial and Temporal Information contents of the sequences is proposed. The model may be used for near real-time monitoring of IPTV video quality.

Simulation of academic performance rates, estimation of indicators of subjects and of a complete degree

The purpose of this paper is to present a program written in Matlab-Octave for the simulation of the time evolution of student curricula, i.e, how students pass their subjects along time until graduation. The program computes, from the simulations, the academic performance rates for the subjects of the study plan for each semester as well as the overall rates, which are a) the efficiency rate defined as the ratio of the number of students passing the exam to the number of students who registered for it and b) the success rate, defined as the ratio of the number of students passing the exam to the number of students who not only registered for it but also actually took it. Additionally, we compute the rates for the bachelor academic degree which are established for Spain by the National Quality Evaluation and Accreditation Agency (ANECA) and which are the graduation rate (measured as the percentage of students who finish as scheduled in the plan or taking an extra year) and the efficiency rate (measured as the percentage of credits which a student who graduated has really taken). The simulation is done in terms of the probabilities of passing all the subjects in their study plan. The application of the simulator to Polytech students in Madrid, where requirements for passing are specially stiff in first and second year subjects, is particularly relevant to analyze student cohorts and the probabilities of students finishing in the minimum of four years, or taking and extra year or two extra years, and so forth. It is a very useful tool when designing new study plans. The calculation of the probability distribution of the random variable "number of semesters a student has taken to complete the curricula and graduate" is difficult or even unfeasible to obtain analytically, and this is even truer when we incorporate uncertainty in parameter estimation. This is why we apply Monte Carlo simulation which not only provides illustration of the stochastic process but also a method for computation. The stochastic simulator is proving to be a useful tool for identification of the subjects most critical in the distribution of the number of semesters for curriculum vitae (CV) completion and subsequently for a decision making process in terms of CV planning and passing standards in the University. Simulations are performed through a graphical interface where also the results are presented in appropriate figures. The Project has been funded by the Call for Innovation in Education Projects of Universidad Politécnica de Madrid (UPM) through a Project of its school Escuela Técnica Superior de Ingenieros Industriales ETSII during the period September 2010-September 2011.

Uncertainty Estimation for Performance Evaluation of a Confocal Microscope as Metrology Equipment

Both in industry and research, the quality control of micrometric manufactured parts is based on the measurement of parameters whose traceability is sometimes difficult to guarantee. In some of these parts, the confocal microscopy shows great aptitudes to characterize a measurand qualitatively and quantitatively. The confocal microscopy allows the acquisition of 2D and 3D images that are easily manipulated. Nowadays, this equipment is manufactured by many different brands, each of them claiming a resolution probably not in accord to their real performance. The Laser Center (Technical University of Madrid) has a confocal microscope to verify the dimensions of the micro mechanizing in their own research projects. The present study pretends to confirm that the magnitudes obtained are true and reliable. To achieve this, a methodology for confocal microscope calibration is proposed, as well as an experimental phase for dimensionally valuing the equipment by 4 different standard positions, with its seven magnifications and the six objective lenses that the equipment currently has, in the x–y and z axis. From the results the uncertainty will be estimated along with an effect analysis of the different magnifications in each of the objective lenses.

Contributions to uncertainty reduction in the estimation of PV plants performance

Esta tesis doctoral presenta un procedimiento integral de control de calidad en centrales fotovoltaicas, que comprende desde la fase inicial de estimación de las expectativas de producción hasta la vigilancia del funcionamiento de la instalación una vez en operación, y que permite reducir la incertidumbre asociada su comportamiento y aumentar su fiabilidad a largo plazo, optimizando su funcionamiento. La coyuntura de la tecnología fotovoltaica ha evolucionado enormemente en los últimos años, haciendo que las centrales fotovoltaicas sean capaces de producir energía a unos precios totalmente competitivos en relación con otras fuentes de energía. Esto hace que aumente la exigencia sobre el funcionamiento y la fiabilidad de estas instalaciones. Para cumplir con dicha exigencia, es necesaria la adecuación de los procedimientos de control de calidad aplicados, así como el desarrollo de nuevos métodos que deriven en un conocimiento más completo del estado de las centrales, y que permitan mantener la vigilancia sobre las mismas a lo largo del tiempo. Además, los ajustados márgenes de explotación actuales requieren que durante la fase de diseño se disponga de métodos de estimación de la producción que comporten la menor incertidumbre posible. La propuesta de control de calidad presentada en este trabajo parte de protocolos anteriores orientados a la fase de puesta en marcha de una instalación fotovoltaica, y las complementa con métodos aplicables a la fase de operación, prestando especial atención a los principales problemas que aparecen en las centrales a lo largo de su vida útil (puntos calientes, impacto de la suciedad, envejecimiento…). Además, incorpora un protocolo de vigilancia y análisis del funcionamiento de las instalaciones a partir de sus datos de monitorización, que incluye desde la comprobación de la validez de los propios datos registrados hasta la detección y el diagnóstico de fallos, y que permite un conocimiento automatizado y detallado de las plantas. Dicho procedimiento está orientado a facilitar las tareas de operación y mantenimiento, de manera que se garantice una alta disponibilidad de funcionamiento de la instalación. De vuelta a la fase inicial de cálculo de las expectativas de producción, se utilizan los datos registrados en las centrales para llevar a cabo una mejora de los métodos de estimación de la radiación, que es la componente que más incertidumbre añade al proceso de modelado. El desarrollo y la aplicación de este procedimiento de control de calidad se han llevado a cabo en 39 grandes centrales fotovoltaicas, que totalizan una potencia de 250 MW, distribuidas por varios países de Europa y América Latina. ABSTRACT This thesis presents a comprehensive quality control procedure to be applied in photovoltaic plants, which covers from the initial phase of energy production estimation to the monitoring of the installation performance, once it is in operation. This protocol allows reducing the uncertainty associated to the photovoltaic plants behaviour and increases their long term reliability, therefore optimizing their performance. The situation of photovoltaic technology has drastically evolved in recent years, making photovoltaic plants capable of producing energy at fully competitive prices, in relation to other energy sources. This fact increases the requirements on the performance and reliability of these facilities. To meet this demand, it is necessary to adapt the quality control procedures and to develop new methods able to provide a more complete knowledge of the state of health of the plants, and able to maintain surveillance on them over time. In addition, the current meagre margins in which these installations operate require procedures capable of estimating energy production with the lower possible uncertainty during the design phase. The quality control procedure presented in this work starts from previous protocols oriented to the commissioning phase of a photovoltaic system, and complete them with procedures for the operation phase, paying particular attention to the major problems that arise in photovoltaic plants during their lifetime (hot spots, dust impact, ageing...). It also incorporates a protocol to control and analyse the installation performance directly from its monitoring data, which comprises from checking the validity of the recorded data itself to the detection and diagnosis of failures, and which allows an automated and detailed knowledge of the PV plant performance that can be oriented to facilitate the operation and maintenance of the installation, so as to ensure a high operation availability of the system. Back to the initial stage of calculating production expectations, the data recorded in the photovoltaic plants is used to improved methods for estimating the incident irradiation, which is the component that adds more uncertainty to the modelling process. The development and implementation of the presented quality control procedure has been carried out in 39 large photovoltaic plants, with a total power of 250 MW, located in different European and Latin-American countries.

Development of Cookstove Emissions and Performance Testing Suite with Time-resolved Particulate Matter Analysis and Excess Air Estimation

Thesis (Master's)--University of Washington, 2016-06

Performance Comparison of MATLAB and Neuro Solution Software on Estimation of Fuel Economy by Using Artificial Neural Network

In the world, scientific studies increase day by day and computer programs facilitate the human’s life. Scientists examine the human’s brain’s neural structure and they try to be model in the computer and they give the name of artificial neural network. For this reason, they think to develop more complex problem’s solution. The purpose of this study is to estimate fuel economy of an automobile engine by using artificial neural network (ANN) algorithm. Engine characteristics were simulated by using “Neuro Solution” software. The same data is used in MATLAB to compare the performance of MATLAB is such a problem and show its validity. The cylinder, displacement, power, weight, acceleration and vehicle production year are used as input data and miles per gallon (MPG) are used as target data. An Artificial Neural Network model was developed and 70% of data were used as training data, 15% of data were used as testing data and 15% of data is used as validation data. In creating our model, proper neuron number is carefully selected to increase the speed of the network. Since the problem has a nonlinear structure, multi layer are used in our model.

High performance shift invariant motion estimation and compensation in wavelet domain video compression

The contributions of this dissertation are in the development of two new interrelated approaches to video data compression: (1) A level-refined motion estimation and subband compensation method for the effective motion estimation and motion compensation. (2) A shift-invariant sub-decimation decomposition method in order to overcome the deficiency of the decimation process in estimating motion due to its shift-invariant property of wavelet transform. ^ The enormous data generated by digital videos call for an intense need of efficient video compression techniques to conserve storage space and minimize bandwidth utilization. The main idea of video compression is to reduce the interpixel redundancies inside and between the video frames by applying motion estimation and motion compensation (MEMO) in combination with spatial transform coding. To locate the global minimum of the matching criterion function reasonably, hierarchical motion estimation by coarse to fine resolution refinements using discrete wavelet transform is applied due to its intrinsic multiresolution and scalability natures. ^ Due to the fact that most of the energies are concentrated in the low resolution subbands while decreased in the high resolution subbands, a new approach called level-refined motion estimation and subband compensation (LRSC) method is proposed. It realizes the possible intrablocks in the subbands for lower entropy coding while keeping the low computational loads of motion estimation as the level-refined method, thus to achieve both temporal compression quality and computational simplicity. ^ Since circular convolution is applied in wavelet transform to obtain the decomposed subframes without coefficient expansion, symmetric-extended wavelet transform is designed on the finite length frame signals for more accurate motion estimation without discontinuous boundary distortions. ^ Although wavelet transformed coefficients still contain spatial domain information, motion estimation in wavelet domain is not as straightforward as in spatial domain due to the shift variance property of the decimation process of the wavelet transform. A new approach called sub-decimation decomposition method is proposed, which maintains the motion consistency between the original frame and the decomposed subframes, improving as a consequence the wavelet domain video compressions by shift invariant motion estimation and compensation. ^

Development of safety performance functions for empirical Bayes estimation of crash reduction factors

Crash reduction factors (CRFs) are used to estimate the potential number of traffic crashes expected to be prevented from investment in safety improvement projects. The method used to develop CRFs in Florida has been based on the commonly used before-and-after approach. This approach suffers from a widely recognized problem known as regression-to-the-mean (RTM). The Empirical Bayes (EB) method has been introduced as a means to addressing the RTM problem. This method requires the information from both the treatment and reference sites in order to predict the expected number of crashes had the safety improvement projects at the treatment sites not been implemented. The information from the reference sites is estimated from a safety performance function (SPF), which is a mathematical relationship that links crashes to traffic exposure. The objective of this dissertation was to develop the SPFs for different functional classes of the Florida State Highway System. Crash data from years 2001 through 2003 along with traffic and geometric data were used in the SPF model development. SPFs for both rural and urban roadway categories were developed. The modeling data used were based on one-mile segments that contain homogeneous traffic and geometric conditions within each segment. Segments involving intersections were excluded. The scatter plots of data show that the relationships between crashes and traffic exposure are nonlinear, that crashes increase with traffic exposure in an increasing rate. Four regression models, namely, Poisson (PRM), Negative Binomial (NBRM), zero-inflated Poisson (ZIP), and zero-inflated Negative Binomial (ZINB), were fitted to the one-mile segment records for individual roadway categories. The best model was selected for each category based on a combination of the Likelihood Ratio test, the Vuong statistical test, and the Akaike's Information Criterion (AIC). The NBRM model was found to be appropriate for only one category and the ZINB model was found to be more appropriate for six other categories. The overall results show that the Negative Binomial distribution model generally provides a better fit for the data than the Poisson distribution model. In addition, the ZINB model was found to give the best fit when the count data exhibit excess zeros and over-dispersion for most of the roadway categories. While model validation shows that most data points fall within the 95% prediction intervals of the models developed, the Pearson goodness-of-fit measure does not show statistical significance. This is expected as traffic volume is only one of the many factors contributing to the overall crash experience, and that the SPFs are to be applied in conjunction with Accident Modification Factors (AMFs) to further account for the safety impacts of major geometric features before arriving at the final crash prediction. However, with improved traffic and crash data quality, the crash prediction power of SPF models may be further improved.

Prospective Estimation of Radiation Dose and Image Quality for Optimized CT Performance

X-ray computed tomography (CT) is a non-invasive medical imaging technique that generates cross-sectional images by acquiring attenuation-based projection measurements at multiple angles. Since its first introduction in the 1970s, substantial technical improvements have led to the expanding use of CT in clinical examinations. CT has become an indispensable imaging modality for the diagnosis of a wide array of diseases in both pediatric and adult populations [1, 2]. Currently, approximately 272 million CT examinations are performed annually worldwide, with nearly 85 million of these in the United States alone [3]. Although this trend has decelerated in recent years, CT usage is still expected to increase mainly due to advanced technologies such as multi-energy [4], photon counting [5], and cone-beam CT [6].

Despite the significant clinical benefits, concerns have been raised regarding the population-based radiation dose associated with CT examinations [7]. From 1980 to 2006, the effective dose from medical diagnostic procedures rose six-fold, with CT contributing to almost half of the total dose from medical exposure [8]. For each patient, the risk associated with a single CT examination is likely to be minimal. However, the relatively large population-based radiation level has led to enormous efforts among the community to manage and optimize the CT dose.

As promoted by the international campaigns Image Gently and Image Wisely, exposure to CT radiation should be appropriate and safe [9, 10]. It is thus a responsibility to optimize the amount of radiation dose for CT examinations. The key for dose optimization is to determine the minimum amount of radiation dose that achieves the targeted image quality [11]. Based on such principle, dose optimization would significantly benefit from effective metrics to characterize radiation dose and image quality for a CT exam. Moreover, if accurate predictions of the radiation dose and image quality were possible before the initiation of the exam, it would be feasible to personalize it by adjusting the scanning parameters to achieve a desired level of image quality. The purpose of this thesis is to design and validate models to quantify patient-specific radiation dose prospectively and task-based image quality. The dual aim of the study is to implement the theoretical models into clinical practice by developing an organ-based dose monitoring system and an image-based noise addition software for protocol optimization.

More specifically, Chapter 3 aims to develop an organ dose-prediction method for CT examinations of the body under constant tube current condition. The study effectively modeled the anatomical diversity and complexity using a large number of patient models with representative age, size, and gender distribution. The dependence of organ dose coefficients on patient size and scanner models was further evaluated. Distinct from prior work, these studies use the largest number of patient models to date with representative age, weight percentile, and body mass index (BMI) range.

With effective quantification of organ dose under constant tube current condition, Chapter 4 aims to extend the organ dose prediction system to tube current modulated (TCM) CT examinations. The prediction, applied to chest and abdominopelvic exams, was achieved by combining a convolution-based estimation technique that quantifies the radiation field, a TCM scheme that emulates modulation profiles from major CT vendors, and a library of computational phantoms with representative sizes, ages, and genders. The prospective quantification model is validated by comparing the predicted organ dose with the dose estimated based on Monte Carlo simulations with TCM function explicitly modeled.

Chapter 5 aims to implement the organ dose-estimation framework in clinical practice to develop an organ dose-monitoring program based on a commercial software (Dose Watch, GE Healthcare, Waukesha, WI). In the first phase of the study we focused on body CT examinations, and so the patient’s major body landmark information was extracted from the patient scout image in order to match clinical patients against a computational phantom in the library. The organ dose coefficients were estimated based on CT protocol and patient size as reported in Chapter 3. The exam CTDIvol, DLP, and TCM profiles were extracted and used to quantify the radiation field using the convolution technique proposed in Chapter 4.

With effective methods to predict and monitor organ dose, Chapters 6 aims to develop and validate improved measurement techniques for image quality assessment. Chapter 6 outlines the method that was developed to assess and predict quantum noise in clinical body CT images. Compared with previous phantom-based studies, this study accurately assessed the quantum noise in clinical images and further validated the correspondence between phantom-based measurements and the expected clinical image quality as a function of patient size and scanner attributes.

Chapter 7 aims to develop a practical strategy to generate hybrid CT images and assess the impact of dose reduction on diagnostic confidence for the diagnosis of acute pancreatitis. The general strategy is (1) to simulate synthetic CT images at multiple reduced-dose levels from clinical datasets using an image-based noise addition technique; (2) to develop quantitative and observer-based methods to validate the realism of simulated low-dose images; (3) to perform multi-reader observer studies on the low-dose image series to assess the impact of dose reduction on the diagnostic confidence for multiple diagnostic tasks; and (4) to determine the dose operating point for clinical CT examinations based on the minimum diagnostic performance to achieve protocol optimization.

Chapter 8 concludes the thesis with a summary of accomplished work and a discussion about future research.

Novel methods of state estimation and parameter identification for high-performance motorcycles

This research activity aims at providing a reliable estimation of particular state variables or parameters concerning the dynamics and performance optimization of a MotoGP-class motorcycle, integrating the classical model-based approach with new methodologies involving artificial intelligence. The first topic of the research focuses on the estimation of the thermal behavior of the MotoGP carbon braking system. Numerical tools are developed to assess the instantaneous surface temperature distribution in the motorcycle's front brake discs. Within this application other important brake parameters are identified using Kalman filters, such as the disc convection coefficient and the power distribution in the disc-pads contact region. Subsequently, a physical model of the brake is built to estimate the instantaneous braking torque. However, the results obtained with this approach are highly limited by the knowledge of the friction coefficient (μ) between the disc rotor and the pads. Since the value of μ is a highly nonlinear function of many variables (namely temperature, pressure and angular velocity of the disc), an analytical model for the friction coefficient estimation appears impractical to establish. To overcome this challenge, an innovative hybrid solution is implemented, combining the benefit of artificial intelligence (AI) with classical model-based approach. Indeed, the disc temperature estimated through the thermal model previously implemented is processed by a machine learning algorithm that outputs the actual value of the friction coefficient thus improving the braking torque computation performed by the physical model of the brake. Finally, the last topic of this research activity regards the development of an AI algorithm to estimate the current sideslip angle of the motorcycle's front tire. While a single-track motorcycle kinematic model and IMU accelerometer signals theoretically enable sideslip calculation, the presence of accelerometer noise leads to a significant drift over time. To address this issue, a long short-term memory (LSTM) network is implemented.

An Embedded In-Cabin Lightweight High-Performance 3D Gaze Estimation System

Gaze estimation has gained interest in recent years for being an important cue to obtain information about the internal cognitive state of humans. Regardless of whether it is the 3D gaze vector or the point of gaze (PoG), gaze estimation has been applied in various fields, such as: human robot interaction, augmented reality, medicine, aviation and automotive. In the latter field, as part of Advanced Driver-Assistance Systems (ADAS), it allows the development of cutting-edge systems capable of mitigating road accidents by monitoring driver distraction. Gaze estimation can be also used to enhance the driving experience, for instance, autonomous driving. It also can improve comfort with augmented reality components capable of being commanded by the driver's eyes. Although, several high-performance real-time inference works already exist, just a few are capable of working with only a RGB camera on computationally constrained devices, such as a microcontroller. This work aims to develop a low-cost, efficient and high-performance embedded system capable of estimating the driver's gaze using deep learning and a RGB camera. The proposed system has achieved near-SOTA performances with about 90% less memory footprint. The capabilities to generalize in unseen environments have been evaluated through a live demonstration, where high performance and near real-time inference were obtained using a webcam and a Raspberry Pi4.