Adrijan Baric

A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines

This paper presents a generic strategy for short-term load forecasting (STLF) based on the support vector regression machines (SVR). Two important improvements to the SVR based load forecasting method are introduced, i.e., procedure for generation of model inputs and subsequent model input selection using feature selection algorithms. One of the objectives of the proposed strategy is to reduce the operator interaction in the model-building procedure. The proposed use of feature selection algorithms for automatic model input selection and the use of the particle swarm global optimization based technique for the optimization of SVR hyper-parameters reduces the operator interaction. To confirm the effectiveness of the proposed modeling strategy, the model has been trained and tested on two publicly available and well-known load forecasting data sets and compared to the state-of-the-art STLF algorithms yielding improved accuracy.

Characterizing the TEM Cell Electric and Magnetic Field Coupling to PCB Transmission Lines

This paper presents the models of the coupling between the transverse electromagnetic (TEM) field generated in the TEM cell and the arbitrarily oriented microstrip (MS) lines and coplanar waveguides (CPW). The lines are modeled in the frequency and time domain by taking into account different geometries and two types of subminiature version A connectors. The method of lines is used to calculate the capacitance matrix for the MS and CPW lines inserted in the TEM cell. The capacitance matrix is then used to calculate the inductance matrix, i.e., self- and coupling inductances. A number of simulations are performed in order to obtain the set of capacitance and inductance matrices for various line geometries. These results are fitted by using linear regression models. The closed-form equations for the coupling parameters are derived. The closed-form equations are used for the evaluation of coupling of arbitrarily oriented lines. The coupling models are compared against the measurements and found to be very accurate and can be used for efficient coupling modeling between the MS and CPW lines and TEM cell.

Design and Optimization of Self-Biased Complementary Folded Cascode

This paper presents design and optimization procedure of a self-biased complementary folded cascade. A self-biased scheme is chosen as a technique that saves power and circuit area, and is less sensitive to process variations. The gain of basic folded cascode is enhanced using a gain boosting approach based on common source self-biased amplifiers. The circuits are optimized using the global optimization approach with the cost function calculated by circuit simulations. The hybrid approach to optimization is used combining the global search strategy using particle swarm optimization (PSO) and direct pattern search (DPS) method used as local search strategy. A complementary folded cascode operational amplifier is designed in the 0.35 mum CMOS technology with the 3.3 V power supply voltage

Recurrent sparse support vector regression machines trained by active learning in the time-domain

A method for the sparse solution of recurrent support vector regression machines is presented. The proposed method achieves a high accuracy versus complexity and allows the user to adjust the complexity of the resulting model. The sparse representation is guaranteed by limiting the number of training data points for the support vector regression method. Each training data point is selected based on the accuracy of the fully recurrent model using the active learning principle applied to the successive time-domain data. The user can adjust the training time by selecting how often the hyper-parameters of the algorithm should be optimised. The advantages of the proposed method are illustrated on several examples, and the experiments clearly show that it is possible to reduce the number of support vectors and to significantly improve the accuracy versus complexity of recurrent support vector regression machines.

Modeling of analog circuits by using support vector regression machines

The support vector regression method is used for modeling of electronic circuits. The method ensures simple, robust and accurate modeling of electronic circuits. It yields very good results for situations not specified in the learning data set, demonstrating very good generalization property of support vector machines. The method is applicable to modeling based on the measurements or device-level circuit simulations. Several GaAs circuits (buffer, resistive mixer, ring oscillator) are modeled using the proposed method.

Modelling of Electromagnetic Immunity of Integrated Circuits by Artificial Neural Networks

A simple and efficient method of modelling electromagnetic immunity (EMI) of integrated circuits (IC) with respect to conducted electromagnetic interference by using artificial neural networks (ANN) is presented. A pulse signal generator is controlled by an ANN to improve stability, robustness and accuracy of the model. A simple and effective way to obtain necessary data for learning the artificial neural network used in EMI modelling is presented. The methodology described in this paper ensures a simple, fast and accurate modelling. As a test case, the EMI model of conducted interference of a simple local interconnect network (LIN) interface circuit is presented.

Reducing Complexity of Echo State Networks with Sparse Linear Regression Algorithms

In this paper the use of sparse linear regression algorithms in echo state networks (ESN) is presented for reducing the number of readouts and improving the robustness and generalization properties of ESNs. Three data sets with overall 80 tests are used to validate the use of sparse linear regression algorithms for echo state networks. It is shown that it is possible to increase accuracy on the test data sets, not used in the ESN training phase, and in the same time reduce the overall number of the required readouts when compared to the standard approach of using ridge linear regression on the echo state network readouts.

Simple and Scalable Methodology for Equivalent Circuit Modeling of IC Packages

This paper presents a methodology for scalable modeling of IC packages by lumped element equivalent circuits. The response surface methodology is used for modeling of the IC package pins, lead frame, and bond wires, whereas the paddle is modeled as a pair of planes. The design of experiment (DOE) approach is used to systematically vary geometrical parameters of the simplified package structures, which are then simulated in a 3-D electromagnetic (EM) simulator. These simplified structures are used as building blocks of the IC packages and EM simulations of the simplified structures are used to build their parameterized equivalent circuit models. The extracted parameters of the equivalent circuit model form the response surface. Simple regression models are used for the response surface modeling. The model of the whole IC package is generated by cascading the models of the simplified structures. The range of the geometrical parameters used in the DOE is selected to cover a wide range of IC package geometries. The response surface models are verified against measurements performed on several IC package types and the accuracy is very good. The scalability and accuracy of the response surface models make this methodology suitable for modeling of a wide range of IC packages. The efficiency and accuracy of the presented models enable the statistical analysis of package performance with respect to package manufacturing parameters.

Sparse multikernel support vector regression machines trained by active learning

A method for the sparse multikernel support vector regression machines is presented. The proposed method achieves a high accuracy versus complexity ratio and allows the user to adjust the complexity of the resulting models. The sparse representation is guaranteed by limiting the number of training data points for the support vector regression method. Each training data point is selected based on its influence on the accuracy of the model using the active learning principle. A different kernel function is attributed to each training data point, yielding multikernel regressor. The advantages of the proposed method are illustrated on several examples and the experiments show the advantages of the proposed method.

Equivalent circuit model of the TEM cell electric and magnetic field coupling to microstrip lines

Electromagnetic compatibility (EMC) analysis of high-speed circuits is becoming mandatory due to the rapid increase in operating frequencies, RF interference and layout densities. Radiated susceptibility tests are important part of overall EMC analysis. In this paper the focus of investigation is on models of the coupling between a transverse electromagnetic (TEM) field generated by the TEM cell and the microstrip lines. In order to accurately model the coupling the models for microstrip lines, SMA connectors and TEM cell are developed. The coupling models are provided for transversal and longitudinal microstrip lines. The results for coupling capacitances are compared against results obtained by Method of Lines (MoL). The presented models are very accurate and include only passive elements, and therefore can be used for efficient coupling modelling between microstrip lines and the TEM cell septum.