Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Neural networks

A microwave method based on complementary split-ring resonators (CSRRs) is proposed for dielectric characterization of planar materials. The technique presents advantages such as high measurement sensitivity and eliminates the extensive sample preparation procedure needed in resonance-based methods. A sensor in the shape of CSRRs working at a 0.8-1.3 GHz band is demonstrated. The sensor is etched in the ground plane of a microstrip line to effectively create a stopband filter. The frequencies at which minimum transmission and minimum reflection are observed depend on the permittivity of the sample under test. The minimum transmission frequency shifts from 1.3 to 0.8 GHz as the sample permittivity changes from 1 to 10. The structure is fabricated using printed circuit board technology. Numerical findings are experimentally verified.

Material Characterization Using Complementary Split-Ring Resonators

Microelectromechanical Systems. Fundamental MEMS Device Physics. Fundamental MEMS Devices: The MEMS Switch. Fundamental MEMS Devices: The MEM Resonator. Microwave MEMS Applications. MEMS-Based Microwave Circuits and Systems.

Introduction to Microelectromechanical(MEM)Microwave Systems

This paper presents and evaluates artificial neural network (ANN) models used for macrocell path-loss prediction. Measurement data obtained by utilizing the IS-95 pilot signal from a commercial code-division multiple-access (CDMA) mobile network in rural Australia are used to train and evaluate the models. A simple neuron model and feed-forward networks with different numbers of hidden layers and neurons are evaluated regarding their training time, prediction accuracy, and generalization properties. Furthermore, different backpropagation training algorithms, such as gradient descent and Levenberg-Marquardt, are evaluated. The artificial neural network inputs are chosen to be distance to base station, parameters easily obtained from terrain path profiles, land usage, and vegetation type and density near the receiving antenna. The path-loss prediction results obtained by using the ANN models are evaluated against different versions of the semi-terrain based propagation model Recommendation ITU-R P.1546 and the Okumura-Hata model. The statistical analysis shows that a non-complex ANN model performs very well compared with traditional propagation models with regard to prediction accuracy, complexity, and prediction time. The average ANN prediction results were 1) maximum error: 22 dB; 2) mean error: 0 dB; and 3) standard deviation: 7 dB. A multilayered feed-forward network trained using the standard backpropagation algorithm was compared with a neuron model trained using the Levenberg-Marquardt algorithm. It was found that the training time decreases from 150 000 to 10 iterations, while the prediction accuracy is maintained.

/pdf/macrocell-path-loss-prediction-using-artificial-neural-3xx7nmhkqk.pdf

Macrocell Path-Loss Prediction Using Artificial Neural Networks

A novel method to provide high-resolution TwoDimensional Direction of Arrival (2D DOA) estimation employing Artificial Neural Networks (ANNs) is presented in this paper. The observed space is divided into azimuth and elevation sectors. Multilayer Perceptron (MLP) neural networks are employed to detect the presence of a source in a sector while Radial Basis Function (RBF) neural networks are utilized for DOA estimation. It is shown that a number of appropriately trained neural networks can be successfully used for the high-resolution DOA estimation of narrowband sources in both azimuth and elevation. The training time of each smaller network is significantly reduced as different training sets are used for networks in detection and estimation stage. By avoiding the spectral search, the proposed method is suitable for real-time applications as it provides DOA estimates in a matter of seconds. At the same time, it demonstrates the accuracy comparable to that of the super-resolution 2D MUSIC algorithm.

Application of Artificial Neural Networks for Efficient High-Resolution 2D DOA Estimation

The modeling of the cylindrical metallic cavity with circular cross-section loaded by lossy dielectric sample of various geometric shapes is done by using the Transmission-Line Matrix (TLM) method For modeling purposes, a hybrid symmetrical condensed node (HSCN) in cylindrical coordinates, developed and implemented in the appropriate software, is applied The proposed TLM models for several characteristic geometric shapes of the lossy dielectric sample are described in detail, the modeling process is discussed and the influence of the load form on the resonant frequencies of the cavity is investigated In addition, the applied TLM approach is experimentally verified for two cases of cavity load form

TLM modeling of the circular cylindrical cavity loaded by lossy dielectric sample of various geometric shapes.

This article describes an implementation of a compact wire model into the three-dimensional transmission-line matrix (TLM) cylindrical mesh for the purpose of an efficient analysis of probe-coupled cylindrical microwave cavity devices. Because of a cylindrical grid structure and empirical nature of the compact model, this implementation has to take into account a change of wire model parameters with a variable cross section of the TLM nodes through which a wire conductor passes. The model accuracy has been experimentally verified and compared with the corresponding results reached by the TLM method based on a rectangular grid in order to consider its advantages. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2012. © 2012 Wiley Periodicals, Inc.

TLM modeling of a probe-coupled cylindrical cavity based on compact wire model in the cylindrical mesh

The detailed research, full development, and experimental realization of a new printed antenna array with cosecant squared-shaped beam pattern are presented. Some advantages of proposed antenna, as compared to previously realized microstrip cosecant-squared pattern antennas, are pointed out. The suggested antenna, which targets X frequency range, has significantly better bandwidth characteristics thanks to its symmetrical radiating elements of pentagonal shape. The symmetrical feeding network of impedance transformers provides necessary amplitude's and phase's distributions obtained by Orchard Elliott's methods and genetic algorithm. Furthermore, it is on the same substrate as antenna, making entire concept simple, easy, and cheap for realization. Moreover, the antenna is in a corner reflector, which enables achieving relatively high gain. The proposed antenna is validated by simulations and measurements. The measured radiation pattern barely varies from theoretical radiation pattern. Realized antenna has gain above 15 dBi and sidelobe suppression greater than 20 dB at the center frequency of 10 GHz.

Design, Realization, and Measurements of a Corner Reflector Printed Antenna Array With Cosecant Squared-Shaped Beam Pattern

This paper presents a new type of turnstile antenna, realized with two crossed dipoles connected in parallel. Feeding of the dipoles in phase quadrature to obtain an omnidirectional radiation pattern is achieved by optimizing their impedances to be complex conjugates. The dipoles are realized with aluminum strips. A balun - the transition from the antenna to a coaxial cable - is accomplished with lumped parameters: two capacitors and two inductors. The concept of the turnstile antenna presented can be used in the VHF and UHF frequency ranges. The measured results show very good agreement with those obtained by simulation. The antenna is also characterized by simple manufacturing and low cost.

Bratislav Milovanovic

Papers

Application of Artificial Neural Networks for Efficient High-Resolution 2D DOA Estimation

TLM modeling of the circular cylindrical cavity loaded by lossy dielectric sample of various geometric shapes.

TLM modeling of a probe-coupled cylindrical cavity based on compact wire model in the cylindrical mesh

Design, Realization, and Measurements of a Corner Reflector Printed Antenna Array With Cosecant Squared-Shaped Beam Pattern

A New Type of Turnstile Antenna