Introduction to Machine Learning and Its Application

In today's world, a huge amount of data is available. So, all the available data are analyzed to get information, and later this data is used to train the machine learning algorithm. Machine learning is a subpart of artificial intelligence where machines are given training with data and the machine predicts the results. Machine learning is being used in healthcare, image processing, marketing, etc. The aim of machine learning is to reduce the work of the programmer by doing complex coding and decreasing human interaction with systems. The machine learns itself from past data and then predict the desired output. This chapter describes machine learning in brief with different machine learning algorithms with examples and about machine learning frameworks such as tensor flow and Keras. The limitations of machine learning and various applications of machine learning are discussed. This chapter also describes how to identify features in machine learning data.

Application of Fingerprint-Matching Algorithm in Smart Gun Using Touch-Less Fingerprint Recognition System

Fingerprint recognition systems are widely used in the field of biometrics. Many existing fingerprint sensors acquire fingerprint images as the user's fingerprint is contacted on a solid flat sensor. Because of this contact, input images from the same finger can be quite different and there are latent fingerprint issues that can lead to forgery and hygienic problems. For these reasons, a touchless fingerprint recognition system has been investigated, in which a fingerprint image can be captured without contact. While this system can solve the problems which arise through contact of the user's finger, other challenges emerge.

Machine Learning With R

In this chapter, the author explained the importance of the R language in machine learning and steps to the installation of R in a different environment like Windows and Linux. The author also describes the basic concepts of R like its syntax, data types, variables, function, operator, etc. with examples in detail. In advanced R, the author explained different charts to plot different data using a barplot function. Using barplot, different graphs like histograms, pie charts can be drawn. The author has also shown how to label the axis of the graph and how to plot a different color. The chapter also consists of some basic R programming examples like a program to make a calculator, checking Armstrong's number, etc. The author also describes the steps and process to install tensor flow.

AI in Cognitive Radio Networks

This chapter provides a-state-of-art of artificial intelligence (AI) techniques applied to cognitive radio networks. Cognitive radio (CR) is an empowering innovation for various new opportunities, for example, spectrum sensing, access, markets, and self-organizing networks. Its target is to enable the system to exploit the available resources through self-learning and to adapt itself accordingly to the sensed environment. To understand this plethora of applications, CR researchers often make use of several types of AI techniques. By utilizing AI, the network system can immediately complete self-awareness learning, structure association, and scheduling several tasks. To help researchers obtain a healthier knowledge of AI techniques along with CR, this chapter presents several such implementations that have already been applied. Finally, the literature review of the best accomplishments in applying AI techniques to CRs is presented and classified according to the major techniques of artificial intelligence.

Application of Novel Techniques in Active Power Filter

Traditionally, the major part of the electrical power is generally consumed by the non-linear loads due to frequent application of the semiconductor devices in the form of domestic and industrial loads. This results from distortion in the actual supply voltage waveform at the source end due to the interference of the multiple harmonics generated out of semiconductor devices used at load end and excessive absorption of the reactive power. The insufficiency of these compensation techniques leads to the advent of the phase multiplication techniques as well as the most reliable and economic active power filtering scheme. A deep analysis showing tedious waveforms using the ORCAD simulation package for the various kind of loads in conjunction with the single-phase active power filter shunted to the single-phase line at the load end for the two current control techniques (i.e., hysteresis band current control, triangularization of current control) has been done. The results are analyzed and tested to lead the optimistic approach for APF (active power filters).

Design of Fuzzy Logic Controller for Up to 25MW Hydropower Plant

In this chapter the emerging control techniques for 25 MW small hydropower (SHP) plants which utilize fuzzy logic are compared with conventional PID control for the speed control of hydraulic turbine in terms of rise time, smoothness of response, settling time, and overshoot in wicket gate opening with the response to change in turbine speed. In the case of the PID controller, gain adjustment (tuning) is required. The fuzzy controller algorithm is based on intuition, experience, and it incorporates a simple, rule-based IF X AND Y THEN Z approach. These controllers obtained don't require gain adjustment. The work done is a small step towards the automation of the hydropower plants.

Design of Linear Phase FIR Low Pass Filter Using Mutation-Based Particle Swarm Optimization Technique

This chapter presents a mutation-based particle swarm optimization (PSO) approach for designing a linear phase digital low pass FIR filter (LPF). Since conventional gradient-based methods are susceptible to being trapped in local optima, the stochastic search methods have proven to be effective in a multi-dimensional non-linear environment. In this chapter, LPF with 20 coefficients has been designed. Since filter design is a multidimensional optimization problem, the concept of mutation helps in maintaining diversity in the swarm population and thereby efficiently controlling the local search and convergence to the global optimum solution. Given the filter specifications to be realized, the Mutation PSO (MPSO) tries to meet the ideal frequency response characteristics by generating an optimal set of filter coefficients. The simulation results have been compared with basic PSO and state of artworks on filter design. The results justify that the proposed technique outperforms not only in convergence speed but also in the quality of the solution obtained.

Improved Design and Optimization of IIR Filters by Cascading of ABC, PSO, and CA

This chapter presents a technique for the design and optimization of the IIR filters by cascading the nature-inspired algorithms including ABC, PSO, and CA. All these algorithms are applied in Low Pass IIR filter and High Pass IIR filter to obtain the optimized filter coefficients so as to minimize the difference between an ideal magnitude response and the desired magnitude response. Finally, IIR filter magnitude response curves and the achieved fitness values for ABC, PSO, and CA are compared to that of the cascaded approach.

Comparison of Artificial Intelligence-Based Solutions Applied to Economic Load Dispatch Problem

The electric power system network is rapidly becoming more and more complex to meet energy requirements. With the development of integrated power systems, it becomes all the more necessary to operate the plant units most economically. More recently, soft computing techniques have received more attention and have been used in a number of successful and practical applications. In the chapter, artificial intelligence-based modern optimization techniques, the genetic algorithm (GA), particle swarm optimization (PSO), and differential evolution (DE), are used to solve the economic load dispatch related problems. In the chapter, the minimum cost is computed by adopting the genetic algorithm, PSO, and DE using the data from 15 generating units. Data has been taken from the published works containing loss coefficients are also given with the maximum-minimum power limits and cost function. All the techniques are implemented in MATLAB environment. Comparing the results obtained from GA, DE, and PSO-based method, better convergence was found in the PSO-based approach.

FLC Technique in Smart Grid for Demand Side Management

The chapter discusses the general characteristics of smart grid, which combines different state-of-the-art technologies intended for operative power distribution when the generation is decentralized. Fault's existence in the power grid is entirely unanticipated. Fuzzy logic is the computational intelligence technique that integrates the knowledge base of experts that is either human or system using the qualitative expression. This technique can successfully be applied for end-user who is a prosumer and aims for low electricity bill as well as provide intelligent decision-making skill in the agents of the multi-agent system. Fuzzy inference system can be efficiently used in such systems due to its capability to deal with imprecision, incomplete data, and its strong knowledge base.