Cloud Approach for the Medical Information System

Healthcare informatics is an important and effective field. It is characterized by the intensive development and design of the new models and protocols. The special emphasize is done on medical information system (MIS) and cloud approaches for its implementation. It is expected that this technology can improve healthcare services, benefit healthcare research, and change the face of health information technology. This chapter discusses the application of cloud computing for the medical information system practical usage.

Evolutionary Control Systems

In control systems, the actual output is compared with the desired value so a corrective action maintains an established behavior. The industrial controller most widely used is the proportional integral derivative (PID). For PIDs, the process is represented in a transfer function. The linear quadratic regulator (LQR) controller needs a state space model. The process behavior depends on the setting of the controller parameters. Current trends in estimating those parameters optimize an integral performance criterion. In this chapter, a unified tuning method for controllers is presented, the evolutionary algorithm MAGO optimizes the parameters of several controllers minimizing the ITAE index, applied on benchmark plants, operating on servo and regulator modes, and representing the system in both transfer functions and differential equation systems. The evolutionary approach gets a better overall performance comparing with traditional methods. The evolutionary method is indeed better than the classical, eliminating the uncertainty in the controller parameters. Better results are yielded with MAGO algorithm than with optimal PID, optimal-robust PID, and LQR.

Evolutionary Approaches to Test Data Generation for Object-Oriented Software

In object-oriented evolutionary testing, metaheuristics are employed to select or generate test data for object-oriented software. Techniques that analyse program structures are predominant among the panoply of studies available in current literature. For object-oriented evolutionary testing, the common objective is to reach some coverage criteria, usually in the form of statement or branch coverage. This chapter explores, reviews, and contextualizes relevant literature, tools, and techniques in this area, while identifying open problems and setting ground for future work.

Biogeographic Computation as Information Processing in Ecosystems

Assuming nature can be investigated and understood as an information processing system, this chapter aims to explore this hypothesis in the field of ecosystems. Therefore, based on the concepts of biogeography, it further investigates a computational approach called biogeographic computation to the study of ecosystems. The original proposal in the literature is built from fundamental concepts of ecosystems and from a framework called a metamodel that allows the understanding of how information processing occurs. This chapter reproduces part of the content of the original proposal and extends and better formalizes the metamodel, including novel experimental results, particularly exploring the role of information and causality in ecosystems, both being considered essential aspects of ecosystems' evolution.

Application of Natural-Inspired Paradigms on System Identification

In this chapter, the application of nature-inspired paradigms on system identification is discussed. A review of the recent applications of techniques such as genetic algorithms, genetic programming, immuno-inspired algorithms, and particle swarm optimization to the system identification is presented, discussing the application to linear, nonlinear, time invariant, time variant, monovariable, and multivariable cases. Then the application of an immuno-inspired algorithm to solve the linear time variant multivariable system identification problem is detailed with examples and comparisons to other methods. Finally, the future directions of the application of nature-inspired paradigms to the system identification problem are discussed, followed by the chapter conclusions.

Finding Optimal Input Values for Desired Target Output by Using Particle Swarm Optimization Algorithm Within Probabilistic Models

Developed predictive models, especially models based on probabilistic concept, regarding numerous potential combinatory states can be very complex. That complexity can cause uncertainty about which factors should have which values to achieve optimal value of output. An example of that problem is developed with a Bayesian network with numerous potential states and their interaction when we would like to find optimal value of nodes for achieving maximum probability on specific output node. This chapter shows a novel concept based on usage of the particle swarm optimization algorithm for finding optimal values within developed probabilistic models.

Comprehensive Learning Particle Swarm Optimization for Structural System Identification

This chapter introduces a novel swarm-intelligence-based algorithm named the comprehensive learning particle swarm optimization (CLPSO) to identify parameters of structural systems, which is formulated as a high-dimensional multi-modal numerical optimization problem. With the new strategy in this variant of particle swarm optimization (PSO), historical best information for all other particles is used to update a particle's velocity. This means that the particles have more exemplars to learn from and a larger potential space to fly, avoiding premature convergence. Simulation results for identifying the parameters of a five degree-of-freedom (DOF) structural system under conditions including limited output data, noise polluted signals, and no prior knowledge of mass, damping, or stiffness are presented to demonstrate improved estimation of these parameters by CLPSO when compared with those obtained from PSO. In addition, the efficiency and applicability of the proposed method are experimentally examined by a 12-story shear building shaking table model.

Multi-Thresholded Histogram Equalization Based on Parameterless Artificial Bee Colony

This chapter presents a novel variant of histogram equalization (HE) method called multi-thresholded histogram equalization (MTHE), depending on entropy-based multi-level thresholding-based segmentation. It is reported that proper segmentation of the histogram significantly assists the HE variants to maintain the original brightness of the image, which is one of the main criterion of the consumer electronics field. Multi-separation-based HE variants are also very effective for multi-modal histogram-based images. But, proper multi-seaparation of the histogram increases the computational time of the corresponding HE variants. In order to overcome that problem, one novel parameterless artifical bee colony (ABC) algorithm is employed to solve the multi-level thresholding problem. Experimental results prove that proposed parameterless ABC helps to reduce the computational time significantly and the proposed MTHE outperforms several existing HE varints in brightness preserving histopathological image enhancement domain.