228 research outputs found
Genetic and Evolutionary Computation: Medical Applications
No full textGenetic and Evolutionary Computation: Medical Applications provides an overview of the range of GEC techniques being applied to medicine and healthcare in a context that is relevant not only for existing GEC practitioners but also those from other disciplines, particularly health professionals. There is rapidly increasing interest in applying evolutionary computation to problems in medicine, but to date no text that introduces evolutionary computation in a medical context. By explaining the basic introductory theory, typical application areas and detailed implementation in one coherent volume, this book will appeal to a wide audience from software developers to medical scientists. Centred around a set of nine case studies on the application of GEC to different areas of medicine, the book offers an overview of applications of GEC to medicine, describes applications in which GEC is used to analyse medical images and data sets, derive advanced models, and suggest diagnoses and treatments, finally providing hints about possible future advancements of genetic and evolutionary computation in medicine. Explores the rapidly growing area of genetic and evolutionary computation in context of its viable and exciting payoffs in the field of medical applications. Explains the underlying theory, typical applications and detailed implementation. Includes general sections about the applications of GEC to medicine and their expected future developments, as well as specific sections on applications of GEC to medical imaging, analysis of medical data sets, advanced modelling, diagnosis and treatment. Features a wide range of tables, illustrations diagrams and photographs
What can we learn from multi-objective meta-optimization of Evolutionary Algorithms in continuous domains?
No full textProperly configuring Evolutionary Algorithms (EAs) is a challenging task made difficult by many different details that affect EAs' performance, such as the properties of the fitness function, time and computational constraints, and many others. EAs' meta-optimization methods, in which a metaheuristic is used to tune the parameters of another (lower-level) metaheuristic which optimizes a given target function, most often rely on the optimization of a single property of the lower-level method. In this paper, we show that by using a multi-objective genetic algorithm to tune an EA, it is possible not only to find good parameter sets considering more objectives at the same time but also to derive generalizable results which can provide guidelines for designing EA-based applications. In particular, we present a general framework for multi-objective meta-optimization, to show that "going multi-objective" allows one to generate configurations that, besides optimally fitting an EA to a given problem, also perform well on previously unseen ones
Modelling of a Safety Instrumented System by a Biologically Inspired Modular Construct
No full textWe present an ongoing research aimed at investigating aspects of a modelling paradigm where system behaviour is modelled by biologically-inspired, concurrent and autonomous modules through a state based formalism. Such modules are named holons after the work of Arthur Koestler, since they are designed in order to host both the features of parts and wholes. Current modelling paradigms tend at emphasising the parts, but miss the notion of whole. A whole models the associative behaviour observed in the domain of interest, while the parts model the behaviour of a specific entity. Holons are aimed at filling the gap. Holons can act as parts by exhibiting the interface of the state behaviour. At the same time holons can act as wholes, by having the state machine behaviour annotated with actions and triggers which allow them to communicate with other holons, coordinating them and therefore modelling the related associative behaviour. In the paradigm, the two roles are tied together, the associative behaviour becoming recursively the behaviour of a single entity which can be composed into further wholes
Hot Topics in Evolutionary Computation
No full textWe introduce the special issue on Evolutionary Computation (EC) reporting a non-exhaustive list of topics which have recently attracted much interest from the EC community, with particular regard to the ones dealt with by the papers included in this issue: EC research, hybrid neuro-evolutionary systems and synergies between EC and complex systems. In addition, we
introduce a more technological emerging topic: the parallel implementation of evolutionary and Swarm Intelligence algorithms on graphics processor units (GPUs), by which new applications of evolutionary algorithms have been made possible, even in real-time environments
A critical assessment of some variants of particle swarm optimization
No full textAmong the variants of the basic Particle Swarm Optimization algorithm as first proposed in 1995 discussed in literature, an interesting one, which
combines both approaches, is the one proposed by Miranda and Fonseca in 2002, which seems to produce significant improvements. We analyze the effects of two modifications introduced in that work (adaptive parameter setting and selection
based on an evolution strategies-like approach) separately, reporting results obtained on a set of multimodal benchmark functions, which showi that they may have opposite and complementary effects. In particular, using only parameter
adaptation when optimizing ’harder’ functions yields better results than when both modifications are applied. We also propose a justification for this, based on recent analyses in which particle swarm optimizers are studied as dynamical systems
A non-traditional omnidirectional vision system with stereo capabilities for autonomous robots
No full textSimultaneous and sequential same-arm measurements in the validation studies of automated blood pressure measuring devices
No full textThe oscillometric ambulatory blood pressure recorder Daypress 500 was validated according to the British Hypertension Society protocol. Both sequential and simultaneous measurements were used. Multiple regression analysis demonstrated a significant influence of subject pulse pressure and arm circumference on device-observer systolic pressure differences. Differences between observer consecutive readings were inversely related to heart rate. Device and observer blood pressure readings were closer at simultaneous than at sequential measurements. However, both kinds of measurement led to the same final evaluation (A for diastolic and B for systolic blood pressure), provided that the appropriate grading criteria were applied for each method
General Lines, Routes and Perspectives of Wetware Embodied AI. From its Organizational Bases to a Glimpse on Social Chemical Robotics
No full text- …
