DEMORS: A hybrid multi-objective optimization algorithm using differential evolution and rough set theory for constrained problems

The aim of this paper is to show how the hybridization of a multi-objective evolutionary algorithm (MOEA) and a local search method based on the use of rough set theory is a viable alternative to obtain a robust algorithm able to solve difficult constrained multi-objective optimization problems at a moderate computational cost. This paper extends a previously published MOEA [Hernández-Díaz AG, Santana-Quintero LV, Coello Coello C, Caballero R, Molina J. A new proposal for multi-objective optimization using differential evolution and rough set theory. In: 2006 genetic and evolutionary computation conference (GECCO’2006). Seattle, Washington, USA: ACM Press; July 2006], which was limited to unconstrained multi-objective optimization problems. Here, the main idea is to use this sort of hybrid approach to approximate the Pareto front of a constrained multi-objective optimization problem while performing a relatively low number of fitness function evaluations. Since in real-world problems the cost of evaluating the objective functions is the most significant, our underlying assumption is that, by aiming to minimize the number of such evaluations, our MOEA can be considered efficient. As in its previous version, our hybrid approach operates in two stages: in the first one, a multi-objective version of differential evolution is used to generate an initial approximation of the Pareto front. Then, in the second stage, rough set theory is used to improve the spread and quality of this initial approximation. To assess the performance of our proposed approach, we adopt, on the one hand, a set of standard bi-objective constrained test problems and, on the other hand, a large real-world problem with eight objective functions and 160 decision variables. The first set of problems are solved performing 10,000 fitness function evaluations, which is a competitive value compared to the number of evaluations previously reported in the specialized literature for such problems. The real-world problem is solved performing 250,000 fitness function evaluations, mainly because of its high dimensionality. Our results are compared with respect to those generated by NSGA-II, which is a MOEA representative of the state-of-the-art in the area.     

Multimodal Interface Technologies for UAV Ground Control Stations

This paper examines different technologies that can be applied in the design and development of a ground control station for Unmanned Aerial Vehicles (UAVs) equipped with multimodal interfaces. Multimodal technologies employ multiple sensory channels/modalities for information transmission as well as for system control. Examples of these technologies could be haptic feedback, head tracking, auditory information (3D audio), voice control, tactile displays, etc. The applicability and benefits of those technologies is analyzed for a task consisting in the acknowledgement of alerts in an UAV ground control station composed by three screens and managed by a single operator. For this purpose, several experiments were conducted with a group of individuals using different combinations of modal conditions (visual, aural and tactile).     

Unmanned Aerial Vehicle Localization Based on Monocular Vision and Online Mosaicking

This paper presents a new approach for vision-based UAV localization, using mosaics as environment representations. Inter-image motions are used to estimate the motion of the UAV. Online mosaicking is applied to reduce the impact of the accumulative errors in UAV position estimation. A new method to build an stochastic mosaic given the image-to-image homographies is detailed. The mosaic consists of a network of inter-image relations, and is used to create a consistent view of the environment of the UAV and hence, to detect the drift in position estimation by using the mosaic as a resource. The technique could be called simultaneous localization and mosaicking. This technique is specially suitable for monitoring and surveillance tasks in which the UAV will repeatedly cover the same area. The paper also shows experimental results with real UAVs where the benefits of the proposed method are evident.     

Multi‐agent system for knowledge‐based event recognition and composition

This work presents a multi‐agent system for knowledge‐based high‐level event composition, which interprets activities, behaviour and situations semantically in a scenario with multi‐sensory monitoring. A perception agent (plurisensory agent and visual agent)‐based structure is presented. The agents process the sensor information and identify (agent decision system) significant changes in the monitored signals, which they send as simple events to the composition agent that searches for and identifies pre‐defined patterns as higher‐level semantic composed events. The structure has a methodology and a set of tools that facilitate its development and application to different fields without having to start from scratch. This creates an environment to develop knowledge‐based systems generally for event composition. The application task of our work is surveillance, and event composition/inference examples are shown which characterize an alarming situation in the scene and resolve identification and tracking problems of people in the scenario being monitored.     

Protein radial distribution function (P-RDF) and Bayesian-Regularized Genetic Neural Networks for modeling protein conformational stability: chymotrypsin inhibitor 2 mutants

Development of novel computational approaches for modeling protein properties is a main goal in applied Proteomics. In this work, we reported the extension of the radial distribution function (RDF) scores formalism to proteins for encoding 3D structural information with modeling purposes. Protein-RDF (P-RDF) scores measure spherical distributions on protein 3D structure of 48 amino acids/residues properties selected from the AAindex data base. P-RDF scores were tested for building predictive models of the change of thermal unfolding Gibbs free energy change (DeltaDeltaG) of chymotrypsin inhibitor 2 upon mutations. In this sense, an ensemble of Bayesian-Regularized Genetic Neural Networks (BRGNNs) yielded an optimum nonlinear model for the conformational stability. The ensemble predictor described about 84% and 70% variance of the data in training and test sets, respectively.     

Obtaining a durable power of attorney for health care from nursing home residents

BACKGROUND: A durable power of attorney for health care (DPA) allows a person to appoint a surrogate decision-maker for any future period of mental incapacity. The absence of advance directives can lead to confusion and the expenditure of resources while trying to exert a substituted judgment. METHODS: The Wisconsin DPA was presented with an organized pilot program to 150 residents who had been judged by their social workers to have the capacity to make informed decisions regarding medical care. The reasons residents gave for accepting or rejecting a DPA were analyzed. RESULTS: Seventy-nine percent prepared a DPA. Reasons for signing included allowing the resident to decide who would make medical decisions and assuring that specific wishes would be carried out. Twenty-one percent did not execute a DPA. Reasons were categorized as confusion and misunderstanding regarding the legal system, mistrust, or social isolation. CONCLUSIONS: The high rate (79%) of DPA completion is probably related to individually counseling residents. However, competent residents who despite counseling do not choose to execute a DPA can have detailed advance directives ("living wills") prepared without appointing a decision-maker.     

Early assessment of diaphragmatic dysfunction in children in the ITU: chest radiology and phrenic nerve stimulation

Diaphragmatic dysfunction is a common postoperative complication of cardiac surgery in children, with important effects on respiratory morbidity. Its early diagnosis, followed by prompt surgical intervention, has been shown to reduce morbidity. However, the commonest method of diagnosis, based on hemi-diaphragmatic elevation on the chest radiograph, may be less accurate than direct techniques for assessing phrenic nerve function. We have compared electrophysiological and radiological diagnoses of diaphragmatic abnormality in 100 children (aged 3 days to 17.5 yrs) undergoing cardiac surgery, looking at respiratory morbidity as assessed by the duration of ventilation, the time spent on the cardiac intensive care unit (CICU), and the requirement for reintubation. Despite showing good reproducibility, radiological diagnosis was neither sensitive nor specific in identifying patients with electrophysiological phrenic nerve damage. Analysis of the measures of outcome supported the electrophysiological technique. Patients with electrophysiological evidence of damage had a longer duration of ventilation, spent longer on the CICU, and had a greater incidence of reintubation than either radiologically abnormal or "normal" patients. Chest X-rays are not a good method for diagnosing phrenic nerve damage in the early postoperative period in children. If early diagnosis is needed, then direct assessment of phrenic nerve function, such as the measurement of phrenic latency, may be a better technique.     

Hand function related to age and sex

After adapting Jebssen's Test of Hand Function to Australian conditions, this study investigated his claim of no significant difference in hand performance among participants younger than 60 years, and determined whether age might be a factor when associated with sex. The method was to test 383 subjects of both sexes in 6 age groups. A 2-factor analysis with age and sex as factors yielded significant differences (p less than 0.01) for "grip strength" "manipulating small objects," and "moving large heavy objects," and indications of significance (p less than 0.05) for "card turning" and "moving large light objects." The sex factor showed males to be significantly better "grip strength," in "moving large heavy objects," and "large light objects," except in the 66-99 age interval where females were significantly better on teh last 2 variables. Females performed better on "writing" and were generally better in "manipulating small objects." These results suggest that the one set of norms given by Jebsen for 60 years and less for each sex, should be replaced by 5 or more, even though the differences were quite small when standard deviations were considered.