A5020726288- Evolutionary Algorithms and Applications
- Metaheuristic Optimization Algorithms Research
- Education Pedagogy and Practices
- Sustainable Supply Chain Management
- Education and Digital Technologies
- Neural Networks and Applications
- Sustainable Industrial Ecology
- Gene Regulatory Network Analysis
- History of Education Research in Brazil
- Innovation and Socioeconomic Development
- Digital Radiography and Breast Imaging
- Recycling and Waste Management Techniques
- Advanced X-ray and CT Imaging
- Imbalanced Data Classification Techniques
- Surgical Simulation and Training
- Healthcare Operations and Scheduling Optimization
- Gender, Sexuality, and Education
- Advanced Multi-Objective Optimization Algorithms
- Machine Learning and Data Classification
- Environmental Sustainability in Business
- Microbial Metabolic Engineering and Bioproduction
- Educational Practices and Policies
- Cardiac, Anesthesia and Surgical Outcomes
- Urban and sociocultural dynamics
- Historical Education Studies Worldwide
Bern University of Applied Sciences
2019-2021
Newcastle University
2015-2020
University of Basel
2017
Universidade Federal Fluminense
2013
University of Nottingham
2010-2013
Hospital Comarcal de Inca
2013
Simón Bolívar University
2008-2010
As the solar photovoltaic market booms, so will volume of (PV) systems entering waste stream. The same is forecast for lithium-ion batteries from electric vehicles, which at end their automotive life can be given a second by serving as stationary energy storage units renewable sources, including PV. main objective this paper to systematically review “state-of-the-art” research on PV value chain (i.e., product design end-of-life), its stages, processes, and stakeholder relationships, in order...
In this paper we introduce a method for computing fitness in evolutionary learning systems based on NVIDIA's massive parallel technology using the CUDA library. Both match process of population classifiers against training set and computation each classifier from its matches have been parallelized. This has integrated within BioHEL system. The methodology presented can be easily extended to any tested broad problems with varying number attributes instances. evaluation function by itself...
The success of any machine learning technique depends on the correct setting its parameters and, when it comes to large-scale datasets, hand-tuning these becomes impractical. However, very large-datasets can be pre-processed in order distil information that could help appropriately various systems parameters. In turn, this makes sophisticated methods easier use end-users. Thus, by modelling performance algorithms as a function structure inherent large datasets one could, principle, detect...
This paper proposes three post-processing operators (rule cleaning, rule pruning and swapping) which combined together in different ways can help reduce the complexity of decision lists evolved by means genetics-based machine learning. While first two work on independent rules to number expressed attributes, last one changes order (based similarities between them) identify delete unnecessary ones. These were tested using BioHEL system over 35 problems. Our results show that it is possible...
Models in Genetic Based Machine Learning (GBML) systems are commonly used to gain understanding of how the system works and, as a consequence, adjust it better. In this paper we propose models for probability having good initial population using Attribute List Knowledge Representation (ALKR) discrete inputs GABIL encoding. We base our work schema and covering bound previously proposed XCS. The extended (a) deal with combination ALKR+GABIL representation, (b) explicitly handle datasets niche...
En la presente revisión, y apoyándonos en nuestra experiencia el Hospital Comarcal de Jaca, intentaremos poner relieve discutir los beneficios problemas que generan las unidades cirugía sin ingreso. Analizaremos distintos tipos programas ambulatorios modelos unidad quirúrgica, mostrando sus ventajas e inconvenientes. Por último, proponer diversas líneas para mejorar calidad ofertada, satisfacción del usuario relación coste / efectividad procesos quirúrgicos.
In this work we present an exhaustive empirical analysis of the Pittsburgh-style BioHEL system using a broad set variants well-known k-DNF boolean function. These functions possible challenges for most machine learning techniques such as varying degrees rule specificity, class unbalance and niche overlap. Moreover, ideal solutions are known, one can easily assess if is able to find them, how fast. Specifically, study two aspects BioHEL: its sensitivity coverage breakpoint parameter (that...
A autora aborda, brevemente, alguns conceitos de tempo, a aproximacao da historia com sociologia e analise preliminar dados colhidos na imprensa operaria das cidades do Rio Janeiro Sao Paulo nas tres primeiras decadas seculo XX, buscando seus aspectos educativos, sociais estruturais.
The Trading Agent Competition in its category Supply Chain Management (TAC SCM) is an international forum where teams construct agents that control a computer assembly company simulated environment. TAC SCM involves the following problems: to determine when send offers, final sales prices of offered goods and plan factory delivery schedules. main goal this work was develop agent called TicTACtoe, using Wilson's XCSR classifier system decide prices. We adaptation system, we blocking...
Sintetiza algumas das dimensões discutidas na pesquisa sobre trabalho-educação "Fontes alternativas de história da educação no Brasil". Partindo perspectiva que os conceitos e as categorias para serem compreendidos implica entendê-los como produtos historicamente construídos, analisa, interior relações sociais capitalistas, a questão escola do trabalho centralidade trabalho. Abstract This article is synthesis of some the dimensions discussed in research "Work-Education: alternative Sources...