TALLER II

TALLER II
CONSULTAS EN BASES DE DATOS DE DOCUMENTOS CIENTÍFICOS
BÚSQUEDAS ESTRUCTURADAS DE INFORMACIÓN.
Departamento de Ingeniería de Sistemas e Industrial
Universidad Nacional de Colombia Sede Bogotá SUSANA ASTRID MONTAÑA LUNA CODIGO: 257418
Recolección inicial de referencias.

1. Realice una lista de 20 palabras clave del área de interés.

Inteligencia
Artificial
Medicina
Tratamiento
Emergencias
Robots
Historia
Enfermedades
Datos
Avances
Tecnología
Revistas
Necesidades
Evolución
Resonancia
Científicos
Pacientes
Intereses
Aplicaciones
diagnostico

2. Partiendo del área de interés general, y teniendo en cuenta la lista de palabras
clave, buscar y recopilar 50 referencias relacionadas (artículos, libros, páginas
web, etc.)
Meta datos a recopilar en Jabref:
Titulo
Autor
Ubicación de la referencia (url, base de datos, texto fuente, etc.)
Descripción general del documento
Deseable: referencia bibliográfica completa, resumen
Recursos de información: Citeseer,ACM,Scirus,IEEE,Scholar google,Corr
1. @inproceedings{41544, author = {C. A. Kulikowski}, title = {Artificial intelligence in medicine: a personal retrospective on its emergence and early function}, booktitle = {Proceedings of ACM conference on History of medical informatics}, year = {1987}, isbn = {0-89791-248-9}, pages = {199}, location = {Bethesda, Maryland, United States}, doi = {http://doi.acm.org/10.1145/41526.41544}, publisher = {ACM Press}, address = {New York, NY, USA}, }
ABSTRACT
Methods of artificial intelligence were gradually introduced into clinical decision-making research from 1970 to 1974. Evolving from pattern recognition and general A.I. problem-solving ideas, such methods helped researchers crystallize the notions of knowledge-based systems by the mid-1970s. In 1978 the early systems gave way to either second-generation frameworks for general consultative reasoning or to new, more sophisticated knowledge representations. This paper traces some of the major events in the early evolution of AIM systems, with emphasis on the developments at the Rutgers Resource, in which the author participated. 2. @article{590368, author = {Luca Chittaro and Angelo Montanari}, title = {Temporal representation and reasoning in artificial intelligence: Issues and approaches}, journal = {Annals of Mathematics and Artificial Intelligence}, volume = {28}, number = {1-4}, year = {2000}, issn = {1012-2443}, pages = {47--106}, publisher = {Kluwer Academic Publishers}, address = {Hingham, MA, USA}, }
ABSTRACT
Time is one of the most relevant topics in AI. It plays a major role in several areas, ranging from logical foundations to applications of knowledge‐based systems. In this paper, we survey a wide range of research in temporal representation and reasoning, without committing ourselves to the point of view of any specific application. The organization of the paper follows the commonly recognized division of the field in two main subfields: reasoning about actions and change, and reasoning about temporal constraints. We give an overview of the basic issues, approaches, and results in these two areas, and outline relevant recent developments. Furthermore, we briefly analyze the major emerging trends in temporal representation and reasoning as well as the relationships with other well‐established areas, such as temporal databases and logic programming.3. @article{1046364, author = {Elena Alessandri and Alessandro Gasparetto and Rafael Valencia Garcia and Rodrigo Martinez B\&\#237;jar}, title = {An application of artificial intelligence to medical robotics}, journal = {J. Intell. Robotics Syst.}, volume = {41}, number = {4}, year = {2005}, issn = {0921-0296}, pages = {225--243}, doi = {http://dx.doi.org/10.1007/s10846-005-3509-x}, publisher = {Kluwer Academic Publishers}, address = {Hingham, MA, USA}, }
ABSTRACT
In this paper an application of Artificial Intelligence (AI) to Medical Robotics is described. Namely, a specific AI technique is employed to generate a sequence of operations understandable by the control system of a robot which is to perform a semi-automatic surgical task. According to this technique, a planner is implemented to translate the "natural" language of the surgeon into the robotic sequence that should be executed by the robot. A robotic simulator has been implemented in order to test the planned sequence in a virtual environment. The planned sequence is then to be input to the medical robotic system, which will execute the surgical operation. The work described in this paper features a high level of originality, since no similar applications of AI to medical robotics could be found in the scientific literature.4. @article{1052556, author = {Subramani Mani and Marco Valtorta and Suzanne McDermott}, title = {Building Bayesian Network Models in Medicine: The MENTOR Experience}, journal = {Applied Intelligence}, volume = {22}, number = {2}, year = {2005}, issn = {0924-669X}, pages = {93--108}, doi = {http://dx.doi.org/10.1007/s10489-005-5599-3}, publisher = {Kluwer Academic Publishers}, address = {Hingham, MA, USA}, }
ABSTRACT
An experiment in Bayesian model building from a large medical dataset for Mental Retardation is discussed in this paper. We give a step by step description of the practical aspects of building a Bayesian Network from a dataset. We enumerate and briefly describe the tools required, address the problem of missing values in big datasets resulting from incomplete clinical findings and elaborate on our solution to the problem. We advance some reasons why imputation is a more desirable approach for model building than some other ad hoc methods suggested in literature. In our experiment, the initial Bayesian Network is learned from a dataset using a machine learning program called CB. The network structure and the conditional probabilities are then modified under the guidance of a domain expert. We present validation results for the unmodified and modified networks and give some suggestions for improvement of the model.5. @inproceedings{1166514, author = {Kathiravelu Ganeshan}, title = {Networked intelligent mobile robot assistants: patient monitoring and telemedicine}, booktitle = {BioMed'06: Proceedings of the 24th IASTED international conference on Biomedical engineering}, year = {2006}, isbn = {0-88986-578-7}, pages = {45--50}, location = {Innsbruck, Austria}, publisher = {ACTA Press}, address = {Anaheim, CA, USA}, }
ABSTRACT
This paper discusses the need for, and the design and development, of highly adaptable, networked, intelligent, mobile robot assistants and systems for use in patient monitoring and telemedicine. It considers the factors that were taken into account in designing these systems and provide details of the hardware and software developed by the author and how these are used, in conjunction with commercially available hardware, to build these robot assistants and systems. It discusses how intelligence, mobility and adaptability are built into these systems and how these robots can be networked and controlled over the Internet. It discusses the increasing awareness and use of telemedicine and how these assistants may be used in the practice of telemedicine and patient monitoring. It also considers how this work relates to work carried out by researchers in other parts of the world. This work is unique in that it uses only inexpensive and therefore very affordable robots and other equipment and in that these systems are designed to be highly adaptable.6. @inproceedings{1166971, author = {Julie Behan and Derek T. O'Keeffe}, title = {The development of an intelligent library assistant robot}, booktitle = {AIA'06: Proceedings of the 24th IASTED international conference on Artificial intelligence and applications}, year = {2006}, isbn = {0-88986-556-6}, pages = {474--479}, location = {Innsbruck, Austria}, publisher = {ACTA Press}, address = {Anaheim, CA, USA}, }
ABSTRACT
In modern society, robots are been designed to play an increasing role in the lives of ordinary people. Among the emerging areas in robotics is the field of service robots. This paper describes a mobile robotic assistant, named 'LUCAS', Limerick University Computerised Assistive System that is currently been developed to assist individuals within a library environment while also socially interacting with them. Human-Robot interaction is initiated through a 3-D animated character displayed on the robots onboard p.c. A continuous localisation process is described which relies on monocular vision and ultrasonic range readings. The process involves dividing the navigable space into localisation variant regions, and employ's methods of landmark feature extraction, vanishing point estimation and ultrasonic pattern detection to localise the robot within each region. 7. @article{1149551, author = {Pawel Pyk and Sergi Berm\&\#250;dez I Badia and Ulysses Bernardet and Philipp Kn\&\#252;sel and Mikael Carlsson and Jing Gu and Eric Chanie and Bill S. Hansson and Tim C. Pearce and Paul F. J. Verschure}, title = {An artificial moth: Chemical source localization using a robot based neuronal model of moth optomotor anemotactic search}, journal = {Auton. Robots}, volume = {20}, number = {3}, year = {2006}, issn = {0929-5593}, pages = {197--213}, doi = {http://dx.doi.org/10.1007/s10514-006-7101-4}, publisher = {Kluwer Academic Publishers}, address = {Hingham, MA, USA}, }
ABSTRACT
Robots have been used to model nature, while nature in turn can contribute to the real-world artifacts we construct. One particular domain of interest is chemical search where a number of efforts are underway to construct mobile chemical search and localization systems. We report on a project that aims at constructing such a system based on our understanding of the pheromone communication system of the moth. Based on an overview of the peripheral processing of chemical cues by the moth and its role in the organization of behavior we emphasize the multimodal aspects of chemical search, i.e. optomotor anemotactic chemical search. We present a model of this behavior that we test in combination with a novel thin metal oxide sensor and custom build mobile robots. We show that the sensor is able to detect the odor cue, ethanol, under varying flow conditions. Subsequently we show that the standard model of insect chemical search, consisting of a surge and cast phases, provides for robust search and localization performance. The same holds when it is augmented with an optomotor collision avoidance model based on the Lobula Giant Movement Detector (LGMD) neuron of the locust. We compare our results to others who have used the moth as inspiration for the construction of odor robots.8. @article{1149547, author = {Dominique Martinez and Oliver Rochel and Etienne Hugues}, title = {A biomimetic robot for tracking specific odors in turbulent plumes}, journal = {Auton. Robots}, volume = {20}, number = {3}, year = {2006}, issn = {0929-5593}, pages = {185--195}, doi = {http://dx.doi.org/10.1007/s10514-006-7157-1}, publisher = {Kluwer Academic Publishers}, address = {Hingham, MA, USA}, }
ABSTRACT
Two basic tasks must be performed by an olfactory robot tracking a specific odor source: navigate in a turbulent odor plume and recognize an odor regardless of its concentration. For these two tasks, we propose simple biologically inspired strategies, well suited for building dedicated circuits and for on-board implementation on real robots. The odor recognition system is based on a spiking neural network using a synchronization coding scheme. The robot navigation system is based on the use of bilateral comparison between two spatially separated gas sensors arrays at either side of the robot. We propose binary or analog navigation laws depending on the nature of the available sensory information extracted from the plume structure (isolated odor patches or smoother concentration field).9. @inproceedings{1124680, author = {P. Marti and A. Pollini and A. Rullo and T. Shibata}, title = {Engaging with artificial pets}, booktitle = {EACE '05: Proceedings of the 2005 annual conference on European association of cognitive ergonomics}, year = {2005}, isbn = {9-60254-656-5}, pages = {99--106}, location = {Chania, Greece}, publisher = {University of Athens}, }
ABSTRACT
This paper is a reflection about the compelling yet difficult nature of interaction dynamics among humans and robots, and a special category among them: robots capable of mediating social interaction. Such systems are not designed to help the human being performing work tasks or saving time in routine activities, but to engage them in personal experiences stimulated by the physical, emotional and behavioural affordances of the robot. The argument is illustrated by a case study in which an artificial pet was used as a support to therapeutic treatment of children with severe cognitive impairment. 10. @article{590368, author = {Luca Chittaro and Angelo Montanari}, title = {Temporal representation and reasoning in artificial intelligence: Issues and approaches}, journal = {Annals of Mathematics and Artificial Intelligence}, volume = {28}, number = {1-4}, year = {2000}, issn = {1012-2443}, pages = {47--106}, publisher = {Kluwer Academic Publishers}, address = {Hingham, MA, USA}, }
ABSTRACT
Time is one of the most relevant topics in AI. It plays a major role in several areas, ranging from logical foundations to applications of knowledge‐based systems. In this paper, we survey a wide range of research in temporal representation and reasoning, without committing ourselves to the point of view of any specific application. The organization of the paper follows the commonly recognized division of the field in two main subfields: reasoning about actions and change, and reasoning about temporal constraints. We give an overview of the basic issues, approaches, and results in these two areas, and outline relevant recent developments. Furthermore, we briefly analyze the major emerging trends in temporal representation and reasoning as well as the relationships with other well‐established areas, such as temporal databases and logic programming.11. @inproceedings{41544, author = {C. A. Kulikowski}, title = {Artificial intelligence in medicine: a personal retrospective on its emergence and early function}, booktitle = {Proceedings of ACM conference on History of medical informatics}, year = {1987}, isbn = {0-89791-248-9}, pages = {199}, location = {Bethesda, Maryland, United States}, doi = {http://doi.acm.org/10.1145/41526.41544}, publisher = {ACM Press}, address = {New York, NY, USA}, }
ABSTRACT
Methods of artificial intelligence were gradually introduced into clinical decision-making research from 1970 to 1974. Evolving from pattern recognition and general A.I. problem-solving ideas, such methods helped researchers crystallize the notions of knowledge-based systems by the mid-1970s. In 1978 the early systems gave way to either second-generation frameworks for general consultative reasoning or to new, more sophisticated knowledge representations. This paper traces some of the major events in the early evolution of AIM systems, with emphasis on the developments at the Rutgers Resource, in which the author participated.12. @article{627451, author = {W. E. Spangler}, title = {The Role of Artificial Intelligence in Understanding the Strategic Decision-Making Process}, journal = {IEEE Transactions on Knowledge and Data Engineering}, volume = {3}, number = {2}, year = {1991}, issn = {1041-4347}, pages = {149--159}, doi = {http://dx.doi.org/10.1109/69.87995}, publisher = {IEEE Educational Activities Department}, address = {Piscataway, NJ, USA}, }
ABSTRACT
A survey is given which focuses on research issues involving strategic planning and artificial intelligence (AI), including the nature of the formulation task, cognitive studies of strategic planners and computer-based support for strategic planning. The author reviews the research to date, and argues that, like traditional decision support systems (DSS) research, much of the potential for future research in this area lies in modeling the ill-structured, early stages of the strategic decision making process namely, the strategic intelligence analysis and the issue diagnosis. Therefore, he discusses a specific model-based approach to the study of these early stages. Research in artificial intelligence-including investigations into diagnosis and situation assessment, analogical reasoning, plan recognition, nonmonotonic reasoning and distributed intelligence, among others-can be used to build models of strategic decision making that help researchers in better understanding this traditionally unstructured activity. 13. @article{607642, author = {P. J. G. Lisboa}, title = {A review of evidence of health benefit from artificial neural networks in medical intervention}, journal = {Neural Netw.}, volume = {15}, number = {1}, year = {2002}, issn = {0893-6080}, pages = {11--39}, doi = {http://dx.doi.org/10.1016/S0893-6080(01)00111-3}, publisher = {Elsevier Science Ltd.}, address = {Oxford, UK, UK}, }
ABSTRACT
The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rôle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention. 14. @article{1132836, author = {Alec Holt and Isabelle Bichindaritz and Rainer Schmidt and Petra Perner}, title = {Medical applications in case-based reasoning}, journal = {Knowl. Eng. Rev.}, volume = {20}, number = {3}, year = {2005}, issn = {0269-8889}, pages = {289--292}, doi = {http://dx.doi.org/10.1017/S0269888906000622}, publisher = {Cambridge University Press}, address = {New York, NY, USA}, }
ABSTRACT
This commentary summarizes case-based reasoning research applied in the medical domain. In this commentary the term ‘medical’ is used in an all-encompassing manner. It comprises all aspects of health, for example, from diagnosis to nutrition planning. This article provides references to researchers in the field, systems, workshops, and landmark publications. 15. @inproceedings{98846, author = {V. Masson and R. Quiniou}, title = {Application of artificial intelligence to aphasia treatment}, booktitle = {IEA/AIE '90: Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems}, year = {1990}, isbn = {0-89791-372-8}, pages = {907--913}, location = {Charleston, South Carolina, United States}, doi = {http://doi.acm.org/10.1145/98894.98846}, publisher = {ACM Press}, address = {New York, NY, USA}, }
ABSTRACT
In this paper we describe SARAH a system devoted to the rehabilitation of aphasic patients. The system has many features of an intelligent tutoring system. Its origininality lies in the patient modelling method used to closely represent the patients' impairments. The patient model provide a means to adapt the rehabilitation sessions to a particular patient. The tests used to diagnose the patient's impairments and then to train him in order to make him avoid his troubles are generated and not retrieved from some knowledge base. This insures the flexibility such a system needs. Finally an expert system is used to schedule the tests during a session.
3. Después de recopilar las referencias actualice la lista de palabras clave.

Inteligencia
Artificial
Medicina
Tratamientos
Emergencias
Robots
Historia
Enfermedades
Rehabilitación
Avances
Tecnología
Revistas
Oncológico
Evolución
Resonancia
Científicos
Pacientes
Problemas
Aplicaciones
diagnostico

4. Escriba un resumen de las referencias revisadas, de 200 palabras.
Los métodos de inteligencia artificial gradualmente fueron presentados en la investigación de toma de decisiones clínica a partir de 1970 hasta 1974. Desarrollando del reconocimiento de modelo e ideas de resolución de los problemas de general A.I.

En la sociedad moderna, los robots han sido diseñados para jugar un papel importante en la vida de personas ordinarias. Entre las áreas emergentes en la robótica es el campo de robots de servicio. A saber, una técnica específica en AI es empleada para generar una secuencia de operaciones comprensibles por el sistema de control de un robot que debe realizar una tarea semiautomática quirúrgica. Según esta técnica, un planificador es puesto en práctica para traducir la lengua "natural" del cirujano en la secuencia robótica que debería ser ejecutada por el robot.

Los artículos seleccionados están relacionados con la aplicación de la inteligencia artificial en la medicina, se hizo un énfasis de esta aplicación a la robótica, y la importancia de esta en nuestros tiempos.