139,654 research outputs found
Architectures of evolving fuzzy rule-based classifiers
Full text linkPrediction of the properties of the crude oil distillation side streams based on statistical methods and laboratory-based analysis has been around for decades. However, there are still many problems with the existing estimators that require a development of new techniques especially for an on-line analysis of the quality of the distillation process. The nature of non-linear characteristics of the refinery process, the variety of properties to measure and control and the narrow window that normally refinery processes operates in are only some of the problems that a prediction technique should deal with in order to be useful for a practical application. There are many successful application cases that refinery units use real plant data to calibrate models. They can be used to predict quality properties of the gas oil, naphtha, kerosene and other products of a crude oil distillation tower. Some of these are distillation end points and cold properties (freeze, cloud). However, it is difficult to identify, control or compensate the dynamic process behaviour and the errors from instrumentation for an online model prediction
Identification of Evolving Rule-based Models.
Full text linkAn approach to identification of evolving fuzzy rule-based (eR) models is proposed. eR models implement a method for the noniterative update of both the rule-base structure and parameters by incremental unsupervised learning. The rule-base evolves by adding more informative rules than those that previously formed the model. In addition, existing rules can be replaced with new rules based on ranking using the informative potential of the data. In this way, the rule-base structure is inherited and updated when new informative data become available, rather than being completely retrained. The adaptive nature of these evolving rule-based models, in combination with the highly transparent and compact form of fuzzy rules, makes them a promising candidate for modeling and control of complex processes, competitive to neural networks. The approach has been tested on a benchmark problem and on an air-conditioning component modeling application using data from an installation serving a real building. The results illustrate the viability and efficiency of the approach. (c) IEEE Transactions on Fuzzy System
Tecnología y la administración financiera para los abogados
Full text linkAngelina Angelov, MBA, CLM es administradora legal certificada en los Estados Unidos, consultora, autora y educadora. Actualmente se desempeña como Gerente Tesorera, miembro del consejo administrativo de Russin, Vecchi & Heredia Bonetti, una de las firmas de abogados más prestigiosas del país, además de liderar las áreas de gerencia administrativa y cumplimiento. Desde el año 2004, ha liderado equipos interdisciplinarios y gestionado áreas críticas como finanzas, recursos humanos, marketing, tecnología, desarrollo organizacional, innovación y gestión del conocimiento, logrando resultados sostenibles y consistentes.
En el ámbito académico, Angelina Angelov ha destacado como docente adjunta de Postgrado en la Universidad APEC, donde recibió el reconocimiento como Profesora Meritoria en 2019, una mención por publicaciones destacadas en 2021 y fue nominada al ACBSP Teaching Excellence Award en Chicago, 2023..
Desde abril de 2024, forma parte del cuerpo docente de la MBA en Gestión Legal de la Faculdade Baiana de Direito, en Brasil, donde imparte la clase de Liderazgo (dentro de la asignatura Emprendimiento Legal) y la Masterclass: Firma de Abogados en América Latina (dentro de la asignatura Marketing Legal).
En el ámbito internacional, Angelina es miembro activa de la Association of Legal Administrators (ALA), con sede en Chicago, donde actualmente forma parte de la Junta Directiva para el período 2023-2026. A lo largo de su membresía desde 2010, ha ocupado diversos cargos de liderazgo, incluyendo Presidente del Comité de Revisión de Productos y Servicios (2021-2024), miembro del Business Partner Relations Committee (BPRC) (2017-2020) y del International Relations Committee (IRC) (2013-2016 y 2019-2021).
Además, Angelina es miembro de la Plataforma de Inteligencia Estratégica del Foro Económico Mundial y de la Asociación Dominicana de Administradores de Recursos Humanos (ADOARH). Entre 2013 y 2016, co-lideró el Consejo de Administradores de Firmas de Abogados (LFAC) de Meritas para la región de Latinoamérica y el Caribe. También sirvió como Coordinadora del Comité de Recursos Humanos de la Asociación de Empresas de Inversión Extranjera (ASIEX) entre 2012 y 2015. Fue miembro de Legal Marketing Association (LMA), de la International Women’s Insolvency and Restructuring Confederation (IWIRC) e International Legal Tecnology Association (ILTA).La práctica de derecho es un campo que cambia rápidamente, así como su administración. La administración financiera ha evolucionado hacia el uso de herramientas tecnológicas, en todos sus aspectos, desde la planificación, gestión de casos, facturación y aspectos impositivos, lo cual incluye las informaciones financieras para la toma de decisiones. No importa lo que suceda en una firma de abogados, todas las decisiones importantes son sustentadas por los números: ¿cuántos abogados contratar?, ¿qué área de práctica es rentable?, ¿cómo se compara su firma con otras? Todas estas decisiones requieren conocimientos financieros. Los abogados están en la práctica de derecho para obtener beneficios, por lo que “Tenemos que administrar una firma como un negocio”
Desafíos del liderazgo entre abogados : inspirar, transformar y construir equipos para el éxito sostenible
Full text linkAngelina Angelov, MBA, CLM es administradora legal certificada en los Estados Unidos, consultora, autora y educadora. Actualmente se desempeña como Gerente Tesorera, miembro del consejo administrativo de Russin, Vecchi & Heredia Bonetti, una de las firmas de abogados más prestigiosas del país, además de liderar las áreas de gerencia administrativa y cumplimiento. Desde el año 2004, ha liderado equipos interdisciplinarios y gestionado áreas críticas como finanzas, recursos humanos, marketing, tecnología, desarrollo organizacional, innovación y gestión del conocimiento, logrando resultados sostenibles y consistentes.
En el ámbito académico, Angelina Angelov ha destacado como docente adjunta de Postgrado en la Universidad APEC, donde recibió el reconocimiento como Profesora Meritoria en 2019, una mención por publicaciones destacadas en 2021 y fue nominada al ACBSP Teaching Excellence Award en Chicago, 2023..
Desde abril de 2024, forma parte del cuerpo docente de la MBA en Gestión Legal de la Faculdade Baiana de Direito, en Brasil, donde imparte la clase de Liderazgo (dentro de la asignatura Emprendimiento Legal) y la Masterclass: Firma de Abogados en América Latina (dentro de la asignatura Marketing Legal).
En el ámbito internacional, Angelina es miembro activa de la Association of Legal Administrators (ALA), con sede en Chicago, donde actualmente forma parte de la Junta Directiva para el período 2023-2026. A lo largo de su membresía desde 2010, ha ocupado diversos cargos de liderazgo, incluyendo Presidente del Comité de Revisión de Productos y Servicios (2021-2024), miembro del Business Partner Relations Committee (BPRC) (2017-2020) y del International Relations Committee (IRC) (2013-2016 y 2019-2021).
Además, Angelina es miembro de la Plataforma de Inteligencia Estratégica del Foro Económico Mundial y de la Asociación Dominicana de Administradores de Recursos Humanos (ADOARH). Entre 2013 y 2016, co-lideró el Consejo de Administradores de Firmas de Abogados (LFAC) de Meritas para la región de Latinoamérica y el Caribe. También sirvió como Coordinadora del Comité de Recursos Humanos de la Asociación de Empresas de Inversión Extranjera (ASIEX) entre 2012 y 2015. Fue miembro de Legal Marketing Association (LMA), de la International Women’s Insolvency and Restructuring Confederation (IWIRC) e International Legal Tecnology Association (ILTA).RESUMEN |
En el entorno legal actual, los líderes de firmas de abogados enfrentan desafíos cada vez más complejos que requieren un enfoque estratégico y transformador. Este artículo examina cómo el liderazgo puede evolucionar para satisfacer las necesidades de un ecosistema cambiante, abordando temas esenciales como el pensamiento estratégico, la velocidad de la confianza y el bienestar sostenible.
También se analizan estrategias para liderar equipos multigeneracionales, fomentar la colaboración y desarrollar habilidades únicas de liderazgo. La innovación tecnológica y la adaptabilidad emergen como elementos cruciales para la competitividad y el éxito a largo plazo. Con un enfoque centrado en inspirar y transformar, los líderes pueden crear un entorno de trabajo positivo y resiliente que impulse el crecimiento sostenible de sus equipos y de la firma
Composing diverse policies for long-horizon tasks
Full text linkHumans utilise a large diversity of control and reasoning methods to solve
different robot manipulation and motion planning tasks. This diversity should be
reflected in the strategies used by robots in the same domains. In current practice
involving sequential decision making over long horizons, even when the formulation
is a hierarchical one, it is common for all elements of this hierarchy to adopt the
same representation. For instance, the overall policy might be a switching model
over Markov Decision Processes (MDPs) or local feedback control laws. This may
not be well suited to a variety of naturally observed behaviours. For instance, when
picking up a book from a crowded shelf, we naturally switch between goal-directed
reaching, tactile regrasping, sliding the book until it is comfortably off an edge and
then once again goal-directed pick and place. It is rare that a single representational
form adequately captures this diversity, even in such a seemingly simple task.
When the robot must learn or adapt policies from experience, this poses significant
challenges. The mis-match between the representational choices and the diversity of
task types can result in a significant (sometimes exponential) increase in complexity
with respect to time, observation and state-space dimensionality and other attributes.
These and other factors can make the learning of such tasks in a “tabula rasa” setting
extremely difficult. However, if we were willing to adopt a multi-representational
framing of the problem, and allow for some of these constituent modules to be
learned in different ways (some from expert demonstration, some by trial and error,
and perhaps some being controllers designed from first principles in model-based
formulations) then the problem becomes much more tractable. The core hypothesis we
explore is that it is possible to devise such learning methods, and that they significantly
outperform conventional alternatives on robotic manipulation tasks of interest.
In the first part of this thesis, we present a framework for sequentially composing
diverse policies facilitating the solution of long-horizon tasks. We rely on demonstrations to provide a quick, not necessarily expert and optimal, way to convey the
desired outcome. We model the similarity to demonstrated states in a Goal Scoring
Estimator model. We show in a real robot experiment the benefits of diverse policies
relying on their own strong inductive biases to efficiently solve different aspects of the
task, through sequencing by the Goal Scoring Estimator model.
Next, we demonstrate how we can elicit policy structure through causal analysis
and task structure through more efficient demonstrations involving interventions. This
allows us to alter the manner of execution of a particular policy to match a desired
learned user specification. Building a surrogate model of the demonstrator gives us
the ability to causally reason about different aspects of the policy and which parts
of that policy are salient. We can observe how intervening in the world by placing
additional symbols impacts the validity of the original plan.
Finally, observing that ‘static’ imitation learning datasets can be limiting if we are
aiming to create more robust policies, we present the Learning from Inverse Intervention
framework. This allows the robot to simultaneously learn a policy while interacting
with the demonstrator. In this interaction, the robot intervenes when there is little
information gain and pushes the demonstrator to explore more informative areas
even as the demonstration is being performed in real-time. This interaction brings the
added benefit of drawing out information about the importance of different regions
of the task. We verify the salience by visually inspecting samples from a generative
model and by crafting plans that test these hypothetical areas.
These methods give us the ability to use demonstrations of a task, to build policies
for salient targets, to alter their manner of execution and inspect to understand the
causal structure, and to sequence them to solve novel tasks
Clustering as a tool for self-generation of intelligent systems : a survey.
Full text linkFuzzy Rule Based (FRB) and Neuro-fuzzy systems are commonly used as a basis for intelligent systems due to their transparent and simple human interpretable structure. One of the crucial steps in designing FRB and neuro-fuzzy systems is to innovate the rule base. Data clustering is one of the approaches that have been applied extensively to automatically generate rules from input-output data. The goal of this paper is to critically review some of the most commonly used as well as recently developed clustering techniques, emphasizing their use in rule base generation. The paper explores the shift from offline clustering techniques to online and finally to evolving techniques that originated due to the current demand of adaptive systems
An approach to online identification of Takagi-Sugeno fuzzy models
Full text linkAn approach to the online learning of Takagi-Sugeno (TS) type models is proposed in the paper. It is based on a novel learning algorithm that recursively updates TS model structure and parameters by combining supervised and unsupervised learning. The rule-base and parameters of the TS model continually evolve by adding new rules with more summarization power and by modifying existing rules and parameters. In this way, the rule-base structure is inherited and up-dated when new data become available. By applying this learning concept to the TS model we arrive at a new type adaptive model called the Evolving Takagi-Sugeno model (ETS). The adaptive nature of these evolving TS models in combination with the highly transparent and compact form of fuzzy rules makes them a promising candidate for online modeling and control of complex processes, competitive to neural networks. The approach has been tested on data from an air-conditioning installation serving a real building. The results illustrate the viability and efficiency of the approach. The proposed concept, however, has significantly wider implications in a number of fields, including adaptive nonlinear control, fault detection and diagnostics, performance analysis, forecasting, knowledge extraction, robotics, behavior modeling
On-line identification of MIMO evolving Takagi-Sugeno fuzzy models
Full text linkEvolving Takagi-Sugeno (eTS) fuzzy models and the method for their on-line identification has been recently introduced as an effective tool for design of flexible system models with minimum a priori information. Their structure develops on-line during the process of model identification itself. In this paper, this approach has been extended for the case of multi-input multi-output (MIMO) system model. Both parts of the identification algorithm, namely the unsupervised fuzzy rule-base antecedents learning by a recursive, noniterative clustering, and the supervised linear sub-model parameters learning by Kalman-filtering-based procedure, are extended for the MIMO case. The radius of influence of each fuzzy rule is considered a vector instead of a scalar as in the original eTS approach, allowing different areas of the data space to be covered by each input variable. As in the eTS, in MIMO eTS, the rule-base and parameters of the fuzzy model continually evolve by adding new rules with more summarization power and by modifying existing rules and parameters. Simulation results using a well-known benchmark are considered in this paper. Further investigation concern the application of MIMO eTS to predictive modeling of the speech spectrum magnitude, classification of multi-channel source modulation etc. (c) IEEE Pres
Análisis de paquetes con Wireshark, estudio de vulnerabilidades
Full text link[ES] El siguiente trabajo se centra en ilustrar, de forma profunda y detallada, cómo funcionan ciertos protocolos y sistemas que usamos en nuestra vida cotidiana al conectarnos a internet. Mediante el analizador de protocolos Wireshark, se estudian exhaustivamente todas las piezas que construyen algunos protocolos y sistemas fundamentales para el correcto funcionamiento de nuestras redes.
Para nuestro estudio elegimos analizar el protocolo ARP (Address Resolution Protocol), desglosarlo con Wireshark y demostrar cómo funciona un ataque MITM con ARP Cache Poisoning. También explicaremos en detalle cómo funcionan los protocolos HTTP y HTTPS.
Para cada uno de los protocolos y sistemas elegidos para realizar el estudio, hemos diseccionado los paquetes que los forman para comprender exactamente qué sucede. Acto seguido, se comentan las vulnerabilidades que tienen y se intentan simular escenarios donde se explotan las susodichas, ilustrando en profundidad cómo funciona. Para ello, se emplean máquinas virtuales con un sistema operativo especializado en ciberseguridad, por ejemplo, Kali Linux, que incluye varias herramientas muy útiles. Por último, se proponen alternativas o parches que mejoran la seguridad, con ejemplos prácticos que ilustran las ventajas de estas.
Como conclusión, justificaremos la utilización en la práctica de unos u otros protocolos, aportando nuestro análisis y datos.[EN] The following work is centered around illustrating in a detailed way how certain protocols and systems, which we use in our daily lives, function in our networks. With the help of the protocol analyzer Wireshark, we will thoroughly analyze each of the pieces which build some of the fundamental protocols and systems that allow our networks to work properly.
For our study we choose to analyze the ARP (Address Resolution Protocol) protocol, break it down with Wireshark and show how an ARP Cache Poisoning attack works. We are also going to explain how the HTTP and HTTPS protocols work.
For each of the protocols and systems we have chosen for the study, we dissect the packets that make them up to understand exactly what happens. Then, we discuss the vulnerabilities they have and simulate scenarios where the aforementioned are exploited, illustrating in depth how it works. For this, virtual machines with an operating system specialized in cybersecurity are used, for example, Kali Linux, which includes several very useful tools. Finally, alternatives or patches that improve security are proposed, with practical examples that illustrate the advantages of these. In conclusion, we justify the use in practice of one or the other protocols, providing our analysis and data.[CA] El següent treball se centra en il·lustrar, de manera profunda i detallada, com
funcionen uns certs protocols i sistemes que usem en la nostra vida quotidiana en
connectar-nos a internet. Mitjançant l'analitzador de protocols Wireshark, s'estudien
exhaustivament totes les peces que construeixen alguns protocols i sistemes
fonamentals per al correcte funcionament de les nostres xarxes.
Per al nostre estudi triem analitzar el protocol ARP (Address Resolution Protocol)
desglossar-lo amb Wireshark i demostrar com funciona un atac MITM (Man In The
Middle) amb ARP Cache Poisoning.
Per a cadascun dels protocols i sistemes triats per a realitzar l'estudi, hem
disseccionat els paquets que els formen per a comprendre exactament què succeeix.
Tot seguit, es comenten les vulnerabilitats que tenen i s'intenten simular escenaris on
s'exploten les susdites, il·lustrant en profunditat com funciona. Per a això, s'empren
màquines virtuals amb un sistema operatiu especialitzat en ciberseguretat, per exemple,
Kali Linux, que inclou diverses eines molt útils. Finalment, es proposen alternatives o
pegats que milloren la seguretat, amb exemples pràctics que il·lustren els avantatges
d'aquestes.
Com a conclusió, justificarem la utilització en la pràctica d'els uns o els altres
protocols, aportant la nostra anàlisi i dades.Mitkov Angelov, I. (2021). Análisis de paquetes con Wireshark, estudio de vulnerabilidades. Universitat Politècnica de València. https://riunet.upv.es/handle/10251/174236TFG
- …
