El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / Protein fold recognition is an important task in the biological area. Different machine learning methods such as multiclass classifiers, one-vs-all and ensemble nested dichotomies were applied to this task and, in most of the cases, multiclass approaches were used. In this paper, we compare classifiers organized in tree structures to classify folds. We used a benchmark dataset containing 125 features to predict folds, comparing different supervised methods and achieving 54% of accuracy. An approach related to tree-structure of classifiers obtained better results in comparison with a hierarchical approach. / Revisión por pares

This paper proposes an innovative way to address real cases of production prediction. This approach consists in the decomposition of original time series into time sub-series according to a group of factors in order to generate a predictive model from the partial predictive models of the sub-series. The adjustment of the models is carried out by means of a set of statistic techniques and Automatic Learning. This method was compared to an intuitive method consisting of a direct prediction of time series. The results show that this approach achieves better predictive performance than the direct way, so applying a decomposition method is more appropriate for this problem than non-decomposition.

Künstliche Intelligenz (KI) verändert die Arbeitswelt und führt zu einer dynamischen Neugestaltung der Arbeitsteilung zwischen Mensch und Technik in Unternehmen. Dies betrifft nicht zuletzt auch den Bereich der Führung. KI-Systeme können Führungskräfte bei der Ausübung ihrer Aufgaben unterstützen, etwa indem sie vor allem administrative Koordinations- und Kontrollaufgaben und -entscheidungen übernehmen. Dadurch bleibt den Führungskräften mehr Zeit, sich der Personalführung oder Innovationsprozessen zu widmen. Führungskräfte nehmen künftig eine zentrale Rolle ein, den KI-Transformationsprozess erfolgreich mitzugestalten und dabei im Rahmen ihrer Fürsorgepflichten besonders auf die menschengerechte Gestaltung der KI-Systeme mit den und für die Beschäftigten hinzuwirken. Expertinnen und Experten der Arbeitsgruppe Arbeit/Qualifikation und Mensch-Maschine-Interaktion der Plattform Lernende Systeme wollen mit diesem Whitepaper aufzeigen, welche neuen Möglichkeiten und Chancen, aber auch welche Herausforderungen durch den Einsatz von KI-Systemen in Führungsaufgaben entstehen können. Dazu skizzieren sie zunächst die Herausforderungen, mit denen Führungskräfte schon heute durch digitale Technologien konfrontiert sind (Kapitel 2). Darauf aufbauend wird dargelegt, welche spezifischen Auswirkungen der Einsatz von Lernenden Systemen auf unterschiedliche Führungsaufgaben haben kann, die anhand von vier Aufgabenclustern vorgestellt werden: Strategische Führung, Organisationale Führung, Personalführung und Selbstführung (Kapitel 3). Entlang dieser Systematik wird aufgezeigt, welche Beiträge Lernende Systeme dabei als „unterstützender Akteur“ leisten können. Führung unterliegt einem Wandel. Bedingt durch den digitalen, strategischen Transformationsprozess in Unternehmen werden traditionelle, hierarchische Führungsmodelle sukzessive durch kooperative, netzwerkdynamische und werteorientierte Führungsstile abgelöst. Dies verändert zunehmend die Rolle der Führungskraft hin zu einem vermittelnden ,Übersetzer‘, Vorbild und Coach und verlangt nach einem stärkeren partizipativen Führungsstil (Kapitel 2). Lernende Systeme in der Arbeitswelt werden nicht nur die Rolle von Führungskräften weiter verändern, sondern zunehmend auch deren Aufgaben. Als technologisches Hilfsmittel unterstützen sie bei Aufgaben, die eine hohe Strukturierung und Regelmäßigkeiten aufweisen, sodass mehr Zeit für strategische Aufgaben und Entwicklungen oder mitarbeiterbezogene Führung bleibt. Eigenständig lernende (KI-)Systeme kommen zudem neben der Führungsperson als weiterer unterstützender und möglichst entlastender ,Akteur‘ zum Führungsprozess hinzu. Mit dem Einsatz von Lernenden Systemen bekommen zentrale Werte wie Datenschutz, Transparenz oder Fairness in der Führung für die Beschäftigten eine neue Bedeutung: Daher darf es nicht verwundern, wenn die Einführung von KI in der Führung zunächst von Skepsis begleitet wird. Entscheidend wird es deshalb sein, das Vertrauen und die Akzeptanz der Beschäftigten sowohl in die Technologie als auch in die eigene Führung für eine gelingende Zusammenarbeit zu fördern. Dies setzt eine frühzeitige Einbindung der Beschäftigten sowie der Interessensvertretungen in Planung und Gestaltung der KI-Systeme voraus: Für ein gelingendes KI-Change-Management in Unternehmen wird eine passende Führungs- und Unternehmenskultur notwendig sein, die auf Partizipation, Offenheit und Transparenz beruht. KI und Führung lassen sich gut ergänzen und können für eine moderne, menschenzentrierte Führung einen wichtigen Beitrag leisten. Dafür sind notwendige Rahmenbedingungen (in den Unternehmen) zu schaffen, damit das volle Potenzial der KI-Systeme auch für Führungskräfte nutzbar werden kann. Welche effektiven Maßnahmen dabei helfen, KI-Systeme für Führungsaufgaben einzusetzen, formulieren die Autorinnen und Autoren in passenden Gestaltungsoptionen (Kapitel 4). Zu diesen Gestaltungsoptionen zählen unter anderem eine menschenzentrierte Aufgabenzuteilung zwischen KI und Beschäftigten durch die Führungskräfte, das Aufbauen von notwendigen KI-Kompetenzen der Mitarbeitenden oder das Vorleben einer Feedbackkultur, die die Perspektiven der Beschäftigten und ihrer Interessensvertretungen offen einbindet.

Technological innovations have been shown to improve the quality of health information and improve safety in health care systems. The purpose of this project was to offer hospital nurses a more flexible and practical alternative to education and training than the traditional face-to-face method, supporting nurse educators in overcoming many of the obstacles in responding to nurses' needs in the clinical areas. This project used a randomized, 2-group posttest-only experimental design to measure the effect of treatment at a targeted hospital. The experimental group received a new instructional approach using an Electronic Learning Management System (ELMS) and the control group used the site's traditional standard method; both groups completed the Posttest Knowledge Assessment. The study population consisted of registered nurses who had attended the project site's Safe Blood Transfusion Practice program over a period of 1 month. There were no significant differences between the 2 groups' members' gender, age, level of education, or nursing experience. Data analysis showed a significant (p < .00) difference between the 2 groups' posttest scores, indicating that the participants who used the ELMS attained a higher median knowledge (M = 89.39, SD = 9.26) than did participants who received traditional, face-to-face instruction (M = 76.85, SD = 10.628). These results suggest that ELMS-based learning is a more effective method of instructional delivery that could effectively replace many of the traditional face-to-face education programs. Implementing this innovative system will create positive social change on the targeted hospital by improving health care delivery. The application of the finding would support clinical educators to improve educational delivery to their clients at the clinical areas.

No description available.

[EN] The stupefying success of Artificial Intelligence (AI) for specific problems, from recommender systems to self-driving cars, has not yet been matched with a similar progress in general AI systems, coping with a variety of problems. This dissertation deals with the long-standing problem of creating more general AI systems, through the analysis of their development and the evaluation of their cognitive abilities. Firstly, this thesis contributes with a general-purpose learning system that meets several desirable characteristics in terms of expressiveness, comprehensibility and versatility. The system works with approaches that are inherently general: inductive programming and reinforcement learning. The system does not rely on a fixed library of learning operators, but can be endowed with new ones, so being able to operate in a wide variety of contexts. This flexibility, jointly with its declarative character, makes it possible to use the system as an instrument for better understanding the role (and difficulty) of the constructs that each task requires. The learning process is also overhauled with a new developmental and lifelong approach for knowledge acquisition, consolidation and forgetting, which is necessary when bounded resources (memory and time) are considered. Secondly, this thesis analyses whether the use of intelligence tests for AI evaluation is a much better alternative to most task-oriented evaluation approaches in AI. Accordingly, we make a review of what has been done when AI systems have been confronted against tasks taken from intelligence tests. In this regard, we scrutinise what intelligence tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence. Finally, the analysis of the concepts of development and incremental learning in AI systems is done at the conceptual level but also through several of these intelligence tests, providing further insight for the understanding and construction of general-purpose developing AI systems. / [ES] El éxito abrumador de la Inteligencia Artificial (IA) en la resolución de tareas específicas (desde sistemas de recomendación hasta vehículos de conducción autónoma) no ha sido aún igualado con un avance similar en sistemas de IA de carácter más general enfocados en la resolución de una mayor variedad de tareas. Esta tesis aborda la creación de sistemas de IA de propósito general así como el análisis y evaluación tanto de su desarrollo como de sus capacidades cognitivas. En primer lugar, esta tesis contribuye con un sistema de aprendizaje de propósito general que reúne distintas ventajas como expresividad, comprensibilidad y versatilidad. El sistema está basado en aproximaciones de carácter inherentemente general: programación inductiva y aprendizaje por refuerzo. Además, dicho sistema se basa en una biblioteca dinámica de operadores de aprendizaje por lo que es capaz de operar en una amplia variedad de contextos. Esta flexibilidad, junto con su carácter declarativo, hace que sea posible utilizar el sistema de forma instrumental con el objetivo de facilitar la comprensión de las distintas construcciones que cada tarea requiere para ser resuelta. Por último, el proceso de aprendizaje también se revisa por medio de un enfoque evolutivo e incremental de adquisición, consolidación y olvido de conocimiento, necesario cuando se trabaja con recursos limitados (memoria y tiempo). En segundo lugar, esta tesis analiza el uso de tests de inteligencia humana para la evaluación de sistemas de IA y plantea si su uso puede constituir una alternativa válida a los enfoques actuales de evaluación de IA (más orientados a tareas). Para ello se realiza una exhaustiva revisión bibliográfica de aquellos sistemas de IA que han sido utilizados para la resolución de este tipo de problemas. Esto ha permitido analizar qué miden realmente los tests de inteligencia en los sistemas de IA, si son significativos para su evaluación, si realmente constituyen problemas complejos y, por último, si son útiles para entender la inteligencia (humana). Finalmente se analizan los conceptos de desarrollo cognitivo y aprendizaje incremental en sistemas de IA no solo a nivel conceptual, sino también por medio de estos problemas mejorando por tanto la comprensión y construcción de sistemas de propósito general evolutivos. / [CA] L'èxit aclaparant de la Intel·ligència Artificial (IA) en la resolució de tasques específiques (des de sistemes de recomanació fins a vehicles de conducció autònoma) no ha sigut encara igualat amb un avanç similar en sistemes de IA de caràcter més general enfocats en la resolució d'una major varietat de tasques. Aquesta tesi aborda la creació de sistemes de IA de propòsit general així com l'anàlisi i avaluació tant del seu desenvolupament com de les seues capacitats cognitives. En primer lloc, aquesta tesi contribueix amb un sistema d'aprenentatge de propòsit general que reuneix diferents avantatges com ara expressivitat, comprensibilitat i versatilitat. El sistema està basat en aproximacions de caràcter inherentment general: programació inductiva i aprenentatge per reforç. A més, el sistema utilitza una biblioteca dinàmica d'operadors d'aprenentatge pel que és capaç d'operar en una àmplia varietat de contextos. Aquesta flexibilitat, juntament amb el seu caràcter declaratiu, fa que siga possible utilitzar el sistema de forma instrumental amb l'objectiu de facilitar la comprensió de les diferents construccions que cada tasca requereix per a ser resolta. Finalment, el procés d'aprenentatge també és revisat mitjançant un enfocament evolutiu i incremental d'adquisició, consolidació i oblit de coneixement, necessari quan es treballa amb recursos limitats (memòria i temps). En segon lloc, aquesta tesi analitza l'ús de tests d'intel·ligència humana per a l'avaluació de sistemes de IA i planteja si el seu ús pot constituir una alternativa vàlida als enfocaments actuals d'avaluació de IA (més orientats a tasques). Amb aquesta finalitat, es realitza una exhaustiva revisió bibliogràfica d'aquells sistemes de IA que han sigut utilitzats per a la resolució d'aquest tipus de problemes. Açò ha permès analitzar què mesuren realment els tests d'intel·ligència en els sistemes de IA, si són significatius per a la seua avaluació, si realment constitueixen problemes complexos i, finalment, si són útils per a entendre la intel·ligència (humana). Finalment s'analitzen els conceptes de desenvolupament cognitiu i aprenentatge incremental en sistemes de IA no solament a nivell conceptual, sinó també per mitjà d'aquests problemes millorant per tant la comprensió i construcció de sistemes de propòsit general evolutius. / Martínez Plumed, F. (2016). Incremental and developmental perspectives for general-purpose learning systems [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/67269

Studies have revealed that securing Information Systems (IS) from intentional misuse is a concern among organizations today. The use of Web-based systems has grown dramatically across industries including e-commerce, e-banking, e-government, and e learning to name a few. Web-based systems provide e-services through a number of diverse activities. The demand for e-learning systems in both academic and non-academic organizations has increased the need to improve security against impersonation fraud. Although there are a number of studies focused on securing Web-based systems from Information Systems (IS) misuse, research has recognized the importance of identifying suitable levels of authenticating strength for various activities. In e-learning systems, it is evident that due to the variation in authentication strength among controls, a ‘one size fits all’ solution is not suitable for securing diverse e-learning activities against impersonation fraud. The main goal of this study was to use the framework of the Task-Technology Fit (TTF) theory to conduct an exploratory research design to empirically investigate what levels of authentication strength users perceive to be most suitable for activities in e-learning systems against impersonation fraud. This study aimed to assess if the ‘one size fits all’ approach mainly used nowadays is valid when it comes to securing e-learning activities from impersonation fraud. Following the development of an initial survey instrument (Phase 1), expert panel feedback was gathered for instrument validity using the Delphi methodology. The initial survey instrument was adjusted according to feedback (Phase 2). The finalized Web-based survey was used to collect quantitative data for final analyses (Phase 3). This study reported on data collected from 1,070 e-learners enrolled at a university. Descriptive statistics was used to identify what e-learning activities perceived by users and what users perceived that their peers would identify to have a high potential for impersonation. The findings determined there are a specific set of e-learning activities that high have potential for impersonation fraud and need a moderate to high level of authentication strength to reduce the threat. Principal Component Analysis was used to identify significant components of authentication strength to be suitable against the threats of impersonation for e-learning activities.

Throughout life, we continuously accumulate data, information and knowledge. The ability to recall much of this accumulated knowledge commonly deteriorates with time, though some forms part of what is referred to as tacit knowledge. In the context of education, students access and interact with a teacher’s knowledge in order to create their own, and may have their own data, information and knowledge that could be added to teacher’s knowledge for everyone’s benefit. The realization that students can contribute to enhancing personal knowledge is an important cornerstone in developing a mentor (teacher, tutor and facilitator) focused knowledge system. The research presented in this thesis discusses an integrated framework that manages an individual’s personal data, information and knowledge and enables it to be enhanced by others, in the context of a blended teaching and learning environment. Existing related models, structures, systems and current practices are discussed. The core outcomes of this thesis include: • the virtualMe framework that can be utilized when developing Web based teaching and learning systems; • the sniplet content model that can be used as the basis for sharing information and knowledge; • an annotation framework used to manage knowledge acquisition; and • a multimedia object (MMO) model that: o allows for related media artefacts to be intuitively grouped in a logical collection; o includes a meta-data schema that encompasses other metadata structures, and manages context and referencing; and o includes a model allowing component parts to be reaggregated if they are separated. The virtualMe framework provides the ability to retain context while transferring the content from one person to another and from one place to another. The framework retains the content’s original context and then allows the receiver to customise the content and metadata so that the content becomes that person’s knowledge. A mechanism has been created for such contextual transfer of content (context retained by the metadata).

In this thesis, we have studied the problem of detecting automated Twitter accounts related to the Ukraine conflict using supervised learning. A striking problem with the collected data set is that it was initially lacking a ground truth. Traditionally, supervised learning approaches rely on manual annotation of training sets, but it incurs tedious work and becomes expensive for large and constantly changing collections. We present a novel approach to synthetically generate large amounts of labeled Twitter accounts for detection of automation using a rule-based classifier. It significantly reduces the effort and resources needed and speeds up the process of adapting classifiers to changes in the Twitter-domain. The classifiers were evaluated on a manually annotated test set of 1,000 Twitter accounts. The results show that rule-based classifier by itself achieves a precision of 94.6% and a recall of 52.9%. Furthermore, the results showed that classifiers based on supervised learning could learn from the synthetically generated labels. At best, the these machine learning based classifiers achieved a slightly lower precision of 94.1% compared to the rule-based classifier, but at a significantly better recall of 93.9% / Detta exjobb har undersökt problemet att detektera automatiserade Twitter-konton relaterade till Ukraina-konflikten genom att använda övervakade maskininlärningsmetoder. Ett slående problem med den insamlade datamängden var avsaknaden av träningsexempel. I övervakad maskininlärning brukar man traditionellt manuellt märka upp en träningsmängd. Detta medför dock långtråkigt arbete samt att det blir dyrt förstora och ständigt föränderliga datamängder. Vi presenterar en ny metod för att syntetiskt generera uppmärkt Twitter-data (klassifieringsetiketter) för detektering av automatiserade konton med en regel-baseradeklassificerare. Metoden medför en signifikant minskning av resurser och anstränging samt snabbar upp processen att anpassa klassificerare till förändringar i Twitter-domänen. En utvärdering av klassificerare utfördes på en manuellt uppmärkt testmängd bestående av 1,000 Twitter-konton. Resultaten visar att den regelbaserade klassificeraren på egen hand uppnår en precision på 94.6% och en recall på 52.9%. Vidare påvisar resultaten att klassificerare baserat på övervakad maskininlärning kunde lära sig från syntetiskt uppmärkt data. I bästa fall uppnår dessa maskininlärningsbaserade klassificerare en något lägre precision på 94.1%, jämfört med den regelbaserade klassificeraren, men med en betydligt bättre recall på 93.9%.

No description available.