Skip to content

Free University of Bozen-Bolzano

26 Jun 2017 29 Jun 2017

Affective Computing, Context and Processing - A cycle of lectures with Grzegorz J. Nalepa

Affective Computing (AfC) is a field of study that puts interest in the design and description of systems that are able to collect, interpret, and process emotional states.

Speaker Prof. Grzegorz J. Nalepa, AGH University, Krakow, Poland

Date 26 Jun 2017 - 00:00 29 Jun 2017 - 23:59

Location Room BZ P1.02, Dominikanerplatz 3 - Piazza Domenicani, 3, 39100 Bozen-Bolzano

More information Francesco Ricci
Francesco.Ricci@unibz.it

Description

26 June, 14:00-15:00:
Cognitive assistants as context-aware systems on mobile devices

Research in the area of pervasive computing and ambient intelligence aims to make use of context information to allow devices or applications behave in a context-aware, thus "intelligent" way. Context-aware systems have been studied in several fields and developed for over 30 years. However, they are still identified by Gartner alongside cloud computing, business impact of social computing and pattern based strategy. By a classic definition context is any information that can be used to characterize the situation of an entity.
We will focus on systems implemented with the use of mobile devices such as smartphones. In such dynamic systems a number of challenges need to be addressed. They include management of uncertain context data, as well as the need of adaptability. Cognitive assistants, or more recently smart advisors (sometimes personal recommender tools), are computer systems that augment human capabilities by providing decision support. Today, such systems should be personalized, and use wearable devices and ambient intelligence technologies to be constantly available to the user. The contex-aware paradigm provides means for the development of such systems. In the talk we will present our recent results in this area including new knowledge representation and reasoning methods and tools introduced in the KnowMe project.

27 June, 14:00-15:00:
Why we want machines to understand emotions? Introduction to Affective Computing


Affective Computing (AfC) is a field of study that puts interest in the design and description of systems that are able to collect, interpret, and process emotional states. Assuming that emotions are physical and cognitive and as such they can be studied interdisciplinary by computer science, biomedical engineering and psychology. Today most often harvested and processed affective information is about: speech, body gestures and poses, facial expressions, and physiological monitoring. We will give an overview of important aspects of AfC. Research challenges in this area include detection and classification of affective states, as well as inducement of emotions in laboratory studies. In our work on AfC we focus on wearable sensors for physiological monitoring which should allow for developing ubiquitous affective systems. We argue, that human-centric cognitive computer systems should be able to detect and interpret changes of emotional state of the users. To this goal we propose to combine to computing approaches: affective computing and context-aware systems. As such we will also explore opportunities of incorporation of affective information into context-aware systems paradigm. We propose the AfCAI software platform as a solution to the development of cognitive assistants that are based on context-aware and affective systems.

28 June, 14:00-15:00:
Development of Rule-based Context-Aware Systems with mobile Android devices. Tutorial on the KnowMe project tools


The main objective of the KnowMe project was to propose methods for knowledge modeling and mediation in mobile context-aware systems and to support a user in adapting the system to his or her personal preferences and habits. A further goal was to improve management of uncertain and incomplete knowledge.
KnowMe is built on the results of the Semantic Knowledge Engineering approach that provides methods and tools for development of rule-based systems. The project provides a visual web-based editor (HWEd) for decision rules grouped in decision tables. A complete rule based system is then deployed and executed by the HeaRTDroid rule engine. It is probably the only open rule-based engine that runs both on desktop and the mobile platform (Android). Two additional KnowMe tools are important in the design of context-aware systems. The first is ContextViewer that allows to review and visualize context data. The second is ContextSimulator. Thanks to it, it is possible to reply the acquired context date and use it to test the prototype of a context-aware system. In the tutorial we demonstrate the practical use of all of these tools with illustrative examples.

29 June, 10:30-11:30:
Integrating Business Processes with Decision Rules - a formalized approach


Business Processes describe the ways in which operations are carried out in order to accomplish the intended objectives of organizations. A process can be depicted using a modeling notation, such as Business Process Model and Notation. Its model can also describe operational aspects of every task.
However, in a properly designed model, the detailed aspects of low-level logic should be delegated to external services, especially to a Business Rule Engine. Business Rules support the specification of knowledge in a declarative manner and can be successfully used for specification of details for process tasks and events. Unfortunately, there is no unified model of processes integrated with rules that supports the design and ensures data types consistency. Thus, we introduce a formal description of the integration of Business Processes with Business Rules. We provide a general model for such an integration as well as the model applied to a specific rule representation from the Semantic Knowledge Engineering approach. We demonstrate how the integrated model can be designed, and then deployed and executed in a hybrid runtime environment composed of the Activity business process engine and HeaRT - the SKE rule engine.

Grzegorz J. Nalepa is an engineer with degrees in computer science - artificial intelligence, and philosophy. He has been working in the area of intelligent systems and knowledge engineering for over 15 years. He formulated the eXtended Tabular Trees rule representation method, as well as the Semantic Knowledge Engineering approach. He authored a book "Modeling with Rules using Semantic Knowledge Engineering", to be published by Springer in 2017. He co-authored over 150 research papers in international journals and conferences. He coordinates GEIST - Group for Engineering of Intelligent Systems and Technologies (http://geist.re/) at AGH University, Krakow, Poland. For almost 10 years he's been co-chairing the Knowledge and Software Engineering Workshop (KESE) at KI, the German AI conference, Spanish CAEPIA, as well ECAI. He is the President of the Polish Artificial Intelligence Society (PSSI), member of EurAI. He is also a member of IEEE, Italian Artificial Intelligence Society (AI*IA), KES, Polish Cognitive Science Society (PTK).
Feedback / Request info