Knowledge management in intelligent tutoring systems

In the last years, Intelligent Tutoring Systems have been a very successful way for improving learning experience. Many issues must be addressed until this technology can be defined mature. One of the main problems within the Intelligent Tutoring Systems is the process of contents authoring: knowledge acquisition and manipulation processes are difficult tasks because they require a specialised skills on computer programming and knowledge engineering. In this thesis we discuss a general framework for knowledge management in an Intelligent Tutoring System and propose a mechanism based on first order data mining to partially automate the process of knowledge acquisition that have to be used in the ITS during the tutoring process. Such a mechanism can be applied in Constraint Based Tutor and in the Pseudo-Cognitive Tutor. We design and implement a part of the proposed architecture, mainly the module of knowledge acquisition from examples based on first order data mining. We then show that the algorithm can be applied at least two different domains: first order algebra equation and some topics of C programming language. Finally we discuss the limitation of current approach and the possible improvements of the whole framework.

Effects and Modes od Action of Canopy Management Practices on Vine Physiology and Berry Composition in Organically-Cultivated cv. Sangiovese (Vitis Vinifera L.)

In organic and biodynamic vineyards, canopy management practices should be carefully and timely modulated, particularly in a context of climate change, for successfully achieving balanced plants, ventilated and exposed berries, elevated grape and wine quality. In 2013 and 2014, characterized by contrasting climatic conditions, the implications of post-veraison (late) or pea-size trimming, post-veraison or pre-harvest late defoliations and shoot-positioning (post-veraison) were assessed against long-shoots non treated controls, under field conditions on organically-cultivated cv. Sangiovese. The key agronomic and enological relevance of late trimming and defoliations clearly emerged in both seasons. Berry skin phenolics (e.g. anthocyanins, flavonols) increased markedly, without changes in technological parameters. In case of early trimming, such positive effects were observed only in 2013. Maintaining long shoots for shading decreased anthocyanins, flavonols and total phenolics concentrations and promoted the production of compact bunches. Experimental data strongly designated late trimming, a practice proved to contain yield and bunch compactness, as a valuable alternative to cluster thinning. Late trimming, defoliations and shoot positioning reduced the severity of Botrytis cluster rot. The highest levels of berry skins phenolic compounds in late trimmed and defoliated plants could have contributed control the severity of this pathogen. The enological benefits induced by late trimming and defoliations and shoot positioning emerged in both young and aged wines. For the first time, cell cultures from cv. Sangiovese berry tissues were obtained and enabled to investigate, in controlled conditions, the relations between mechanisms regulating secondary metabolism in grapevine cells and changes induced by environmental and agronomic factors. The Doctoral Dissertation strongly highlights the need to consider, for a proper interpretation of the multiple modifications induced by canopy management strategies, physiological mechanisms other than the canonic source-sink relationships, in particular their impact on the vine hormonal status.