No abstract

This article is a proof-of-concept case study to evaluate the functionality of a block metaphor–based linked data generator. In this work, we chose to produce linked data repository of recipes, which provide a medium for people to share their regional and healthy recipes with the masses. However, the same approach can also be adapted easily to other domains. Therefore, the applicability of our approach extends well beyond the food domain that we are considering in this article. As a medium for information sharing and understanding between heterogeneous systems, ontologies will play an important role in the realisation of the Internet of things (IoT) vision. Therefore, an ontology-based recipe repository would also be one of the basic blocks of a smart kitchen environment. However, building ontologies is a challenging task, especially for users who are not conversant in the ontology building languages. This article proposes an approach that can be used even by non-experts and facilitates the sharing and searching of recipe data. In our case, we exploit the features of the block paradigm to publish recipes in Linked Data format. In this way, users do not have to know the OWL (Web Ontology Language) syntax and the text input is kept minimal. As far as we know, this article is the first study that produces linked data using Blockly in the literature. We also conducted a user-based evaluation of the proposed approach using the System Usability Scale (SUS) questionnaire.

No abstract

Turkish Music pieces are used in various studies including makam recognition in computational music domain. Turkish Music pieces offer a rich content to the researchers because of their different makam properties. SymbTr is one of the most referred Turkish Music data sets in this area. In this study, the pieces from SymbTr data set belonging to 13 makams are used to execute 10 different machine learning algorithms for makam recognition and the performances of these algorithms are evaluated. These algorithms were executed on WEKA application environment and the performances in makam recognition were obtained with F-measure and recall metrics. The machine learning algorithms performed between 82% and 88%.

No abstract