When it comes to the writing of a new logic program or theory, it is of great importance to obtain a concise and minimal representation, for simplicity and ease of interpretation reasons. There are already a few methods and many tools, such as Karnaugh Maps or the Quine-McCluskey method, as well as their numerous software implementations, that solve this minimization problem in Boolean logic. This is not the case for Here-and-There logic, also called three-valued logic. Even though there are theoretical minimization methods for logic theories and programs, there aren’t any published tools that are able to obtain a minimal equivalent logic program. In this paper we present the first version of a tool called that is able to efficiently obtain minimal and equivalent representations for any logic program in Here-and-There. The described tool uses an hybrid method both leveraging a modified version of the Quine-McCluskey algorithm and Answer Set Programming techniques to minimize fairly complex logic programs in a reduced time.

The mRNA molecules expressed in cow’s milk are important molecular biomarkers for different physiological and pathological conditions in cattle. The prediction of the quantity that a specific mRNA type could be expressed in cow’s milk is a challenging theoretical task. The current study presents for the first time several different Machine Learning models to predict the mRNA expression using the mRNA secondary structure fragments. This unique methodology is based on a dataset of experimental mRNA expression data. Each mRNA molecule has a specific secondary structure represented as a string that can be used to read all the possible mRNA secondary structure fragments. This information is used as input for the Machine Learning methods from Weka software in order to obtain classification models that can predict low, medium and high expression of new mRNA types in the cow’s milk. The mRNA expression levels have been measured with High Throughput Screening techniques. The initial features included the counting of the mRNA secondary structure fragments for each expressed mRNA. The model features were transformed in frequencies and the expression levels were converted into low and high classes. In order to reduce the high number of possible features, a feature selection method has been applied. Thus, the best classification model was obtained with BayesNet method and is based on 24 features and 4067 cases. The model has the true positive rate for the low mRNA expression class of 0.78 (average true positive rate of 0.66). Further studies are needed improve the current results, using datasets with different feature sets and more advanced Machine Learning methods.

In this paper we describe an environment that enables the interaction and data-fetching through a computer system from the Xiaomi Mi Band 2, a very popular and inexpensive Bluetooth Low Energy Fitness device, thus making it suitable for health-care long-term projects in which continuously gathering sleep and activity data is required. The environment is composed by a communication server running a custom library, exposed through both a shell command prompt and a RESTful API so it can be used by any other system connected to this server. The library is capable of connecting to an arbitrary number of devices at a time, bypassing many restrictions of the manufacturer’s proprietary application and not depending on an outgoing network connection to synchronize data between the system and the devices. In this paper we cover not only the process to enable communication with the target device from computers but also the architectural aspects of the developed system. We also provide brief information about the prototypes developed to test the system on a real ongoing geriatric study.

In this paper we introduce aspBEEF, a tool for generating explanations for the outcome of an arbitrary machine learning classifier. This is done using Grover’s et al. framework known as Balanced English Explanations of Forecasts (BEEF) that generates explanations in terms of in terms of finite intervals over the values of the input features. Since the problem of obtaining an optimal BEEF explanation has been proved to be NP-complete, BEEF existing implementation computes an approximation. In this work we use instead an encoding into the Answer Set Programming paradigm, specialized in solving NP problems, to guarantee that the computed solutions are optimal.