The pervasiveness of mobile phones creates an unprecedented opportunity for analyzing human dynamics with the help of the data they generate. This enables a novel human-driven approach for service creation in a variety of domains (e.g., healthcare, transportation, etc.) Telecom operators own and manage billions of mobile network events (Call Detailed Records -CDRs) per day: interpreting such a big stream of data needs a deep understanding of the events' context through the available background knowledge. We introduce an ontological and stochastic model (HRBModel) to interpret mobile human behavior using merged mobile network data and the geo-referenced background knowledge (e.g., OpenStreetMap, etc.) The model characterizes locations with human activities that can happen (with a given likelihood) there. This allows us to predicatively compile sets of tasks that people are likely to engage in under certain contextual conditions or to characterize exceptional events detected from anomalies in the CDR. An experimental evaluation of the approach is presented.

The enormous amount of recently available mobile phone data is providing unprecedented direct measurements of human behavior. Early recognition and prediction of behavioral patterns are of great importance in many societal applications like urban planning, transportation optimization, and health-care. Understanding the relationships between human behaviors and location's context is an emerging interest for understanding human-environmental dynamics. Growing availability of Web 2.0, i.e. the increasing amount of websites with mainly user created content and social platforms opens up an opportunity to study such location's contexts. This paper investigates relationships existing between human behavior and location context, by analyzing log mobile phone data records. First an advanced approach to categorize areas in a city based on the presence and distribution of categories of human activity (e.g., eating, working, and shopping) found across the areas, is proposed. The proposed classification is then evaluated through its comparison with the patterns of temporal variation of mobile phone activity and applying machine learning techniques to predict a timeline type of communication activity in a given location based on the knowledge of the obtained category vs. land-use type of the locations areas. The proposed classification turns out to 1 arXiv:1510.02995v1 [cs.SI] 11 Oct 2015 be more consistent with the temporal variation of human communication activity, being a better predictor for those compared to the official land use classification.

Background Due to the advent of deep learning, the increasing number of studies in the biomedical domain has attracted much interest in feature extraction and classification tasks. In this research, we seek the best combination of feature set and hyperparameter setting of deep learning algorithms for relation classification. To this end, we incorporate an entity and relation extraction tool, PKDE4J to extract biomedical features (i.e., biomedical entities, relations) for the relation classification. We compared the chosen Convolutional Neural Networks (CNN) based classification model with the most widely used learning algorithms. Results Our CNN based classification model outperforms the most widely used supervised algorithms. We achieved a significant performance on binary classification with a weighted macro-average F1-score: 94.79% using pre-extracted relevant feature combinations. For multi-class classification, the weighted macro-average F1-score is estimated around 86.95%. Conclusions Our results suggest that our proposed CNN based model using the not only single feature as the raw text of the sentences of biomedical literature, but also coupling with multiple and highlighted features extracted from the biomedical sentences could improve the classification performance significantly. We offer hyperparameter tuning and optimization approaches for our proposed model to obtain optimal hyperparameters of the models with the best performance.