Toward a General Framework for Multimodal Big Data Analysis

Multimodal Analytics in Big Data architectures implies compounded configurations of the data processing tasks. Each modality in data requires specific analytics that triggers specific data processing tasks. Scalability can be reached at the cost of an attentive calibration of the resources shared by the different tasks searching for a trade-off with the multiple requirements they impose. We propose a methodology to address multimodal analytics within the same data processing approach to get a simplified architecture that can fully exploit the potential of the parallel processing of Big Data infrastructures. Multiple data sources are first integrated into a unified knowledge graph (KG). Different modalities of data are addressed by specifying ad hoc views on the KG and producing a rewriting of the graph containing merely the data to be processed. Graph traversal and rule extraction are this way boosted. Using graph embeddings methods, the different ad hoc views can be transformed into low-dimensional representation following the same data format. This way a single machine learning procedure can address the different modalities, simplifying the architecture of our system. The experiments we executed demonstrate that our approach reduces the cost of execution and improves the accuracy of analytics.

A methodology to engineering continuous monitoring of intrinsic capacity for elderly people

Continuous monitoring of the well-being state of elderly people is about to become an urgent need in the early future due to population aging. Aiming a unified notion of well-being, we find the Intrinsic Capacity concept in accordance with the SMART BEAR project goals. In this study, we mainly focus on the enabling infrastructure, mapping our models to interoperable repositories and to streaming/computing components that can foster monitoring. Our method is also innovative for explicitly combining personalized and risk levels in generating the Intrinsic Capacity score. Leveraging on synthetic data, we represent the outcome trajectories of some sample patients for 1-year continuous monitoring and discuss approaches to characterize them based on the exhibited tendency and evaluate the results from the predictability point of view providing by the entropy of time series concept. At the end, we discuss the possible data quality issues in health care studies using synthetic data.

The dynamical formation of ephemeral groups on networks and their effects on epidemics spreading

In network models of propagation processes, the individual, microscopic level perspective is the norm, with aggregations studied as possible outcomes. On the contrary, we adopted a mesoscale perspective with groups as the core element and in this sense we present a novel agent-group dynamic model of propagation in networks. In particular, we focus on ephemeral groups that dynamically form, create new links, and dissolve. The experiments simulated 160 model configurations and produced results describing cases of consecutive and non-consecutive dynamic grouping, bounded or unbounded in the number of repetitions. Results revealed the existence of complex dynamics and multiple behaviors. An efficiency metric is introduced to compare the different cases. A Null Model analysis disclosed a pattern in the difference between the group and random models, varying with the size of groups. Our findings indicate that a mesoscopic construct like the ephemeral group, based on assumptions about social behavior and absent any microscopic level change, could produce and describe complex propagation dynamics. A conclusion is that agent-group dynamic models may represent a powerful approach for modelers and a promising new direction for future research in models of coevolution between propagation and behavior in society.

The coevolution of contagion and behavior with increasing and decreasing awareness

Understanding the effects of individual awareness on epidemic phenomena is important to comprehend the coevolving system dynamic, to improve forecasting, and to better evaluate the outcome of possible interventions. In previous models of epidemics on social networks, individual awareness has often been approximated as a generic personal trait that depends on social reinforcement, and used to introduce variability in state transition probabilities. A novelty of this work is to assume that individual awareness is a function of several contributing factors pooled together, different by nature and dynamics, and to study it for different epidemic categories. This way, our model still has awareness as the core attribute that may change state transition probabilities. Another contribution is to study positive and negative variations of awareness, in a contagion-behavior model. Imitation is the key mechanism that we model for manipulating awareness, under different network settings and assumptions, in particular regarding the degree of intentionality that individuals may exhibit in spreading an epidemic. Three epidemic categories are considered-disease, addiction, and rumor-to discuss different imitation mechanisms and degree of intentionality. We assume a population with a heterogeneous distribution of awareness and different response mechanisms to information gathered from the network. With simulations, we show the interplay between population and awareness factors producing a distribution of state transition probabilities and analyze how different network and epidemic configurations modify transmission patterns.