Davide Bacciu

An experimental characterization of reservoir computing in ambient assisted living applications

In this paper, we present an introduction and critical experimental evaluation of a reservoir computing (RC) approach for ambient assisted living (AAL) applications. Such an empirical analysis jointly addresses the issues of efficiency, by analyzing different system configurations toward the embedding into computationally constrained wireless sensor devices, and of efficacy, by analyzing the predictive performance on real-world applications. First, the approach is assessed on a validation scheme where training, validation and test data are sampled in homogeneous ambient conditions, i.e., from the same set of rooms. Then, it is introduced an external test set involving a new setting, i.e., a novel ambient, which was not available in the first phase of model training and validation. The specific test-bed considered in the paper allows us to investigate the capability of the RC approach to discriminate among user movement trajectories from received signal strength indicator sensor signals. This capability can be exploited in various AAL applications targeted at learning user indoor habits, such as in the proposed indoor movement forecasting task. Such a joint analysis of the efficiency/efficacy trade-off provides novel insight in the concrete successful exploitation of RC for AAL tasks and for their distributed implementation into wireless sensor networks.

Robotic Ubiquitous Cognitive Ecology for Smart Homes

Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them both autonomous and adaptive, so as to reduce the amount of preparation, pre-programming and human supervision that they require in real world applications. The project RUBICON develops learning solutions which yield cheaper, adaptive and efficient coordination of robotic ecologies. The approach we pursue builds upon a unique combination of methods from cognitive robotics, machine learning, planning and agent-based control, and wireless sensor networks. This paper illustrates the innovations advanced by RUBICON in each of these fronts before describing how the resulting techniques have been integrated and applied to a proof of concept smart home scenario. The resulting system is able to provide useful services and pro-actively assist the users in their activities. RUBICON learns through an incremental and progressive approach driven by the feedback received from its own activities and from the user, while also self-organizing the manner in which it uses available sensors, actuators and other functional components in the process. This paper summarises some of the lessons learned by adopting such an approach and outlines promising directions for future work.

Compositional Generative Mapping for Tree-Structured Data—Part I: Bottom-Up Probabilistic Modeling of Trees

We introduce a novel compositional (recursive) probabilistic model for trees that defines an approximated bottom-up generative process from the leaves to the root of a tree. The proposed model defines contextual state transitions from the joint configuration of the children to the parent nodes. We argue that the bottom-up context postulates different probabilistic assumptions with respect to a top-down approach, leading to different representational capabilities. We discuss classes of applications that are best suited to a bottom-up approach. In particular, the bottom-up context is shown to better correlate and model the co-occurrence of substructures among the child subtrees of internal nodes. A mixed memory approximation is introduced to factorize the joint children-to-parent state transition matrix as a mixture of pairwise transitions. The proposed approach is the first practical bottom-up generative model for tree-structured data that maintains the same computational class of its top-down counterpart. Comparative experimental analyses exploiting synthetic and real-world datasets show that the proposed model can deal with deep structures better than a top-down generative model. The model is also shown to better capture structural information from real-world data comprising trees with a large out-degree. The proposed bottom-up model can be used as a fundamental building block for the development of other new powerful models.

Competitive Repetition Suppression (CoRe) Clustering: A Biologically Inspired Learning Model With Application to Robust Clustering

Determining a compact neural coding for a set of input stimuli is an issue that encompasses several biological memory mechanisms as well as various artificial neural network models. In particular, establishing the optimal network structure is still an open problem when dealing with unsupervised learning models. In this paper, we introduce a novel learning algorithm, named competitive repetition-suppression (CoRe) learning, inspired by a cortical memory mechanism called repetition suppression (RS). We show how such a mechanism is used, at various levels of the cerebral cortex, to generate compact neural representations of the visual stimuli. From the general CoRe learning model, we derive a clustering algorithm, named CoRe clustering, that can automatically estimate the unknown cluster number from the data without using a priori information concerning the input distribution. We illustrate how CoRe clustering, besides its biological plausibility, posses strong theoretical properties in terms of robustness to noise and outliers, and we provide an error function describing CoRe learning dynamics. Such a description is used to analyze CoRe relationships with the state-of-the art clustering models and to highlight CoRe similitude with rival penalized competitive learning (RPCL), showing how CoRe extends such a model by strengthening the rival penalization estimation by means of loss functions from robust statistics.

Learning context-aware mobile robot navigation in home environments

We present an approach to make planning adaptive in order to enable context-aware mobile robot navigation. We integrate a model-based planner with a distributed learning system based on reservoir computing, to yield personalized planning and resource allocations that account for user preferences and environmental changes. We demonstrate our approach in a real robot ecology, and show that the learning system can effectively exploit historical data about navigation performance to modify the models in the planner, without any prior information oncerning the phenomenon being modeled. The plans produced by the adapted CL fail more rarely than the ones generated by a non-adaptive planner. The distributed learning system handles the new learning task autonomously, and is able to automatically identify the sensorial information most relevant for the task, thus reducing the communication and computational overhead of the predictive task.

A fuzzy approach for negotiating quality of services

A central point when integrating services concerns to the description, agreement and enforcement of the quality aspect of service interaction, usually known as Service Level Agreement (SLA). This paper presents a framework for SLA negotiation based on fuzzy sets.We propose (i) a request language for clients to describe quality preferences, (ii) a publication language for providers to define the qualities of their offered services, and (iii) a decision procedure for granting any client request with a SLA contract fitting the requestor requirements. We start with a restricted framework in which the different qualities of a service are handled independently (as being orthogonal) and then we propose an extension that allows clients and providers to express dependencies among different qualities.

An Experimental Evaluation of Reservoir Computation for Ambient Assisted Living

In this paper we investigate the introduction of Reservoir Computing (RC) neural network models in the context of AAL (Ambient Assisted Living) and self-learning robot ecologies, with a focus on the computational constraints related to the implementation over a network of sensors. Specifically, we experimentally study the relationship between architectural parameters influencing the computational cost of the models and the performance on a task of user movements prediction from sensors signal streams. The RC shows favorable scaling properties results for the analyzed AAL task.

A General Purpose Distributed Learning Model for Robotic Ecologies

Abstract The design of a learning system for robotic ecologies need to account for some key aspects of the ecology model such as distributivity, heterogeneity of the computational, sensory and actuator capabilities, as well as self-configurability. The paper proposes general guiding principles for learning systems’ design that ensue from key ecology properties, and presents a distributed learning system for the Rubicon ecology that draws inspiration from such guidelines. The proposed learning system provides the Rubicon ecology with a set of generalpurpose learning services which can be used to learn generic computational tasks that involve predicting information of interest based on dynamic sensorial input streams.

A cognitive robotic ecology approach to self-configuring and evolving AAL systems

Robotic ecologies are systems made out of several robotic devices, including mobile robots, wireless sensors and effectors embedded in everyday environments, where they cooperate to achieve complex tasks. This paper demonstrates how endowing robotic ecologies with information processing algorithms such as perception, learning, planning, and novelty detection can make these systems able to deliver modular, flexible, manageable and dependable Ambient Assisted Living (AAL) solutions. Specifically, we show how the integrated and self-organising cognitive solutions implemented within the EU project RUBICON (Robotic UBIquitous Cognitive Network) can reduce the need of costly pre-programming and maintenance of robotic ecologies. We illustrate how these solutions can be harnessed to (i) deliver a range of assistive services by coordinating the sensing & acting capabilities of heterogeneous devices, (ii) adapt and tune the overall behaviour of the ecology to the preferences and behaviour of its inhabitants, and also (iii) deal with novel events, due to the occurrence of new users activities and changing users habits.

Patient stratification with competing risks by multivariate Fisher distance

Early characterization of patients with respect to their predicted response to treatment is a fundamental step towards the delivery of effective, personalized care. Starting from the results of a time-to-event model with competing risks using the framework of partial logistic artificial neural networks with automatic relevance determination (PLANNCR-ARD), we discuss an effective semi-supervised approach to patient stratification with application to Acute Myeloid Leukaemia (AML) data (n = 509) acquired prospectively by the GIMEMA consortium. Multiple prognostic indices provided by the survival model are exploited to build a metric based on the Fisher information matrix. Cluster number estimation is then performed in the Fisher-induced affine space, yielding to the discovery of a stratification of the patients into groups characterized by significantly different mortality risks following induction therapy in AML. The proposed model is shown to be able to cluster the input data, while promoting specificity of both target outcomes, namely Complete Remission (CR) and Induction Death (ID). This generic clustering methodology generates an affine transformation of the data space that is coherent with the prognostic information predicted by the PLANNCR-ARD model.