Silvia Cascianelli

SmartSEAL: A ROS based home automation framework for heterogeneous devices interconnection in smart buildings

With this paper we present the SmartSEAL inter-connection system developed for the nationally founded SEAL project. SEAL is a research project aimed at developing Home Automation (HA) solutions for building energy management, user customization and improved safety of its inhabitants. One of the main problems of HA systems is the wide range of communication standards that commercial devices use. Usually this forces the designer to choose devices from a few brands, limiting the scope of the system and its capabilities. In this context, SmartSEAL is a framework that aims to integrate heterogeneous devices, such as sensors and actuators from different vendors, providing networking features, protocols and interfaces that are easy to implement and dynamically configurable. The core of our system is a Robotics middleware called Robot Operating System (ROS). We adapted the ROS features to the HA problem, designing the network and protocol architectures for this particular needs. These software infrastructure allows for complex HA functions that could be realized only levering the services provided by different devices. The system has been tested in our laboratory and installed in two real environments, Palazzo Fogazzaro in Schio and “Le Case” childhood school in Malo. Since one of the aim of the SEAL project is the personalization of the building environment according to the user needs, and the learning of their patterns of behaviour, in the final part of this work we also describe the ongoing design and experiments to provide a Machine Learning based re-identification module implemented with Convolutional Neural Networks (CNNs). The description of the adaptation module complements the description of the SmartSEAL system and helps in understanding how to develop complex HA services through it.

Dimensionality Reduction Strategies for CNN-Based Classification of Histopathological Images

Features from pre-trained Convolutional Neural Newtorks (CNN) have proved to be effective for many tasks such as object, scene and face recognition. Compared with traditional, hand-designed image descriptors, CNN-based features produce higher-dimensional feature vectors. In specific applications where the number of samples may be limited – as in the case of histopatological images – high dimensionality could potentially cause overfitting and redundancy in the information to be processed and stored. To overcome these potential problems feature reduction methods can be applied, at the cost of a moderate reduction in the discrimination accuracy. In this paper we investigate dimensionality reduction schemes for CNN-based features applied to computer-assisted classification of histopathological images. The purpose of this study is to find the best trade-off between accuracy and dimensionality. Specifically, we test two well-known techniques (i.e.: Principal Component Analysis and Gaussian Random Projection) and propose a novel reduction strategy based on the cross-correlation between the components of the feature vector. The results show that it is possible to reduce CNN-based features by a high ratio with a moderate decrease in accuracy with respect to the original values.

Hand-Designed Local Image Descriptors vs. Off-the-Shelf CNN-Based Features for Texture Classification: An Experimental Comparison

Convolutional Neural Networks have proved extremely successful in object classification applications; however, their suitability for texture analysis largely remains to be established. We investigate the use of pre-trained CNNs as texture descriptors by tapping the output of the last fully connected layer, an approach that has proved its effectiveness in other domains. Comparison with classical descriptors based on signal processing or statistics over a range of standard databases suggests that CNNs may be more effective where the intra-class variability is large. Conversely, classical approaches may be preferable where classes are well defined and homogeneous.

Robust visual semi-semantic loop closure detection by a covisibility graph and CNN features ☆

Abstract Visual Self-localization in unknown environments is a crucial capability for an autonomous robot. Real life scenarios often present critical challenges for autonomous vision-based localization, such as robustness to viewpoint and appearance changes. To address these issues, this paper proposes a novel strategy that models the visual scene by preserving its geometric and semantic structure and, at the same time, improves appearance invariance through a robust visual representation. Our method relies on high level visual landmarks consisting of appearance invariant descriptors that are extracted by a pre-trained Convolutional Neural Network (CNN) on the basis of image patches. In addition, during the exploration, the landmarks are organized by building an incremental covisibility graph that, at query time, is exploited to retrieve candidate matching locations improving the robustness in terms of viewpoint invariance. In this respect, through the covisibility graph, the algorithm finds, more effectively, location similarities by exploiting the structure of the scene that, in turn, allows the construction of virtual locations i.e., artificially augmented views from a real location that are useful to enhance the loop closure ability of the robot. The proposed approach has been deeply analysed and tested in different challenging scenarios taken from public datasets. The approach has also been compared with a state-of-the-art visual navigation algorithm.

Role of Artificial Intelligence Techniques (Automatic Classifiers) in Molecular Imaging Modalities in Neurodegenerative Diseases

Artificial Intelligence (AI) is a very active Computer Science research field aiming to develop systems that mimic human intelligence and is helpful in many human activities, including Medicine. In this review we presented some examples of the exploiting of AI techniques, in particular automatic classifiers such as Artificial Neural Network (ANN), Support Vector Machine (SVM), Classification Tree (ClT) and ensemble methods like Random Forest (RF), able to analyze findings obtained by positron emission tomography (PET) or single-photon emission tomography (SPECT) scans of patients with Neurodegenerative Diseases, in particular Alzheimers Disease. We also focused our attention on techniques applied in order to preprocess data and reduce their dimensionality via feature selection or projection in a more representative domain (Principal Component Analysis - PCA - or Partial Least Squares - PLS - are examples of such methods); this is a crucial step while dealing with medical data, since it is necessary to compress patient information and retain only the most useful in order to discriminate subjects into normal and pathological classes. Main literature papers on the application of these techniques to classify patients with neurodegenerative disease extracting data from molecular imaging modalities are reported, showing that the increasing development of computer aided diagnosis systems is very promising to contribute to the diagnostic process.

A robust semi-semantic approach for visual localization in urban environment

This paper provides a new contribution to the problem of vision-based place recognition introducing a novel appearance and viewpoint invariant approach that guarantees robustness with respect to perceptual aliasing and kidnapping. Most of the state-of-the-art strategies rely on low level visual features and ignore the semantical structure of the scene. Thus, even small changes in the appearance of the scene (e.g., illumination conditions) cause a significant performance drop. In contrast to previous work, we propose a new strategy to model the scene by preserving its geometrical and the semantical structure and, at the same time, achieving an improved appearance invariance through a robust visual representation. In particular, to manage the perceptual aliasing problem, we introduce a covisibility graph, that connects semantical entities of the scene preserving their geometrical relations. The method relies on high level patches consisting of dense and robust descriptors that are extracted by a Convolutional Neural Network (CNN). Through the graph structure, we are able to efficiently retrieve candidate locations and to synthesize virtual locations (i.e., artificial intermediate views between two keyframes) to improve the viewpoint invariance. The proposed approach has been compared with state-of-the-art approaches in different challenging scenarios taken from public datasets.

Full-GRU Natural Language Video Description for Service Robotics Applications

Enabling effective human–robot interaction is crucial for any service robotics application. In this context, a fundamental aspect is the development of a user-friendly human–robot interface, such as a natural language interface. In this letter, we investigate the robot side of the interface, in particular the ability to generate natural language descriptions for the scene it observes. We achieve this capability via a deep recurrent neural network architecture completely based on the gated recurrent unit paradigm. The robot is able to generate complete sentences describing the scene, dealing with the hierarchical nature of the temporal information contained in image sequences. The proposed approach has fewer parameters than previous state-of-the-art architectures, thus it is faster to train and smaller in memory occupancy. These benefits do not affect the prediction performance. In fact, we show that our method outperforms or is comparable to previous approaches in terms of quantitative metrics and qualitative evaluation when tested on benchmark publicly available datasets and on a new dataset we introduce in this letter.

Computing the Real Impact of Wind Turbine Power Curve Upgrades: A SCADA-Based Multivariate Linear Method and a Vortex Generator Test Case

Computing the real impact of wind turbine power curve upgrades: a SCADA-based multivariate linear method and a vortex generator test case Davide Astolfi 1,‡*, Francesco Castellani 1,‡, Mario Luca Fravolini1,‡, Silvia Cascianelli1,‡, Ludovico Terzi 2,‡ 1 University of Perugia Department of Engineering, Via G. Duranti 93 06125 Perugia (Italy); davide.astolfi@unipg.it; francesco.castellani@unipg.it; mario.fravolini@unipg.it; silvia.cascianelli@unipg.it 2 Renvico srl, Via San Gregorio 34, Milano 20124, Italy; ludovico.terzi@renvico.it * Correspondence: davide.astolfi@unipg.it; Tel.: +39 075 585 3709 ‡ These authors contributed equally to this work.

A Learning Strategy for the Autonomous Control of Type 1 Diabetes

This article proposes a learning strategy for the control of the blood glucose in type 1 diabetes based on continuous subcutaneous glucose measurement and subcutaneous insulin administration. The method relies on an Iterative Learning Control strategy that exploits the approximated repetitiveness of the daily feeding habits of a patient. The administration strategy for the insulin is based on a mixed feedback and feedforward law whose parameters are tuned through a learning process based on the day-by-day analysis of the glucose response to the infusion of exogenous insulin. The proposed scheme is fully autonomous in the sense that it does not require any a priori information on the insulin/glucose response of the patient, on the amount of ingested carbohydrates, and on the announcement of the mealtimes. A novel filtering strategy of the subcutaneous glucose signal is proposed to provide a robust detection of the meal occurrence despite the significant noise introduced by the subcutaneous glucose sensor. A specific module is proposed to detect and prevent possible hypoglycemia events. Considering a prototype diabetic virtual patient it was showed that, thanks to the learning mechanism, the scheme in a few days is able to bring and to maintain the blood glucose in the normoglycemia region and that the control performance can improve over time. Long-run simulation studies have also shown the robustness of the learning scheme in the presence of realistic uncertainties and interpatient variability.