Antonietta M. Esposito

Unsupervised Neural Analysis of Very-Long-Period Events at Stromboli Volcano Using the Self-Organizing Maps

We have implemented a method based on an unsupervised neural network to cluster the waveforms of very-long-period (VLP) events associated with explosive activity at the Stromboli volcano (southern Italy). Stromboli has several active vents in the summit area producing together more than 200 explosions/day. We applied this method to investigate the relationship between each vent and its associated VLP explosive waveform. We selected 147 VLP events recorded between November and December 2005, when digital infrared camera recordings were available. From a visual inspection of the infrared camera images, we classified the VLPs on the basis of which vent produced each explosion. We then applied the self-organizing map (SOM), an unsupervised neural technique widely applied in data exploratory analysis, to cluster the VLPs on the basis of their waveform similarity. Our analysis demonstrates that the most recurrent VLP waveforms are usually generated by the same vent. Some exceptions occurred, however, in which different waveforms are associated with the same vent, as well as different vents generating similar waveforms. This suggests that the geometry of the upper conduit-vent system plays a role in shaping the recurring VLP events, whereas occasional modest changes in the source process dynamics produce the observed exceptions.

Automatic Discrimination among Landslide, Explosion-Quake, and Microtremor Seismic Signals at Stromboli Volcano Using Neural Networks

In this article we report on the implementation of an automatic system for discriminating landslide seismic signals on Stromboli island (southern Italy). This is a critical point for monitoring the evolution of this volcanic island, where at the end of 2002 a violent tsunami occurred, triggered by a big landslide. We have devised a supervised neural system to discriminate among landslide, explosion-quake, and volcanic microtremor signals. We first preprocess the data to obtain a compact representation of the seismic records. Both spectral features and amplitude-versus-time information have been extracted from the data to characterize the different types of events. As a second step, we have set up a supervised classification system, trained using a subset of data (the training set) and tested on another data set (the test set) not used during the training stage. The automatic system that we have realized is able to correctly classify 99% of the events in the test set for both explosion-quake/ landslide and explosion-quake/microtremor couples of classes, 96% for landslide/ microtremor discrimination, and 97% for three-class discrimination (landslides/ explosion-quakes/microtremor). Finally, to determine the intrinsic structure of the data and to test the efficiency of our parametrization strategy, we have analyzed the preprocessed data using an unsupervised neural method. We apply this method to the entire dataset composed of landslide, microtremor, and explosion-quake signals. The unsupervised method is able to distinguish three clusters corresponding to the three classes of signals classified by the analysts, demonstrating that the parametrization technique characterizes the different classes of data appropriately.

Needs and challenges in human computer interaction for processing social emotional information

Emotional expressions.Multimodal communication.Needs and challenges in emotionally and believable ICT interfaces. Demand for and delivery so far of sophisticated computational instruments able to recognize, process and store relevant interactional signals, as well as interact with people, displaying suitable autonomous reactions appropriately sensitive to environmental changes, have produced great expectations in Information Communication Technology (ICT). Knowing what an appropriate continuation of an interaction is depends on detecting the addressers register and a machine interface unable to assess differences will have difficulty managing interactions. Progress toward understanding and modeling such facets is crucial for implementing behaving Human Computer Interaction (HCI) systems that will simplify user access to future, profitable, remote and nearby social services. This paper raises new research questions via new means for socio?behavioral and emotional investigations, and suggests the gathering of new experimental data and theories across a spectrum of research concepts, in order to develop new psychological and computational approaches crucial for implementing believable and trustable HCI systems which exploit synthetic agents, robots, and sophisticated humanlike interfaces.

On the recognition of emotional vocal expressions: motivations for a holistic approach

Human beings seem to be able to recognize emotions from speech very well and information communication technology aims to implement machines and agents that can do the same. However, to be able to automatically recognize affective states from speech signals, it is necessary to solve two main technological problems. The former concerns the identification of effective and efficient processing algorithms capable of capturing emotional acoustic features from speech sentences. The latter focuses on finding computational models able to classify, with an approximation as good as human listeners, a given set of emotional states. This paper will survey these topics and provide some insights for a holistic approach to the automatic analysis, recognition and synthesis of affective states.

Nonlinear exploratory data analysis applied to seismic signals

This paper compares three unsupervised projection methods: Principal Component Analysis (PCA), which is linear, Self-Organizing Map (SOM) and Curvilinear Component Analysis (CCA), which are both nonlinear. Performance comparison of the three methods is made on a set of seismic data recorded on Stromboli that includes three classes of signals: explosion-quakes, landslides, and microtremors. The unsupervised analysis of the signals is able to discover the nature of the seismic events. Our analysis shows that the SOM algorithm discriminates better than CCA and PCA on the data under examination.

Cognitive Behavioural Systems : COST 2102 International Training School, Dresden, Germany, February 21-26, 2011, Revised Selected Papers

This book constitutes refereed proceedings of the COST 2102 International Training School on Cognitive Behavioural Systems held in Dresden, Germany, in February 2011. The 39 revised full papers presented were carefully reviewed and selected from various submissions. The volume presents new and original research results in the field of human-machine interaction inspired by cognitive behavioural human-human interaction features. The themes covered are on cognitive and computational social information processing, emotional and social believable Human-Computer Interaction (HCI) systems, behavioural and contextual analysis of interaction, embodiment, perception, linguistics, semantics and sentiment analysis in dialogues and interactions, algorithmic and computational issues for the automatic recognition and synthesis of emotional states

Recent Advances in Nonlinear Speech Processing

This book presents recent advances in nonlinear speech processing beyond nonlinear techniques. It shows that it exploits heuristic and psychological models of human interaction in order to succeed in the implementations of socially believable VUIs and applications for human health and psychological support. The book takes into account the multifunctional role of speech and what is outside of the box (see Bjrn Schullers foreword). To this aim, the book is organized in 6 sections, each collecting a small number of short chapters reporting advances inside and outside themes related to nonlinear speech research. The themes emphasize theoretical and practical issues for modelling socially believable speech interfaces, ranging from efforts to capture the nature of sound changes in linguistic contexts and the timing nature of speech; labors to identify and detect speech features that help in the diagnosis of psychological and neuronal disease, attempts to improve the effectiveness and performance of Voice User Interfaces, new front-end algorithms for the coding/decoding of effective and computationally efficient acoustic and linguistic speech representations, as well as investigations capturing the social nature of speech in signaling personality traits, emotions and improving human machine interactions.

On the significance of speech pauses in depressive disorders: Results on read and spontaneous narratives

This paper investigates whether and how depressive disorders affect speech and in particular timing strategies for speech pauses (empty and filled pauses, as well as, phoneme lengthening). The investigation is made exploiting read and spontaneous narratives . The collected data are from 24 subjects, divided into two groups (depressed and control) asked to read a tale, as well as, spontaneously report on their daily activities. Ten different frequency and duration measures for pauses and clauses are proposed and have been collected using the PRAAT software on the speech recordings produced by the participants. A T-Student test for independent samples was applied on the collected frequency and duration measures in order to ascertain whether significant differences between healthy and depressed speech measures are observed. In the “spontaneous narrative” condition, depressed patients exhibited significant differences in: the average duration of their empty pauses, the average frequency, and the average duration of their clauses. In the read narratives, only the average pause’s frequency of the clauses was significantly lower in the depressed subjects with respect to the healthy ones. The results suggest that depressive disorders affect speech quality and speech production through pause and clause durations, as well as, clause quantities. In particular, the significant differences in clause quantities (observed both in the read and spontaneous narratives), suggest a strong general effect of depressive symptoms on cognitive and psychomotor functions. Depressive symptoms produce changes in the planned timing of pauses, even when reading, modifying the timing of pausing strategies.

Seismological Insights on the Shallow Magma System

We present an overview of the volcanic seismicity recorded at Stromboli from January to September 2003. The data set starts a few weeks after the onset of the eruption and covers most of the effusive phase and the subsequent recovery of the explosive activity. The most important variations occurred between May and July coinciding with the waning of the lava flow and the reappearance of Strombolian activity at the summit craters. All the parameters indicate that the shallow magmatic system has not undergone permanent changes during this period. The only significant variation related to the shallow conduit is the increase in volcanic tremor amplitude and the change in the spectral content of long-period events during the transition between effusive and explosive activity. A slight increase in the very long period (VLP) events source elevation seems to mark the rise of the magma at the end of the effusive phase. The variations in the VLP events occurrence rate are more likely to be attributed to changes in the gas flow rate and the bubble coalescence mechanism, therefore, to a deeper portion of the magmatic system. The 5 April paroxysm is associated only with a small increase of the activity in the following days.

Models for identifying structures in the data: a performance comparison

This paper reports on the unsupervised analysis of seismic signals recorded in Italy, respectively on the Vesuvius volcano, located in Naples, and on the Stromboli volcano, located North of Eastern Sicily. The Vesuvius dataset is composed of earthquakes and false events like thunders, man-made quarry and undersea explosions. The Stromboli dataset consists of explosion-quakes, landslides and volcanic microtremor signals. The aim of this paper is to apply on these datasets three projection methods, the linear Principal Component Analysis (PCA), the Self-Organizing Map (SOM), and the Curvilinear Component Analysis (CCA), in order to compare their performance. Since these algorithms are well known to be able to exploit structures and organize data providing a clear framework for understanding and interpreting their relationships, this work examines the category of structural information that they can provide on our specific sets. Moreover, the paper suggests a breakthrough in the application area of the SOM, used here for clustering different seismic signals. The results show that, among the three above techniques, SOM better visualizes the complex set of high-dimensional data discovering their intrinsic structure and eventually appropriately clustering the different signal typologies under examination, discriminating the explosion-quakes from the landslides and microtremor recorded at the Stromboli volcano, and the earthquakes from natural (thunders) and artificial (quarry blasts and undersea explosions) events recorded at the Vesuvius volcano.