Discriminative Power of Handwriting and Drawing Features in Depression.

This study contributes knowledge on the detection of depression through handwriting/drawing features, to identify quantitative and noninvasive indicators of the disorder for implementing algorithms for its automatic detection. For this purpose, an original online approach was adopted to provide a dynamic evaluation of handwriting/drawing performance of healthy participants with no history of any psychiatric disorders ([Formula: see text]), and patients with a clinical diagnosis of depression ([Formula: see text]). Both groups were asked to complete seven tasks requiring either the writing or drawing on a paper while five handwriting/drawing features' categories (i.e. pressure on the paper, time, ductus, space among characters, and pen inclination) were recorded by using a digitalized tablet. The collected records were statistically analyzed. Results showed that, except for pressure, all the considered features, successfully discriminate between depressed and nondepressed subjects. In addition, it was observed that depression affects different writing/drawing functionalities. These findings suggest the adoption of writing/drawing tasks in the clinical practice as tools to support the current depression detection methods. This would have important repercussions on reducing the diagnostic times and treatment formulation.

The School Attachment Monitor-A novel computational tool for assessment of attachment in middle childhood.

BACKGROUND: Attachment research has been limited by the lack of quick and easy measures. We report development and validation of the School Attachment Monitor (SAM), a novel measure for largescale assessment of attachment in children aged 5-9, in the general population. SAM offers automatic presentation, on computer, of story-stems based on the Manchester Child Attachment Story Task (MCAST), without the need for trained administrators. SAM is delivered by novel software which interacts with child participants, starting with warm-up activities to familiarise them with the task. Children's story completion is video recorded and augmented by 'smart dolls' that the child can hold and manipulate, with movement sensors for data collection. The design of SAM was informed by children of users' age range to establish their task understanding and incorporate their innovative ideas for improving SAM software. METHODS: 130 5-9 year old children were recruited from mainstream primary schools. In Phase 1, sixty-one children completed both SAM and MCAST. Inter-rater reliability and rating concordance was compared between SAM and MCAST. In Phase 2, a further 44 children completed SAM complete and, including those children completing SAM in Phase 1 (total n = 105), a machine learning algorithm was developed using a "majority vote" procedure where, for each child, 500 non-overlapping video frames contribute to the decision. RESULTS: Using manual rating, SAM-MCAST concordance was excellent (89% secure versus insecure; 97% organised versus disorganised; 86% four-way). Comparison of human ratings of SAM versus the machine learning algorithm showed over 80% concordance. CONCLUSIONS: We have developed a new tool for measuring attachment at the population level, which has good reliability compared to a validated attachment measure and has the potential for automatic rating-opening the door to measurement of attachment in large populations.

Infinite Feature Selection: A Graph-based Feature Filtering Approach.

We propose a filtering feature selection framework that considers subsets of features as paths in a graph, where a node is a feature and an edge indicates pairwise (customizable) relations among features, dealing with relevance and redundancy principles. By two different interpretations (exploiting properties of power series of matrices and relying on Markov chains fundamentals) we can evaluate the values of paths (i.e., feature subsets) of arbitrary lengths, eventually go to infinite, from which we dub our framework Infinite Feature Selection (Inf-FS). Going to infinite allows to constrain the computational complexity of the selection process, and to rank the features in an elegant way, that is, considering the value of any path (subset) containing a particular feature. We also propose a simple unsupervised strategy to cut the ranking, so providing the subset of features to keep. In the experiments, we analyze diverse settings with heterogeneous features, for a total of 11 benchmarks, comparing against 18 widely-known comparative approaches. The results show that Inf-FS behaves better in almost any situation, that is, when the number of features to keep are fixed a priori, or when the decision of the subset cardinality is part of the process.

Automatic Recognition of Personality Profiles Using EEG Functional Connectivity During Emotional Processing.

Personality is the characteristic set of an individual's behavioral and emotional patterns that evolve from biological and environmental factors. The recognition of personality profiles is crucial in making human-computer interaction (HCI) applications realistic, more focused, and user friendly. The ability to recognize personality using neuroscientific data underpins the neurobiological basis of personality. This paper aims to automatically recognize personality, combining scalp electroencephalogram (EEG) and machine learning techniques. As the resting state EEG has not so far been proven efficient for predicting personality, we used EEG recordings elicited during emotion processing. This study was based on data from the AMIGOS dataset reflecting the response of 37 healthy participants. Brain networks and graph theoretical parameters were extracted from cleaned EEG signals, while each trait score was dichotomized into low- and high-level using the k-means algorithm. A feature selection algorithm was used afterwards to reduce the feature-set size to the best 10 features to describe each trait separately. Support vector machines (SVM) were finally employed to classify each instance. Our method achieved a classification accuracy of 83.8% for extraversion, 86.5% for agreeableness, 83.8% for conscientiousness, 83.8% for neuroticism, and 73% for openness.

Social signals: from theory to applications.

The Special Issue Editorial introduces the research milieu in which Social Signal Processing originates, by merging computer scientists and social scientists and giving rise to this field in parallel with Human-Computer Interaction, Affective Computing, and Embodied Conversational Agents, all similarly characterized by high interdisciplinarity, stress on multimodality of communication, and the continuous loop from theory to simulation and application. Some frameworks of the cognitive and social processes underlying social signals are identified as reference points (Theory of Mind and Intersubjectivity, mirror neurons, and the ontogenesis and phylogenesis of communication), while three dichotomies (automatic vs. controlled, individualistic vs. intersubjective, and meaning vs. influence) are singled out as leads to navigate within the theoretical and applicative studies presented in the Special Issue.

Conversation analysis at work: detection of conflict in competitive discussions through semi-automatic turn-organization analysis.

This study proposes a semi-automatic approach aimed at detecting conflict in conversations. The approach is based on statistical techniques capable of identifying turn-organization regularities associated with conflict. The only manual step of the process is the segmentation of the conversations into turns (time intervals during which only one person talks) and overlapping speech segments (time intervals during which several persons talk at the same time). The rest of the process takes place automatically and the results show that conflictual exchanges can be detected with Precision and Recall around 70% (the experiments have been performed over 6 h of political debates). The approach brings two main benefits: the first is the possibility of analyzing potentially large amounts of conversational data with a limited effort, the second is that the model parameters provide indications on what turn-regularities are most likely to account for the presence of conflict.

Noisy text categorization.

This work presents categorization experiments performed over noisy texts. By noisy, we mean any text obtained through an extraction process (affected by errors) from media other than digital texts (e.g., transcriptions of speech recordings extracted with a recognition system). The performance of a categorization system over the clean and noisy (Word Error Rate between approximately 10 and approximately 50 percent) versions of the same documents is compared. The noisy texts are obtained through handwriting recognition and simulation of optical character recognition. The results show that the performance loss is acceptable for Recall values up to 60-70 percent depending on the noise sources. New measures of the extraction process performance, allowing a better explanation of the categorization results, are proposed.

Offline recognition of unconstrained handwritten texts using HMMs and statistical language models.

This paper presents a system for the offline recognition of large vocabulary unconstrained handwritten texts. The only assumption made about the data is that it is written in English. This allows the application of Statistical Language Models in order to improve the performance of our system. Several experiments have been performed using both single and multiple writer data. Lexica of variable size (from 10,000 to 50,000 words) have been used. The use of language models is shown to improve the accuracy of the system (when the lexicon contains 50,000 words, the error rate is reduced by approximately 50 percent for single writer data and by approximately 25 percent for multiple writer data). Our approach is described in detail and compared with other methods presented in the literature to deal with the same problem. An experimental setup to correctly deal with unconstrained text recognition is proposed.