In this position paper we present the FP7 ERC starting grant project iHEARu (Intelligent systems’ Holistic Evolving Analysis of Real-life Universal speaker characteristics). This project addresses several fundamental shortcomings in state of the art methods for computational paralinguistics, by introducing holistic analysis, evolving learning of features and models, and collection of real-life,...

Holistic processing has been identified as an expertise marker of face and object recognition. In contrast, the expertise marker of recognizing Chinese characters is reduced holistic processing (Hsiao & Cottrell, 2009), which is driven by Chinese writing experiences rather than reading ability (Tso, Au, & Hsiao, 2011). Here we investigate the developmental trend of holistic processing in Chines...

Background & aim: Perinatal mental health problems have been demonstrated to impact upon maternal, and fetal/child outcomes. Despite the global evidence and a policy-driven responsibility for identification of these problems, research demonstrates that student midwives/midwives lack knowledge and confidence to assess, identify, and manage them. A similar context is evident for learning disabili...

Many arguments have been proposed in favor of and against the idea of protolanguage as a set of holistic utterances that were later segmented into words. This paper presents data from a human iterated learning experiment which corroborates arguments in favor of holistic protolanguage and forms a counterexample to some of the arguments that were proposed against it. This experiment involves iter...

The purpose of this family-focused, grounded-theory study was to develop a substantive theory that explains how individual family members heal in the aftermath of youth suicide. Individual healing following youth suicide is conceptualized as a process of "journeying toward wholeness." In response to youth suicide, survivors characteristically tap into their innate strengths and coping capabilit...

Adversarial robustness studies the worst-case performance of a machine learning model to ensure safety and reliability. With proliferation deep-learning-based technology, potential risks associated with development deployment can be amplified become dreadful vulnerabilities. This paper provides comprehensive overview research topics foundational principles methods for adversarial deep models, i...

The hidden Markov model (HMM)-based approach for eye movement analysis is able to reflect individual differences in both spatial and temporal aspects of eye movements. Here we used this approach to understand the relationship between eye movements during face learning and recognition, and its association with recognition performance. We discovered holistic (i.e., mainly looking at the face cent...

The author independently developed the Holistic Approach to Learning and Teaching Interaction over nine years of reflective teaching practice in the field of information systems and computing across three higher educational institutions. It has been taught on undergraduate and post-graduate degrees and doctoral programmes. Though its roots are in the computing field, the holistic approach can b...