Northumbria University

About: Northumbria University is a education organization based out in Newcastle upon Tyne, United Kingdom. It is known for research contribution in the topics: Context (language use) & Population. The organization has 5624 authors who have published 17423 publications receiving 381949 citations. The organization is also known as: University of Northumbria at Newcastle.

Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot

Abstract: Automatic perception of human affective behaviour from facial expressions and recognition of intentions and social goals from dialogue contexts would greatly enhance natural human robot interaction. This research concentrates on intelligent neural network based facial emotion recognition and Latent Semantic Analysis based topic detection for a humanoid robot. The work has first of all incorporated Facial Action Coding System describing physical cues and anatomical knowledge of facial behaviour for the detection of neutral and six basic emotions from real-time posed facial expressions. Feedforward neural networks (NN) are used to respectively implement both upper and lower facial Action Units (AU) analysers to recognise six upper and 11 lower facial actions including Inner and Outer Brow Raiser, Lid Tightener, Lip Corner Puller, Upper Lip Raiser, Nose Wrinkler, Mouth Stretch etc. An artificial neural network based facial emotion recogniser is subsequently used to accept the derived 17 Action Units as inputs to decode neutral and six basic emotions from facial expressions. Moreover, in order to advise the robot to make appropriate responses based on the detected affective facial behaviours, Latent Semantic Analysis is used to focus on underlying semantic structures of the data and go beyond linguistic restrictions to identify topics embedded in the users’ conversations. The overall development is integrated with a modern humanoid robot platform under its Linux C++ SDKs. The work presented here shows great potential in developing personalised intelligent agents/robots with emotion and social intelligence.

A double-blind, placebo-controlled, multi-dose evaluation of the acute behavioural effects of guaraná in humans:

Abstract: The present study aimed to systematically assess acute, dose-related behavioural effects of an extract of guarana plant for the first time in humans. This double-blind, counterbalanced, placebo-controlled study (n=26) assessed the acute mood and cognitive effects throughout the day of four different doses (37.5 mg, 75 mg, 150 mg and 300 mg) of a standardised guarana extract (PC-102). Assessment included the Cognitive Drug Research computerized test battery and Bond-Lader mood scales. Guarana improved secondary memory performance and increased alert and content mood ratings. The two lower doses produced more positive cognitive effects than the higher doses. This research supports previous findings of cognitive improvements following 75 mg guarana and provides the first exploration of different dose effects of guarana in humans. The findings suggest that the effects cannot be attributed to caffeine alone.

"Watts in it for me?": design implications for implementing effective energy interventions in organisations

Abstract: The design of technological interventions to motivate behaviour-based reductions in end-user energy consumption has recently been identified as a priority for the HCI community. Previous interventions have produced promising results, but have typically focused on domestic energy consumption. By contrast, this paper focuses on the workplace context, which presents very different opportunities and challenges. For instance, financial consequences, which have proved successful as motivations in the domestic environment, are not present in the workplace in the context of employees. We describe the outcome of a sequence of workshops that focussed on understanding employee perceptions of energy use in the workplace, with the locus of activity on energy intervention design. Using a grounded theory analysis, we produced a framework of key themes detailing user perceptions and energy intervention design considerations. Our findings provide a framework of considerations for the design of successful workplace energy interventions.

Kernelized Multiview Projection for Robust Action Recognition

Abstract: Conventional action recognition algorithms adopt a single type of feature or a simple concatenation of multiple features. In this paper, we propose to better fuse and embed different feature representations for action recognition using a novel spectral coding algorithm called Kernelized Multiview Projection (KMP). Computing the kernel matrices from different features/views via time-sequential distance learning, KMP can encode different features with different weights to achieve a low-dimensional and semantically meaningful subspace where the distribution of each view is sufficiently smooth and discriminative. More crucially, KMP is linear for the reproducing kernel Hilbert space, which allows it to be competent for various practical applications. We demonstrate KMP's performance for action recognition on five popular action datasets and the results are consistently superior to state-of-the-art techniques.