KEDRI - the Knowledge Engineering and Discovery Research Institute
Permanent link for this collection
KEDRI - the Knowledge Engineering and Discovery Research Institute of Auckland University of Technology was established in June 2002 and since then has been developing novel information processing methods, technologies and their applications to enhance discoveries across different areas of science and engineering. The methods are mainly based on principles from Nature, such as brain information processing, evolution, genetics, quantum physics.
Now showing 1 - 5 of 57
- ItemInvestigation of Social and Cognitive Predictors in Non-transition Ultra-high-risk' Individuals for Psychosis Using Spiking Neural Networks(Springer Science and Business Media LLC, 2023-02-15) Doborjeh, Zohreh; Doborjeh, Maryam; Sumich, Alexander; Singh, Balkaran; Merkin, Alexander; Budhraja, Sugam; Goh, Wilson; Lai, Edmund M-K; Williams, Margaret; Tan, Samuel; Lee, Jimmy; Kasabov, NikolaFinding predictors of social and cognitive impairment in non-transition Ultra-High-Risk individuals (UHR) is critical in prognosis and planning of potential personalised intervention strategies. Social and cognitive functioning observed in youth at UHR for psychosis may be protective against transition to clinically relevant illness. The current study used a computational method known as Spiking Neural Network (SNN) to identify the cognitive and social predictors of transitioning outcome. Participants (90 UHR, 81 Healthy Control (HC)) completed batteries of neuropsychological tests in the domains of verbal memory, working memory, processing speed, attention, executive function along with social skills-based performance at baseline and 4 × 6-month follow-up intervals. The UHR status was recorded as Remitters, Converters or Maintained. SNN were used to model interactions between variables across groups over time and classify UHR status. The performance of SNN was examined relative to other machine learning methods. Higher interaction between social and cognitive variables was seen for the Maintained, than Remitter subgroup. Findings identified the most important cognitive and social variables (particularly verbal memory, processing speed, attention, affect and interpersonal social functioning) that showed discriminative patterns in the SNN models of HC vs UHR subgroups, with accuracies up to 80%; outperforming other machine learning models (56-64% based on 18 months data). This finding is indicative of a promising direction for early detection of social and cognitive impairment in UHR individuals that may not anticipate transition to psychosis and implicate early initiated interventions to stem the impact of clinical symptoms of psychosis.
- ItemMachine Learning Methods for the Study of Cybersickness: A Systematic Review(Springer, 2022-10-09)This systematic review offers a world-first critical analysis of machine learning methods and systems, along with future directions for the study of cybersickness induced by virtual reality (VR). VR is becoming increasingly popular and is an important part of current advances in human training, therapies, entertainment, and access to the metaverse. Usage of this technology is limited by cybersickness, a common debilitating condition experienced upon VR immersion. Cybersickness is accompanied by a mix of symptoms including nausea, dizziness, fatigue and oculomotor disturbances. Machine learning can be used to identify cybersickness and is a step towards overcoming these physiological limitations. Practical implementation of this is possible with optimised data collection from wearable devices and appropriate algorithms that incorporate advanced machine learning approaches. The present systematic review focuses on 26 selected studies. These concern machine learning of biometric and neuro-physiological signals obtained from wearable devices for the automatic identification of cybersickness. The methods, data processing and machine learning architecture, as well as suggestions for future exploration on detection and prediction of cybersickness are explored. A wide range of immersion environments, participant activity, features and machine learning architectures were identified. Although models for cybersickness detection have been developed, literature still lacks a model for the prediction of first-instance events. Future research is pointed towards goal-oriented data selection and labelling, as well as the use of brain-inspired spiking neural network models to achieve better accuracy and understanding of complex spatio-temporal brain processes related to cybersickness.
- ItemThe Role of Event Related Potentials in Pre-comprehension Processing of Consumers to Marketing Logos(Guilan University of Medical Sciences, and co-published by Negah Institute for Scientific Communication, 2019-01-01) Nazari, MA; Salehi Fadardi, J; Gholami Doborjeh, Z; Amanzadeh Oghaz, T; Saeedi, MT; Yazdi, SAABackground: In human behavior study, by peering directly into the brain and assessing distinct patterns, evoked neurons and neuron spike can be more understandable by taking advantages of accurate brain analysis. Objectives: We investigated the role of Event Related Potentials (ERPs) in pre-comprehension processing of consumers to marketing logos. Materials and Methods: In the framework of an experimental design, twenty-six right-handed volunteers (13 men, 13 women) participated in 2013 in the University of Tabriz. An individual task with a presentation of familiar vs. unfamiliar logos was designed. Stimuli were displayed on a monitor controlled by a PC using the Mitsar® stimulus presentation system PsyTask. Statistical analyses of ERPs data were analyzed by repeated measures ANOVA. Results: Our results showed, when subjects were dealing with familiar logos, higher peak amplitude for the N1 component in right hemisphere of the brain can be observed. These variations on averages of early components of ERPs in occipital lobe can be referred to the pre-perceptual brain activities. Conclusion: Investigating early components of ERP can be utilized further as an effective factor in prediction of the consumers ‘preference particularly in neuromarketing field.
- ItemClassification and segmentation of fMRI Spatio-temporal Brain Data with a NeuCube Evolving Spiking Neural Network Model(IEEE, 2014) Doborjeh, M; Capecci, E; Kasabov, NThe proposed feasibility analysis introduces a new methodology for modelling and understanding functional Magnetic Resonance Image (fMRI) data recorded during human cognitive activity. This constitutes a type of Spatio-Temporal Brain Data (STBD) measured according to neurons spatial location inside the brain and their signals oscillating over the mental activity period ; thus, it is challenging to analyse and model dynamically. This paper addresses the problem by means of a novel Spiking Neural Networks (SNN) architecture, called NeuCube . After the NeuCube is trained with the fMRI samples, the `hidden' spatio- temporal relationship between data is learnt. Different cognitive states of the brain are activated while a subject is reading different sentences in terms of their polarity (affirmative and negative sentences). These are visualised via the SNN cube (SNNc) and then recognized through its classifier. The excellent classification accuracy of 90% proves the NeuCube potential in capturing the fMRI data information and classifying it correctly. The significant improvement in accuracy is demonstrated as compared with some already published results  on the same data sets and traditional machine learning methods. Future works is based on the proposed NeuCube model are also discussed in this paper.
- ItemDynamic 3D Clustering of Spatio-temporal Brain Data in the NeuCube Spiking Neural Network Architecture on a Case Study of fMRI and EEG Data(Springer, 2015-02-19) Gholami, M; Kasabov, NThe paper presents a novel clustering method for dynamic Spatio-Temporal Brain Data (STBD) on the case study of functional Magnetic Resonance Image (fMRI). The method is based on NeuCube spiking neural network (SNN) architecture, where the spatio-temporal relationships between STBD streams are learned and simultaneously the clusters are created. The clusters are represented as groups of spiking neurons inside the NeuCube’s spiking neural network cube (SNNc). The centroids of the clusters are predefined by spatial location of the brain data sources used as input variables. We illustrate the proposed clustering method on an fMRI case study STBD recorded during a cognitive task. A comparative analysis of the clusters across different mental activities can reveal new findings about the brain processes under study.