Category: blog

Posted on

Horia Maior – Paper

Exploring the Impact of Verbal-Imagery Cognitive Style on Web Search Behaviour and Mental Workload

CHIIR ’24, March 10–14, 2024, Sheffield, United Kingdom

Cognitive style has been shown to influence users’ interaction with search interfaces. However, as a fundamental dimension of cognitive styles, the relationship between the Verbal-Imagery (VI) cognitive style dimension and search behaviour has not been studied thoroughly, and it is not clear whether VI cognitive style can be used to inform search user interface design. We present a study (N=29), investigating how search behaviour and mental workload (MWL) changes relate to VI cognitive styles by examining participants’ search behaviour across three increasingly complex tasks.
MWL was subjectively rated by participants, and blood oxygenation
changes in the prefrontal cortex were measured using functional
near-infrared spectroscopy (fNIRS).
Our results revealed a significant difference between verbalisers
and imagers in search behaviour. In particular, verbalisers preferred
a Sporadic navigation style and adopted the Scanning strategy as
they processed information, according to their viewing and bookmarking patterns, whereas imagers preferred the Structured navigation style and reading information in detail. The fNIRS data
showed that verbalisers had significantly higher blood oxygenation in the prefrontal cortex when using the same search interface,
suggesting a higher MWL than imagers. When based on task complexity bias, the search time significantly increased as task complexity increased, but there were no significant differences in search
behaviours. Our study indicated that VI cognitive styles have a
noticeable and stronger impact on users’ searching behaviour and
their MWL when interacting with the same interface than task complexity, which can be considered further in future search behaviour
studies and search user interface design.

Posted on

Horia Maior – new paper

Adaptive Human-Swarm Interaction based on Workload Measurement using Functional Near-Infrared Spectroscopy

One of the challenges of human-swarm interaction (HSI) is how to manage the operator’s workload. In order to do this, we propose a novel neurofeedback technique for the realtime measurement of workload using functional near-infrared spectroscopy (fNIRS). The objective is to develop a baseline
for workload measurement in human-swarm interaction using fNIRS and to develop an interface that dynamically adapts to the operator’s workload. The proposed method consists of using fNIRS device to measure brain activity, process this through a machine learning algorithm, and pass it on to the
HSI interface. By dynamically adapting the HSI interface, the swarm operator’s workload could be reduced and the performance improved.

Read more from this paper here

Posted on

Horia Maior – new paper – consumer wearable technologies

The CHI’24 Workshop on the Future of Cognitive Personal Informatics

While Human-Computer Interaction (HCI) has contributed to demonstrating that physiological measures can be used to detect cognitive changes, engineering and machine learning will bring these to application in consumer wearable technology. For HCI, many open questions remain, such as: What happens when this becomes a cognitive form of personal informatics? What goals do we have for our daily cognitive activity? How should such a complex concept be conveyed to users to be useful in their everyday lives? How can we mitigate potential ethical concerns? This is different to designing BCI interactions; we are concerned with understanding how people will live with consumer neurotechnology. This workshop will directly address the future of Cognitive Personal Informatics (CPI), by bringing together design, BCI and physiological data, ethics, and personal informatics researchers to discuss and set the research agenda in this inevitable future.

Read more from this paper here

 

Posted on

AI Safety Summit workshop

Horizon Transitional Assistant Professor Horia Maior shares his experience of facilitating a workshop on Ethics and Responsible Innovation in the application of AI within the nuclear energy sector at the AI Summit hosted by the UK Atomic Energy Authority and the Robotics and AI Collaboration (RAICo)..

“Together with Dr Virginia Portillo and Dr Pepita Barnard I had the privilege of facilitating a workshop on Ethics and Responsible Innovation in the application of AI within the nuclear energy sector.

The summit was nothing short of inspiring. It was an incredible opportunity to delve into the critical discussions surrounding AI safety and ethics, particularly in an industry as crucial as nuclear energy.

But what made the summit truly remarkable was the chance to connect with a diverse group of passionate researchers and practitioners. From academia and industry to the public sector, the breadth of knowledge, enthusiasm, and willingness to collaborate was genuinely inspiring.

I must also shout out to my University of Nottingham colleagues Jack Chaplin, and Giovanna Martinez Arellano who delivered two other enlightening workshops on AI Safety and AI Assurance, as well as colleagues from the Omnifactory® for the amazing facility tour provided on the day.

Reflecting on these amazing few days, I’m filled with gratitude for the opportunity to contribute to such vital conversations, to learn, network, and collaborate, and advance the ethical use of AI across different sectors.

Thank huge thank you to Horizon Digital Economy Research, UKRI Trustworthy Autonomous Systems (TAS) Hub and Responsible Ai UK  for supporting our work!

Thanks also to the UK Atomic Energy Authority, RAICo, the University of Nottingham, Phill Mulvana MSc FIET CMgr MCMI, David Branson III and everyone involved for an unforgettable summit.

 

Posted on

Privacy-preserving & machine-learned catchment models for national dietary surveillance via digital footprint data

Horizon’s Transitional Assistant Professor, Georgiana Nica-Avram has co-authored a paper ‘Privacy-preserving & machine-learned catchment models for national dietary surveillance via digital footprint data’ which was submitted to the 2022 IEEE International Conference on Big Data.

Abstract

Big data from food retail stores is increasingly being used for population dietary surveillance, epidemiological studies of diet-related diseases, and evaluations of public health interventions. However, for retail data to be useful it is necessary to understand the spatio-temporal variation of when and where food is purchased and consumed. While some customers willingly share home location data with retailers as part of loyalty programs such data is typically too fine-grained/sensitive to be applied for research purposes. The aim of this study was to analyse differences between privacy-preserving models and actual retail catchments, and investigate if machine learning techniques could improve the accuracy of such catchment models. Based on a UK-wide sample of 4 million grocery store loyalty card holders, covering 485 million transactions over 29 months (2019-2021) and distributed across 33,000 neighbourhoods (Lower Super Output Areas, or LSOA), the study demonstrates how models trained on geolocated data perform at predicting, per store, catchment areas which contain 50, 80, and 95% of its customers’ primary location. Through comparative assessment of machine learning approaches, we find better performance from tree-based models (RF, XGB) with the best performance from an XGB model achieving an R2 of 0.72 and MAE of 1.06. To conclude, we review variable importance measures using SHAP values and discuss the relative merits of including specific features when modeling catchment areas. © 2022 IEEE.