Towards Trusted Cognitive Intelligence for User-centric Smart Systems


   Faculty of Computing, Engineering and the Built Environment

  Dr Matias Garcia-Constantino  Monday, February 26, 2024  Competition Funded PhD Project (Students Worldwide)

About the Project

Data Analytics has evolved from Descriptive (what has happened) and Diagnostic (why did it happen), to Predictive (what could happen) and Prescriptive (what action could be taken). It is currently in the process of shifting towards Cognitive Analytics, which aims to create cognitive capabilities by learning from interactions with humans, environments and artifacts.

Computational Intelligence (CI), predominantly built upon data analytics, has recently made significant progress owing to increased computation power, improved machine learning algorithm performance, and the availability of big data. It has shown huge potential and to some extent reached industrial strengths offering real-world deployment opportunities such as face-recognition-based security checks and image analysis-based medical diagnosis. Nevertheless, CI-based applications suffer from challenges around explainability and interpretability due to the opaque nature of learning algorithms. This can lead to the lack of trust and has been identified as a key barrier to the uptake and acceptability of AI innovations.

This project aims to address the aforementioned challenges by marrying strengths of computational intelligence, data analytics and human-level intelligence. It will develop models, algorithms, methods and technologies that enable and support the synergy, symbiosis, and augmentation of human and artificial intelligence. Specifically, the project will first develop symbolic modelling and representation of human-level cognition and decision-making processes, then explore two approaches to enhancing CI systems with explainable and interpretable capabilities. The first is to develop methods to bootstrap or train CI algorithms with the semantic, expandable cognitive models, thus making the CI-based learnt findings explainable and interpretable. The second approach is to view CI-based agent/systems and humans as a hybrid intelligent system combining machines’ strengths in effective and efficient discovery of implicit knowledge or hidden patterns from large-scale data, and humans’ advantage of conducting cognitive analysis such as reasoning and making instinct judgments under dynamic and multiple factors.

Computer Science (8)

References

1. S. Dhelim, H. Ning, F. Farha, L. Chen, IoT-Enabled Social Relationships Meet Artificial Social Intelligence, IEEE Internet of Things, DOI: 10.1109/JIOT.2021.3081556, 2021.
2. F. Yang, Z. Yu, L. Chen, J. Gu, Q. Li, B. Guo, Human-Machine Cooperative Video Anomaly Detection, Proceedings of the ACM on Human-Computer Interaction, vol. 4, issue CSCW3, Article no.274, 2021
3. L. Chen, H. Ning, C. Nugent, Z. Yu, Hybrid Human-Artificial Intelligence, IEEE Computer, 10.1109/MC.2020.2997573, 53(8):14-17, 2020.
4. M. Garcia-Constantino, A. Konios, M. A. Mustafa, C. Nugent and G. Morrison, "Ambient and Wearable Sensor Fusion for Abnormal Behaviour Detection in Activities of Daily Living," 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 2020, pp. 1-6.
5. L. Chen, C. Nugent, Human Activity Recognition and Behaviour Analysis For Cyber-Physical Systems in Smart Environments, Monograph, ISBN:978-3-030-19407-9, Springer, 2019.
6. M. Garcia-Constantino, A. Konios, C. Nugent, Modelling Activities of Daily Living with Petri nets, 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 2018, pp. 866-871.
7. J. Rafferty, CD Nugent, J. Liu, L. Chen, From Activity Recognition to Intention Recognition for Assisted Living within Smart Homes, IEEE Trans. on Human-Machine Systems, 47(3):368-379, 2017.
8. G. Azkune, A. Almeida, D. López-de-Ipiña, L. Chen, Extending Knowledge-driven Activity Models through Data-driven Learning techniques, Expert Systems with Applications, 42(6):3115-3128, 2015.
9. L. Chen, C. Nugent, G. Okeyo, An Ontology-based Hybrid Approach to Activity Modeling for Smart Homes, IEEE Trans. Human-Machine Syst., 44(1):92-105, 2014.
10. L. Chen, C. Nugent, H Wang, A Knowledge-Driven Approach to Activity Recognition in Smart Homes, IEEE Trans on Knowledge and Data Engineering, 24(6):961-974, 2012.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.