Qianchu Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qianchu Li has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Gary Eves
CAE, Homebush West, NSW 2140, Australia
1 shared publication - Heba El-Fiqi
School of Systems & Computing, University of New South Wales, Canberra, ACT 2612, Australia
1 shared publication - Oleksandra Molloy
School of Science, University of New South Wales
1 shared publication
Latest Publications
- Open Access
Applications of Machine Learning in Assessing Cognitive Load of Uncrewed Aerial System Operators and in Enhancing Training: A Systematic Review
This research is based on a systematic review of machine learning (ML) approaches for the cognitive load (CL) assessment of applications for unmanned aerial system (UAS) operator training. The review synthesises evidence on how ML techniques have been applied to assess CL using diverse data sources, including physiological signals (e.g., EEG, HRV), behavioural measures (e.g., eye-tracking), and performance indicators. It highlights the effectiveness of models such as Support Vector Machines (SVMs), Random Forests (RFs), and advanced deep learning (DL) architectures such as Long Short-Term Memory (LSTM), as well as how the use of different methods affects the performance of ML models, with studies reporting accuracies of up to 98%. The findings also indicate that, compared with traditional UAS training approaches, ML approaches can enhance training by providing adaptive assessment, with methodological factors such as model selection, data preprocessing, and validation being central to ML assessment performance. These findings highlight the value of accurate CL assessment as a foundation for adaptive training systems, supporting enhanced UAS operator performance and operational safety. By consolidating the methodological insights and identifying research gaps, this review provides valuable background information for advancing ML-based CL assessment and its integration into adaptive UAS operator training systems to enhance UAS operator training.
Open AccessApplications of Machine Learning in Assessing Cognitive Load of Uncrewed Aerial System Operators and in Enhancing Training: A Systematic Review
This research is based on a systematic review of machine learning (ML) approaches for the cognitive load (CL) assessment of applications for unmanned aerial system (UAS) operator training. The review synthesises evidence on how ML techniques have been applied to assess CL using diverse data sources, including physiological signals (e.g., EEG, HRV), behavioural measures (e.g., eye-tracking), and performance indicators. It highlights the effectiveness of models such as Support Vector Machines (SVMs), Random Forests (RFs), and advanced deep learning (DL) architectures such as Long Short-Term Memory (LSTM), as well as how the use of different methods affects the performance of ML models, with studies reporting accuracies of up to 98%. The findings also indicate that, compared with traditional UAS training approaches, ML approaches can enhance training by providing adaptive assessment, with methodological factors such as model selection, data preprocessing, and validation being central to ML assessment performance. These findings highlight the value of accurate CL assessment as a foundation for adaptive training systems, supporting enhanced UAS operator performance and operational safety. By consolidating the methodological insights and identifying research gaps, this review provides valuable background information for advancing ML-based CL assessment and its integration into adaptive UAS operator training systems to enhance UAS operator training.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 464-470
A Novel Approach for Balancing Accuracy and Interpretability in Neural Networks
Neural networks have transformed numerous domains, exhibiting unmatched performance when fitting dataset features to a single network or enhancing interpretability using distinct networks for each feature, known as Neural Additive Models (NAM). This paper presents the Grouped-NAM (GNAM) approach, aiming to find a balance between performance and interpretability by clustering features and allocating a unique network to each cluster. Our primary objective is to determine if GNAM can outperform NAM in model accuracy. Using k-means clustering for feature grouping, we evaluated GNAM to identify the ideal number of feature groups. The results highlight a discernible trade-off between accuracy and interpretability, influenced by factors such as feature significance and clarity in decision-making. The study pinpoints the optimal feature group count that outperforms NAM while preserving meaningful interpretability. These insights substantially contribute to the field of neural network modeling, emphasizing the importance of balancing performance and interpretability. GNAM presents itself as a promising framework that adeptly bridges this tradeoff.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 464-470
A Novel Approach for Balancing Accuracy and Interpretability in Neural Networks
Neural networks have transformed numerous domains, exhibiting unmatched performance when fitting dataset features to a single network or enhancing interpretability using distinct networks for each feature, known as Neural Additive Models (NAM). This paper presents the Grouped-NAM (GNAM) approach, aiming to find a balance between performance and interpretability by clustering features and allocating a unique network to each cluster. Our primary objective is to determine if GNAM can outperform NAM in model accuracy. Using k-means clustering for feature grouping, we evaluated GNAM to identify the ideal number of feature groups. The results highlight a discernible trade-off between accuracy and interpretability, influenced by factors such as feature significance and clarity in decision-making. The study pinpoints the optimal feature group count that outperforms NAM while preserving meaningful interpretability. These insights substantially contribute to the field of neural network modeling, emphasizing the importance of balancing performance and interpretability. GNAM presents itself as a promising framework that adeptly bridges this tradeoff.