Dissertation defence (Information and Communication Technology): PhD Muhammad Irfan
PhD Muhammad Irfan defends the dissertation in Information and Communication Technology titled “Computationally Efficient AI in Brain-Tumour MRI and Physiological Signals in Sleep and Emotion Analysis” at the University of Turku on 20 April 2026 at 12.00 (University of Turku, Educarium, EDU1, Assistentinkatu 5, Turku).
Opponent: Professor Theodoros Arvanitis, PhD (University of Birmingham, UK)
Custos: Professor Tomi Westerlund, PhD (University of Turku)
Summary of the Doctoral Dissertation:
In healthcare, diagnosing neurological and behavioural disorders depends on AI models that efficiently process complex data. However, many artificial intelligence (AI) models are too complex and resource-intensive, limiting their use in settings with limited computational power, battery capacity, or bandwidth.
This thesis aims to develop AI that is both reliable and efficient in resource-limited environments, thereby maximising patient benefit. This thesis presents three contributions in medical imaging and signal analysis. First, it introduces two convolutional operators, Fuzzy Atrous Convolution (FAC) and Fuzzy Sigmoid Convolution (FSC), for binary brain-tumour classification from magnetic resonance imaging (MRI). Both methods improve feature extraction while reducing the number of parameters compared to standard CNNs. Despite their compactness, both models achieve state-of-the-art (SOTA) results. The FSC model achieves 0.9917, 0.9975, and 0.9989 in binary classification accuracy on three datasets, with 100 times fewer parameters than transfer-learning models. The FAC model achieves 0.9883, 0.9967, and 0.9956, outperforming SOTA models with 300 times fewer parameters, showing efficiency in inference time and size.
Second, the thesis examines whether accurate neonatal sleep-stage classification can be achieved with reduced-channel EEG. Through multiview feature extraction, AdaptiSelect, and a data-reduction module, it reduces data transmission by 153.6 times while enabling full data reconstruction. On a four-year dataset, it achieves classification accuracy of 0.8116 (Kappa=0.7217) with one EEG channel and 0.8279 (Kappa=0.7470) with two channels under cross-validation. Leave-one-subject-out validation confirms its generalisability. It outperforms SOTA approaches in neonatal sleep analysis.
Third, the thesis explores lightweight emotion-recognition models using single-modality electrocardiography. Accurate emotion detection is vital in human-computer interaction, mental health, and neurorehabilitation, where continuous, reliable evaluation improves outcomes. For edge monitoring, models must be computationally efficient. The approach employs multidomain feature extraction & fusion, and a voting model for low-power, real-time emotion tracking, ideal for wearables. The tailored model achieves an average accuracy of 0.9559 on the POPANE dataset, outperforming the general model's 0.6992. Comparisons show consistent improvement over past research.
